Package cascading.tap

Examples of cascading.tap.Hfs

67
68
69
70
71
72
73
74
75
76
77
      input.add(t);
    }
    input.close();

    // Create flow to read from local file and insert into HBase.
    Tap source = new Hfs(new SequenceFile(inputFields), mHelper.manageTemporaryPath("input"));

    Pipe pipe = new Pipe("values");
    Fields keyFields = new Fields("num");
    Fields valueFields = new Fields("lower", "upper");
    Tap hBaseTap = new HBaseTap("testTable",
View Full Code Here
97
98
99
100
101
102
103
104
105
    File inputFile = new File(inputPath);
    if (inputFile.exists()) {
      throw new CascadingException("Input file " + inputPath + " already exists.");
    }
    Tap inputTap = new Hfs(new SequenceFile(fields), inputPath, SinkMode.REPLACE);
    TupleEntryCollector collector = inputTap.openForWrite(getJobConf());
    return collector;
  }
View Full Code Here
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
   */
  public Flow runFlow(Pipe[] tails, Map<String, Fields> inputs, Fields[] outputs,
                      String[] outputPaths) {
    Map<String, Tap> sources = new HashMap<String, Tap>();
    for (Map.Entry<String, Fields> input : inputs.entrySet()) {
      Tap tap = new Hfs(new SequenceFile(input.getValue()),
                        manageTemporaryPath(input.getKey()));
      sources.put(input.getKey(), tap);
    }

    if (tails.length != outputs.length) {
      System.err.println("size of tails should be same as outputs.");
      return null;
    }

    int i = 0;
    Map<String, Tap> sinks = new HashMap<String, Tap>();
    for (Fields output : outputs) {
      String sinkName = tails[i].getName();
      Tap sink = new Hfs(new SequenceFile(output), outputPaths[i]);
      sinks.put(sinkName, sink);
      i++;
    }

    Flow f = mFlowConnector.connect(sources, sinks, tails);
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
    // define what the input file looks like, "offset" is bytes from beginning
    TextLine input = new TextLine(new Fields("offset", "line"));

    // create SOURCE tap to read a resource from HDFS
    Tap logTap = new Hfs(input, inputPath);

    // create an assembly to parse an Apache log file and store on an HDFS cluster

    // declare the field names we will parse out of the log file
    Fields apacheFields = new Fields("resource");

    // define the regular expression to parse the log file with
    String apacheRegex = "^([^ ]*) +[^ ]* +[^ ]* +\\[([^]]*)\\] +\\\"([^ ]*) ([^ ]*) [^ ]*\\\" ([^ ]*) ([^ ]*).*$";

    // declare the groups from the above regex we want to keep. each regex group will be given
    // a field name from 'apacheFields', above, respectively
    int[] allGroups = {4};

    // create the parser
    RegexParser parser = new RegexParser(apacheFields, apacheRegex, allGroups);

    // create the import pipe element, with the name 'import', and with the input argument named "line"
    // replace the incoming tuple with the parser results
    // "line" -> parser -> "ts"
    Pipe pipeline = new Each("import", new Fields("line"), parser, Fields.RESULTS);


    // group the Tuple stream by the "word" value
    pipeline = new GroupBy(pipeline, new Fields("resource"));

    // For every Tuple group
    // count the number of occurrences of "word" and store result in
    // a field named "count"
    Aggregator count = new Count(new Fields("resource"));
    pipeline = new Every(pipeline, count);


    // create a SINK tap to write to the default filesystem
    // by default, TextLine writes all fields out
    Tap remoteLogTap = new Hfs(new TextLine(), outputPath, SinkMode.REPLACE);

    // set the current job jar
    Properties properties = new Properties();
    FlowConnector.setApplicationJarClass(properties, PopularLogResources.class);

View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
    Pipe importPipe = new Each( "import", new Fields( "line" ), parser );

    // create tap to read a resource from the local file system, if not an url for an external resource
    // Lfs allows for relative paths
    Tap logTap =
      inputPath.matches( "^[^:]+://.*" ) ? new Hfs( new TextLine(), inputPath ) : new Lfs( new TextLine(), inputPath );
    // create a tap to read/write from the default filesystem
    Tap parsedLogTap = new Hfs( apacheFields, logsPath );

    // connect the assembly to source and sink taps
    Flow importLogFlow = flowConnector.connect( logTap, parsedLogTap, importPipe );

    // create an assembly to parse out the time field into a timestamp
    // then count the number of requests per second and per minute

    // apply a text parser to create a timestamp with 'second' granularity
    // declares field "ts"
    DateParser dateParser = new DateParser( new Fields( "ts" ), "dd/MMM/yyyy:HH:mm:ss Z" );
    Pipe tsPipe = new Each( "arrival rate", new Fields( "time" ), dateParser, Fields.RESULTS );

    // name the per second assembly and split on tsPipe
    Pipe tsCountPipe = new Pipe( "tsCount", tsPipe );
    tsCountPipe = new GroupBy( tsCountPipe, new Fields( "ts" ) );
    tsCountPipe = new Every( tsCountPipe, Fields.GROUP, new Count() );

    // apply expression to create a timestamp with 'minute' granularity
    // declares field "tm"
    Pipe tmPipe = new Each( tsPipe, new ExpressionFunction( new Fields( "tm" ), "ts - (ts % (60 * 1000))", long.class ) );

