Marmelator/layout-parser
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 289 Wiki Activity

RED-7607 - Rotating pages leads to lost annotations (RM & DM)

Browse Source 
- fix PMD findings
This commit is contained in:
Corina Olariu 2023-10-04 14:09:46 +03:00
parent b8ef55e6e2
commit f2c0991987
2 changed files with 25 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/utils/MarkedContentUtils.java
View File

@ -9,6 +9,7 @@ import org.apache.pdfbox.text.TextPosition;
import java.awt.geom.Rectangle2D;
import java.util.Collection;
import java.util.Collections;
import java.util.List;
import java.util.Map;
import java.util.stream.Collectors;
@ -22,7 +23,7 @@ public class MarkedContentUtils {
public List<Rectangle2D> getMarkedContentBboxPerLine(List<PDMarkedContent> markedContents, String subtype) {
if (markedContents == null) {
return null;
return Collections.emptyList();
}
var markedContentByYPosition = markedContents.stream()
@ -37,7 +38,7 @@ public class MarkedContentUtils {
.collect(Collectors.groupingBy(TextPosition::getY));
if (markedContentByYPosition.isEmpty()) {
return null;
return Collections.emptyList();
}
return markedContentByYPosition.values().stream()

25
layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/graph/ExtractMarkedContentTest.java
View File

@ -53,7 +53,9 @@ public class ExtractMarkedContentTest {
@SneakyThrows
public void testExtractTestWPhromma() throws IOException {
System.out.printf("\n\n===\n%s\n===\n", "testWPhromma.pdf");
PDDocument document = Loader.loadPDF(new ClassPathResource("files/bdr/Drucksache_19_9865.pdf").getFile());
PDDocument document = null;
try {
document = Loader.loadPDF(new ClassPathResource("files/bdr/Drucksache_19_9865.pdf").getFile());
Map<PDPage, Map<Integer, PDMarkedContent>> markedContents = new HashMap<>();
@ -70,6 +72,10 @@ public class ExtractMarkedContentTest {
PDStructureNode root = document.getDocumentCatalog().getStructureTreeRoot();
showStructure(root, markedContents);
} finally {
if (null != document )
document.close();
}
}
/**
@ -87,7 +93,10 @@ public class ExtractMarkedContentTest {
@Test
public void testExtractResMultipage() throws IOException {
System.out.printf("\n\n===\n%s\n===\n", "res_multipage.pdf");
PDDocument document = Loader.loadPDF(new ClassPathResource("files/bdr/Drucksache_19_9865.pdf").getFile());
PDDocument document = null;
try {
document = Loader.loadPDF(new ClassPathResource("files/bdr/Drucksache_19_9865.pdf").getFile());
Map<PDPage, Map<Integer, PDMarkedContent>> markedContents = new HashMap<>();
@ -104,6 +113,10 @@ public class ExtractMarkedContentTest {
PDStructureNode root = document.getDocumentCatalog().getStructureTreeRoot();
showStructure(root, markedContents);
} finally {
if (document != null)
document.close();
}
}
/**
@ -121,7 +134,9 @@ public class ExtractMarkedContentTest {
@Test
public void testExtractDailyReport() throws IOException {
System.out.printf("\n\n===\n%s\n===\n", "Daily Report.pdf");
PDDocument document = Loader.loadPDF(new ClassPathResource("files/bdr/Drucksache_19_9865.pdf").getFile());
PDDocument document = null;
try {
document = Loader.loadPDF(new ClassPathResource("files/bdr/Drucksache_19_9865.pdf").getFile());
Map<PDPage, Map<Integer, PDMarkedContent>> markedContents = new HashMap<>();
@ -138,7 +153,11 @@ public class ExtractMarkedContentTest {
PDStructureNode root = document.getDocumentCatalog().getStructureTreeRoot();
showStructure(root, markedContents);
} finally {
if (null != document)
document.close();
}
}
/**
* @see #testExtractTestWPhromma()