milindjagre
/ pom.xml
Created
April 13, 2016 12:17
This pom.xml file is used for third party jar files involved in Writing PDF files using JAVA API
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| <?xml version="1.0" encoding="UTF-8"?> | |
| <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> | |
| <modelVersion>4.0.0</modelVersion> | |
| <groupId>com.milind</groupId> | |
| <artifactId>word-to-pdf</artifactId> | |
| <version>1.0</version> | |
| <packaging>jar</packaging> | |
| <properties> | |
| <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding> | |
| <maven.compiler.source>1.7</maven.compiler.source> |
milindjagre
/ ExcelDriver.java
Created
April 16, 2016 02:19
This is Driver Class for reading Excel File using MapReduce
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| /* * To change this license header, choose License Headers in Project Properties. | |
| * To change this template file, choose Tools | Templates | |
| * and open the template in the editor. */ | |
| package com.milind.mr.excel; | |
| /** | |
| * * @author milind | |
| */ | |
| import org.apache.hadoop.fs.Path; | |
| import org.apache.hadoop.mapreduce.Job; | |
| import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; |
milindjagre
/ csvtohive_withheader.sh
Created
May 6, 2016 08:41
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Assuming we are using hduser for doing Hadoop Operations | |
| cd /home/hduser | |
| # Loading .bashrc file in order to access HIVE Installation Directory Path | |
| source .bashrc | |
| # Removing already existing CSV SERDE JAR FILE | |
| rm csv-serde-1.1.2-0.11.0-all.jar | |
| # Downloading CSV SERDE JAR FILE during run time | |
| wget https://drone.io/github.com/ogrodnek/csv-serde/files/target/csv-serde-1.1.2-0.11.0-all.jar | |
| # Copying Downloaded CSV SERDE FILE to HIVE lib Directory | |
| cp csv-serde-1.1.2-0.11.0-all.jar $HIVE_HOME/lib |
milindjagre
/ csvtohive_withoutheader.sh
Created
May 6, 2016 09:17
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Assuming we are using hduser for doing Hadoop Operations | |
| cd /home/hduser | |
| # Loading .bashrc file in order to access HIVE Installation Directory Path | |
| source .bashrc | |
| # Removing already existing CSV SERDE JAR FILE | |
| rm csv-serde-1.1.2-0.11.0-all.jar | |
| # Downloading CSV SERDE JAR FILE during run time | |
| wget https://drone.io/github.com/ogrodnek/csv-serde/files/target/csv-serde-1.1.2-0.11.0-all.jar | |
| # Copying Downloaded CSV SERDE FILE to HIVE lib Directory | |
| cp csv-serde-1.1.2-0.11.0-all.jar $HIVE_HOME/lib |
milindjagre
/ xml_to_hive.txt
Created
May 9, 2016 09:31
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| STEP 1 : CREATING INPUT XML FILE WHICH WE WILL LOAD IN HIVE TABLE | |
| nano student.xml | |
| <student> <id>1</id> <name>Milind</name> <age>25</age> </student> | |
| <student> <id>2</id> <name>Ramesh</name> <age>Testing</age> </student> | |
| STEP 2 : LOG IN TO HIVE | |
| hive | |
| STEP 3 : CREATING HIVE TABLE |
milindjagre
/ ExcelInputFormat.java
Created
May 9, 2016 13:50
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| /* | |
| * To change this license header, choose License Headers in Project Properties. | |
| * To change this template file, choose Tools | Templates | |
| * and open the template in the editor. | |
| */ | |
| package com.milind.mr.excel; | |
| import java.io.IOException; | |
| import org.apache.hadoop.io.LongWritable; | |
| import org.apache.hadoop.io.Text; | |
| import org.apache.hadoop.mapreduce.InputSplit; |
milindjagre
/ ExcelMapper.java
Created
May 9, 2016 13:52
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| /* | |
| * To change this license header, choose License Headers in Project Properties. | |
| * To change this template file, choose Tools | Templates | |
| * and open the template in the editor. | |
| */ | |
| package com.milind.mr.excel; | |
| /** | |
| * | |
| * @author milind |
milindjagre
/ ExcelParser.java
Created
May 9, 2016 13:54
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| /* | |
| * To change this license header, choose License Headers in Project Properties. | |
| * To change this template file, choose Tools | Templates | |
| * and open the template in the editor. | |
| */ | |
| package com.milind.mr.excel; | |
| /** | |
| * | |
| * @author milind |
milindjagre
/ ExcelRecordReader.java
Created
May 9, 2016 13:57
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| /* | |
| * To change this license header, choose License Headers in Project Properties. | |
| * To change this template file, choose Tools | Templates | |
| * and open the template in the editor. | |
| */ | |
| package com.milind.mr.excel; | |
| /** | |
| * | |
| * @author milind |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| <?xml version="1.0" encoding="UTF-8"?> | |
| <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> | |
| <modelVersion>4.0.0</modelVersion> | |
| <groupId>com.milind</groupId> | |
| <artifactId>mr-excel</artifactId> | |
| <version>1.0</version> | |
| <packaging>jar</packaging> | |
| <properties> | |
| <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding> | |
| <maven.compiler.source>1.7</maven.compiler.source> |