[
https://issues.apache.org/jira/browse/FLINK-1040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14206120#comment-14206120
]
ASF GitHub Bot commented on FLINK-1040:
---------------------------------------
Github user fhueske commented on a diff in the pull request:
https://github.com/apache/incubator-flink/pull/194#discussion_r20136871
--- Diff:
flink-examples/flink-java-examples/src/main/java/org/apache/flink/examples/java/relational/WebLogAnalysisWithoutType.java
---
@@ -0,0 +1,334 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.flink.examples.java.relational;
+
+
+import org.apache.flink.api.common.functions.CoGroupFunction;
+import org.apache.flink.api.common.functions.FilterFunction;
+import org.apache.flink.api.java.tuple.Tuple;
+import org.apache.flink.api.java.tuple.Tuple1;
+import org.apache.flink.api.java.tuple.Tuple2;
+import org.apache.flink.api.java.tuple.Tuple3;
+import org.apache.flink.util.Collector;
+import org.apache.flink.api.java.DataSet;
+import org.apache.flink.api.java.ExecutionEnvironment;
+import org.apache.flink.examples.java.relational.util.WebLogData;
+import org.apache.flink.examples.java.relational.util.WebLogDataGenerator;
+
+/**
+ * This program processes web logs and relational data.
+ * It implements the following relational query:
+ *
+ * <code><pre>
+ * SELECT
+ * r.pageURL,
+ * r.pageRank,
+ * r.avgDuration
+ * FROM documents d JOIN rankings r
+ * ON d.url = r.url
+ * WHERE CONTAINS(d.text, [keywords])
+ * AND r.rank > [rank]
+ * AND NOT EXISTS
+ * (
+ * SELECT * FROM Visits v
+ * WHERE v.destUrl = d.url
+ * AND v.visitDate < [date]
+ * );
+ * </pre></code>
+ *
+ * <p>
+ * Input files are plain text CSV files using the pipe character ('|') as
field separator.
+ * The tables referenced in the query can be generated using the {@link
WebLogDataGenerator} and
+ * have the following schemas
+ * <code><pre>
+ * CREATE TABLE Documents (
+ * url VARCHAR(100) PRIMARY KEY,
+ * contents TEXT );
+ *
+ * CREATE TABLE Rankings (
+ * pageRank INT,
+ * pageURL VARCHAR(100) PRIMARY KEY,
+ * avgDuration INT );
+ *
+ * CREATE TABLE Visits (
+ * sourceIP VARCHAR(16),
+ * destURL VARCHAR(100),
+ * visitDate DATE,
+ * adRevenue FLOAT,
+ * userAgent VARCHAR(64),
+ * countryCode VARCHAR(3),
+ * languageCode VARCHAR(6),
+ * searchWord VARCHAR(32),
+ * duration INT );
+ * </pre></code>
+ *
+ * <p>
+ * Usage: <code>WebLogAnalysis <documents path> <ranks path>
<visits path> <result path></code><br>
+ * If no parameters are provided, the program is run with default data
from {@link WebLogData}.
+ *
+ * <p>
+ * This example shows how to use:
+ * <ul>
+ * <li> tuple data types
+ * <li> projection and join projection
+ * <li> the CoGroup transformation for an anti-join
+ * </ul>
+ *
+ */
+@SuppressWarnings("serial")
+public class WebLogAnalysisWithoutType {
+
+ //
*************************************************************************
+ // PROGRAM
+ //
*************************************************************************
+
+ public static void main(String[] args) throws Exception {
+
+ if(!parseParameters(args)) {
+ return;
+ }
+
+ final ExecutionEnvironment env =
ExecutionEnvironment.getExecutionEnvironment();
+
+ // get input data
+ DataSet<Tuple2<String, String>> documents =
getDocumentsDataSet(env);
+ DataSet<Tuple3<Integer, String, Integer>> ranks =
getRanksDataSet(env);
+ DataSet<Tuple2<String, String>> visits = getVisitsDataSet(env);
+
+ // Retain documents with keywords
+ /*DataSet<Tuple1<String>> filterDocs = documents
+ .filter(new FilterDocByKeyWords())
+ .projection(0); */
--- End diff --
Why did you comment this block out?
> Make type() call in projections optional (or remove it)
> -------------------------------------------------------
>
> Key: FLINK-1040
> URL: https://issues.apache.org/jira/browse/FLINK-1040
> Project: Flink
> Issue Type: Improvement
> Components: Java API
> Reporter: Stephan Ewen
> Priority: Minor
> Labels: simple, starter
>
> I think the type() call should be optional. The compiler can also cast the
> data set directly and the result type is computed from the input types
> anyways.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
