Print diff to log file (if PDFBox creates different output)

portfolio-performance · Jan 6, 2025 · aeea8dd · aeea8dd
1 parent 78a48b0
commit aeea8dd
Show file tree

Hide file tree

Showing 3 changed files with 39 additions and 3 deletions.
diff --git a/name.abuchen.portfolio.ui/META-INF/MANIFEST.MF b/name.abuchen.portfolio.ui/META-INF/MANIFEST.MF
@@ -120,7 +120,8 @@ Require-Bundle: name.abuchen.portfolio;bundle-version="0.73.1",
  org.eclipse.e4.ui.css.core,
  org.eclipse.ui.themes,
  org.eclipse.jface,
- org.apache.httpcomponents.core5.httpcore5
+ org.apache.httpcomponents.core5.httpcore5,
+ io.github.java-diff-utils
 Automatic-Module-Name: name.abuchen.portfolio.ui
 Service-Component: OSGI-INF/name.abuchen.portfolio.ui.util.theme.ColorAndFontProviderImpl.xml,
  OSGI-INF/name.abuchen.portfolio.ui.theme.CustomThemeEngineManager.xml
diff --git a/...abuchen.portfolio.ui/src/name/abuchen/portfolio/ui/handlers/CreateTextFromPDFHandler.java b/...abuchen.portfolio.ui/src/name/abuchen/portfolio/ui/handlers/CreateTextFromPDFHandler.java
@@ -2,7 +2,9 @@
 
 import java.io.File;
 import java.io.IOException;
+import java.util.Arrays;
 import java.util.Random;
+import java.util.stream.Collectors;
 
 import jakarta.inject.Named;
 
@@ -18,6 +20,9 @@
 import org.eclipse.swt.widgets.Shell;
 import org.eclipse.swt.widgets.Text;
 
+import com.github.difflib.DiffUtils;
+import com.github.difflib.UnifiedDiffUtils;
+
 import name.abuchen.portfolio.datatransfer.pdf.PDFInputFile;
 import name.abuchen.portfolio.money.CurrencyUnit;
 import name.abuchen.portfolio.ui.Messages;
@@ -45,11 +50,31 @@ public void execute(@Named(IServiceConstants.ACTIVE_PART) MPart part,
         {
             File file = new File(fileDialog.getFilterPath(), fileName);
             PDFInputFile inputFile = new PDFInputFile(file);
+
+            // create text from PDF
             inputFile.convertPDFtoText();
+            var extractedText = inputFile.getText();
+            var pdfBoxVersion = inputFile.getPDFBoxVersion();
+
+            // check if the extracted text changed with the PDFBox version
+            inputFile.convertLegacyPDFtoText();
+            var legacyText = inputFile.getText();
+            var legacyPdfBoxVersion = inputFile.getPDFBoxVersion();
+            var isDifferent = !extractedText.equals(legacyText);
+
+            if (isDifferent)
+            {
+                var patch = DiffUtils.diff(legacyText, extractedText, null);
+                var unifiedDiff = UnifiedDiffUtils.generateUnifiedDiff(legacyPdfBoxVersion, pdfBoxVersion,
+                                Arrays.asList(legacyText.split("\n")), patch, 0);
+                PortfolioPlugin.info(
+                                inputFile.getName() + "\n\n" + unifiedDiff.stream().collect(Collectors.joining("\n")));
+            }
 
             StringBuilder textBuilder = new StringBuilder();
             textBuilder.append("```").append("\n");
-            textBuilder.append("PDFBox Version: ").append(inputFile.getPDFBoxVersion()) //
+            textBuilder.append("PDFBox Version: ").append(pdfBoxVersion)
+                            .append(isDifferent ? " != " + legacyPdfBoxVersion : "") //
                             .append("\n");
             textBuilder.append("Portfolio Performance Version: ")
                             .append(PortfolioPlugin.getDefault().getBundle().getVersion().toString()) //
@@ -62,7 +87,7 @@ public void execute(@Named(IServiceConstants.ACTIVE_PART) MPart part,
                             .append(System.getProperty("java.vm.vendor", "unknown")).append("\n");
 
             textBuilder.append("-----------------------------------------\n");
-            textBuilder.append(inputFile.getText().replace("\r", "")).append("\n");
+            textBuilder.append(extractedText).append("\n");
             textBuilder.append("```");
 
             String text = textBuilder.toString();

diff --git a/portfolio-target-definition/portfolio-target-definition.target b/portfolio-target-definition/portfolio-target-definition.target
@@ -325,5 +325,15 @@
 			</dependency>
 		</dependencies>
 	</location>
+	<location includeDependencyDepth="none" includeDependencyScopes="compile" includeSource="true" label="io.github.java-diff-utils" missingManifest="generate" type="Maven">
+		<dependencies>
+			<dependency>
+			    <groupId>io.github.java-diff-utils</groupId>
+			    <artifactId>java-diff-utils</artifactId>
+			    <version>4.15</version>
+				<type>jar</type>
+			</dependency>
+		</dependencies>
+	</location>
 </locations>
 </target>