Fixed issue with weird colors

This commit is contained in:
Timo Bejan 2023-08-18 16:21:45 +03:00
parent c09bb06da6
commit 83d39ba3a5
4 changed files with 25 additions and 1 deletions

4
.gitignore vendored
View File

@ -38,3 +38,7 @@ build/
### VS Code ###
.vscode/
gradlew.bat
gradlew
gradle.properties
gradle/

View File

@ -4,6 +4,7 @@ import java.awt.color.CMMException;
import java.awt.geom.Point2D;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import org.apache.pdfbox.contentstream.operator.Operator;
@ -219,7 +220,11 @@ public class PDFLinesTextStripper extends PDFTextStripper {
// This is a quick and dirt hack
// Happens for file 216.pdf
log.debug(e.getMessage());
return color.getComponents()[0] == 0 && color.getComponents()[1] == 0 && color.getComponents()[2] == 0 && color.getComponents()[1] == 1;
var result = true;
for (var component : color.getComponents()) {
result = result && component == 0;
}
return result;
}
}

View File

@ -1,5 +1,7 @@
package com.knecon.fforesight.service.layoutparser.server;
import static org.assertj.core.api.AssertionsForClassTypes.assertThat;
import java.awt.Color;
import java.io.File;
import java.io.FileInputStream;
@ -17,6 +19,7 @@ import org.apache.pdfbox.pdmodel.PDDocument;
import org.junit.jupiter.api.Disabled;
import org.junit.jupiter.api.Test;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.core.io.ClassPathResource;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.knecon.fforesight.service.layoutparser.internal.api.data.taas.ResearchDocumentData;
@ -56,6 +59,18 @@ public class BdrJsonBuildTest extends AbstractTest {
}
@Test
@SneakyThrows
public void testBDRFile199865() {
File file = new ClassPathResource("files/bdr/Drucksache_19_9865.pdf").getFile();
Document document = buildGraph(file);
ResearchDocumentData researchDocumentData = TaasDocumentDataMapper.fromDocument(document);
assertThat(researchDocumentData).isNotNull();
}
@Test
@Disabled
public void writeBDRDocumentData() throws IOException {