java + eclipse + mvn + pdfbox + apache poi

pom.xml

参考のまま作成した pom.xml ではうまく jar が作成できなかった。
直下の プロパティを削除すると上手く「jar-with-dependencies」が効くようになる。

<?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><PACKAGE_NAME></groupId>
	<artifactId>mvn_sample</artifactId>
	<version>0.0.1-SNAPSHOT</version>

	<name>mvn_sample</name>
	<!-- FIXME change it to the project's website -->
	<url>http://www.example.com</url>

	<properties>
		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
		<java.version>17</java.version>
		<maven.compiler.source>${java.version}</maven.compiler.source>
		<maven.compiler.target>${java.version}</maven.compiler.target>

	</properties>

	<dependencies>
		<dependency>
			<groupId>junit</groupId>
			<artifactId>junit</artifactId>
			<version>4.11</version>
			<scope>test</scope>
		</dependency>
		<dependency>
			<groupId>org.hamcrest</groupId>
			<artifactId>hamcrest-core</artifactId>
			<version>1.3</version>
			<scope>test</scope>
		</dependency>
		<dependency>
			<groupId>org.apache.commons</groupId>
			<artifactId>commons-lang3</artifactId>
			<version>3.1</version>
		</dependency>
		<dependency>
			<groupId>org.apache.pdfbox</groupId>
			<artifactId>pdfbox</artifactId>
			<version>2.0.32</version>
		</dependency>
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi</artifactId>
			<!-- 5.2.5 4.1.2 -->
			<version>5.3.0</version>
		</dependency>
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi-ooxml</artifactId>
			<version>5.3.0</version>
		</dependency>
	</dependencies>

	<build>
		<plugins>
			<plugin>
				<artifactId>maven-assembly-plugin</artifactId>
				<version>3.0.0</version>
				<executions>
					<execution>
						<id>make-assembly</id>
						<phase>package</phase>
						<goals>
							<goal>single</goal>
						</goals>
					</execution>
				</executions>
				<configuration>
					<descriptorRefs>
						<descriptorRef>jar-with-dependencies</descriptorRef>
					</descriptorRefs>
					<archive>
						<manifest>
							<mainClass><PACKAGE_NAME>.mvn_sample.App</mainClass>
						</manifest>
					</archive>
				</configuration>
			</plugin>
		</plugins>
	</build>
</project>

App.java

Java17,eclipse 2024-06での pdfbox とpoi 参考

package <PACKAGE_NAME>.mvn_sample;

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;

import org.apache.commons.lang3.StringUtils;
import org.apache.pdfbox.io.RandomAccessBufferedFileInputStream;
import org.apache.pdfbox.io.RandomAccessRead;
import org.apache.pdfbox.pdfparser.PDFParser;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.pdfbox.text.PDFTextStripperByArea;
import org.apache.poi.EncryptedDocumentException;
import org.apache.poi.ss.usermodel.Cell;
import org.apache.poi.ss.usermodel.Row;
import org.apache.poi.ss.usermodel.Sheet;
import org.apache.poi.ss.usermodel.Workbook;
import org.apache.poi.ss.usermodel.WorkbookFactory;
import org.apache.poi.ss.util.CellReference;

public class App {
	public static void main(String[] args) throws IOException {
		String exe_method = "";
		if (args.length == 0) {
			exe_method = "readXLS";
		} else {
			exe_method = args[0];
		}
		System.out.println("execute method : " + exe_method);
		switch (exe_method) {
		case "parsePDF":
			new App().parsePDF();
			break;
		case "parsePDF2":
			new App().parsePDF2();
			break;
		case "retvoid":
			new App().retvoid();
			break;
		case "readPDF":
			new App().readPDF();
			break;
		case "readXLS":
			new App().readXLS();
			break;
		default:
			String[] myArray = { "value1", "value2", "value3" };
			String ret = new App().join(myArray);
			System.out.println(ret);
		}

	}

	public void parsePDF() throws IOException {
		System.out.println("parsePDF");
		File file = new File("PATH\\sample_01.pdf");
		PDFParser pdfParser = new PDFParser(new org.apache.pdfbox.io.RandomAccessFile(file, "r"));
		pdfParser.parse(); // 分析
		PDDocument pdf = pdfParser.getPDDocument();
		PDFTextStripper stripper = new PDFTextStripper();
		System.out.println(stripper.getText(pdf));
	}

	public void parsePDF2() throws IOException {
		System.out.println("parsePDF2");
		RandomAccessRead rar = new RandomAccessBufferedFileInputStream(
				"PATH\\sample_01.pdf");
		PDFParser parser = new PDFParser(rar);
		parser.parse();
		PDDocument pdf = parser.getPDDocument();
		PDFTextStripper stripper = new PDFTextStripper();
		System.out.println(stripper.getText(pdf));

	}

	public void readPDF() throws IOException {
		System.out.println("readPDF");

		try (PDDocument document = PDDocument
				.load(new File("PATH\\sample_02.pdf"))) {
			System.out.println("PDDocument.load");

			document.getClass();

			PDFTextStripperByArea stripper = new PDFTextStripperByArea();
			stripper.setSortByPosition(true);

			PDFTextStripper tStripper = new PDFTextStripper();

			String pdfFileInText = tStripper.getText(document);
			//System.out.println("Text:" + st);

			// split by whitespace
			String lines[] = pdfFileInText.split("\\r?\\n");
			for (String line : lines) {
				System.out.println(line);
			}

		}

	}

	public void readXLS() throws EncryptedDocumentException, IOException {
		try (InputStream input = new FileInputStream("PATH\\sample_01.xls")) {
			//InputStream inp = new FileInputStream("workbook.xlsx");
			Workbook workbook = WorkbookFactory.create(input);
			Sheet sheet = workbook.getSheetAt(1);
			CellReference reference = new CellReference("A1");
			Row row = sheet.getRow(reference.getRow());
			Cell cell = row.getCell(reference.getCol());
			System.out.println(cell.getStringCellValue());

		}

	}

	public void retvoid() {
		System.out.println("retvoid");
	}

	public String join(String[] args) {
		return StringUtils.join(args, ",");
	}

}