Initial commit

This commit is contained in:
coolneng 2020-10-06 18:45:22 +02:00
commit fcbb4da4ba
Signed by: coolneng
GPG Key ID: 9893DA236405AF57
4 changed files with 108 additions and 0 deletions

1
.gitignore vendored Normal file
View File

@ -0,0 +1 @@
target

80
pom.xml Normal file
View File

@ -0,0 +1,80 @@
<?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>org.RI.P1</groupId>
<artifactId>P1</artifactId>
<version>1.0-SNAPSHOT</version>
<name>P1</name>
<!-- FIXME change it to the project's website -->
<url>http://www.example.com</url>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<maven.compiler.source>1.7</maven.compiler.source>
<maven.compiler.target>1.7</maven.compiler.target>
</properties>
<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.11</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-core</artifactId>
<version>1.22</version>
</dependency>
</dependencies>
<build>
<pluginManagement><!-- lock down plugins versions to avoid using Maven defaults (may be moved to parent pom) -->
<plugins>
<!-- clean lifecycle, see https://maven.apache.org/ref/current/maven-core/lifecycles.html#clean_Lifecycle -->
<plugin>
<artifactId>maven-clean-plugin</artifactId>
<version>3.1.0</version>
</plugin>
<!-- default lifecycle, jar packaging: see https://maven.apache.org/ref/current/maven-core/default-bindings.html#Plugin_bindings_for_jar_packaging -->
<plugin>
<artifactId>maven-resources-plugin</artifactId>
<version>3.0.2</version>
</plugin>
<plugin>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.8.0</version>
</plugin>
<plugin>
<artifactId>maven-surefire-plugin</artifactId>
<version>2.22.1</version>
</plugin>
<plugin>
<artifactId>maven-jar-plugin</artifactId>
<version>3.0.2</version>
</plugin>
<plugin>
<artifactId>maven-install-plugin</artifactId>
<version>2.5.2</version>
</plugin>
<plugin>
<artifactId>maven-deploy-plugin</artifactId>
<version>2.8.2</version>
</plugin>
<!-- site lifecycle, see https://maven.apache.org/ref/current/maven-core/lifecycles.html#site_Lifecycle -->
<plugin>
<artifactId>maven-site-plugin</artifactId>
<version>3.7.1</version>
</plugin>
<plugin>
<artifactId>maven-project-info-reports-plugin</artifactId>
<version>3.0.0</version>
</plugin>
</plugins>
</pluginManagement>
</build>
</project>

5
shell.nix Normal file
View File

@ -0,0 +1,5 @@
{ pkgs ? import <nixpkgs> { } }:
with pkgs;
mkShell { buildInputs = [ jdk11 maven ]; }

View File

@ -0,0 +1,22 @@
import java.io.File;
import org.apache.tika.Tika ;
public class EjemploSimple {
public static void main(String[] args) throws Exception {
// Creamos una instancia de Tika con la configuracion por defecto
Tika tika = new Tika();
// Se parsean los ficheros pasados como argumento y se extrae el contenido
for (String file : args) {
File f = new File(file);
// Detectamos el MIME tipo del fichero
String type = tika.detect(f);
System.out.println(file +":"+type);
// Extraemos el texto plano en un string
String text = tika.parseToString(f);
System.out.print(text);
}
}
}