    // name the per minute assembly and split on tmPipe
    Pipe tmCountPipe = new Pipe( "tmCount", tmPipe );
    tmCountPipe = new GroupBy( tmCountPipe, new Fields( "tm" ) );
    tmCountPipe = new Every( tmCountPipe, Fields.GROUP, new Count() );

    // create taps to write the results the default filesystem, using the given fields
    Tap tsSinkTap = new Hfs( new TextLine(), arrivalRateSecPath );
    Tap tmSinkTap = new Hfs( new TextLine(), arrivalRateMinPath );

    // a convenience method for binding taps and pipes, order is significant
    Map<String, Tap> sinks = Cascades.tapsMap( Pipe.pipes( tsCountPipe, tmCountPipe ), Tap.taps( tsSinkTap, tmSinkTap ) );

    // connect the assembly to the source and sink taps
View Full Code Here
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
    // a predefined pipe assembly that returns fields named "url" and "page"
    Pipe importPipe = new ImportCrawlDataAssembly( "import pipe" );

    // create the tap instances
    Tap localPagesSource = new Lfs( new TextLine(), inputPath );
    Tap importedPages = new Hfs( new SequenceFile( new Fields( "url", "page" ) ), pagesPath );

    // connect the pipe assembly to the tap instances
    Flow importPagesFlow = flowConnector.connect( "import pages", localPagesSource, importedPages, importPipe );

    // a predefined pipe assembly that splits the stream into two named "url pipe" and "word pipe"
    // these pipes could be retrieved via the getTails() method and added to new pipe instances
    SubAssembly wordCountPipe = new WordCountSplitAssembly( "wordcount pipe", "url pipe", "word pipe" );

    // create Hadoop sequence files to store the results of the counts
    Tap sinkUrl = new Hfs( new SequenceFile( new Fields( "url", "word", "count" ) ), urlsPath );
    Tap sinkWord = new Hfs( new SequenceFile( new Fields( "word", "count" ) ), wordsPath );

    // convenience method to bind multiple pipes and taps
    Map<String, Tap> sinks = Cascades.tapsMap( new String[]{"url pipe", "word pipe"}, Tap.taps( sinkUrl, sinkWord ) );

    // wordCountPipe will be recognized as an assembly and handled appropriately
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
    // define what the input file looks like, "offset" is bytes from beginning
    TextLine scheme = new TextLine( new Fields( "offset", "line" ) );

    // create SOURCE tap to read a resource from the local file system, if input is not an URL
    Tap logTap = inputPath.matches( "^[^:]+://.*" ) ? new Hfs( scheme, inputPath ) : new Lfs( scheme, inputPath );

    // create an assembly to parse an Apache log file and store on an HDFS cluster

    // declare the field names we will parse out of the log file
    Fields apacheFields = new Fields( "ip", "time", "method", "event", "status", "size" );

    // define the regular expression to parse the log file with
    String apacheRegex = "^([^ ]*) +[^ ]* +[^ ]* +\\[([^]]*)\\] +\\\"([^ ]*) ([^ ]*) [^ ]*\\\" ([^ ]*) ([^ ]*).*$";

    // declare the groups from the above regex we want to keep. each regex group will be given
    // a field name from 'apacheFields', above, respectively
    int[] allGroups = {1, 2, 3, 4, 5, 6};

    // create the parser
    RegexParser parser = new RegexParser( apacheFields, apacheRegex, allGroups );

    // create the import pipe element, with the name 'import', and with the input argument named "line"
    // replace the incoming tuple with the parser results
    // "line" -> parser -> "ts"
    Pipe importPipe = new Each( "import", new Fields( "line" ), parser, Fields.RESULTS );

    // create a SINK tap to write to the default filesystem
    // by default, TextLine writes all fields out
    Tap remoteLogTap = new Hfs( new TextLine(), outputPath, SinkMode.REPLACE );

    // set the current job jar
    Properties properties = new Properties();
    FlowConnector.setApplicationJarClass( properties, Main.class );

View Full Code Here
56
57
58
59
60
61
62
63
64
65
66
      return b.split(" ");
    }
  }

  public static void main( String[] args ) {
    Tap inputTap = new Hfs( new TextDelimited(
                                new Fields("docid", "body"), "\t" ),
                            args[0] );
    Tap outputTap = new StdoutTap();

    // create the flow
View Full Code Here
39
40
41
42
43
44
45
46
47
48
49
**/
public class HtmlSimhash {
  private static final Logger LOG = Logger.getLogger( HtmlSimhash.class );

  public static void main( String[] args ) {
    Tap inputTap = new Hfs( new TextDelimited(
                                new Fields("docid", "body"), "  " ),
                            args[0] );
    Tap outputTap = new StdoutTap();

    // create the flow
View Full Code Here
TOP

Related Classes of cascading.tap.Hfs

  • com.manning.hip.ch12.cascading.PopularLogResources
  • com.tellapart.cascading.hbase.SerializingHBaseSchemeTest
  • com.tellapart.test.cascading.ClusterTestHelper
  • loganalysis.Main
  • logparser.Main
  • simhash.examples.HtmlSimhash
  • simhash.examples.SimpleSimhash
  • wordcount.Main
    • Copyright © 2018 www.massapicom. All rights reserved.
    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.