main latex export functionality

src/main/java/org/texttechnologylab/project/gruppe_05_1/Main.java

@@ -34,11 +34,13 @@ public class Main {
     private static final FileObjectFactory xmlFactory = FileObjectFactory.getFactory();
     private static final MongoObjectFactory mongoFactory = MongoObjectFactory.getFactory();
 
+    public static final String RESOURCES_DIR = "src/main/resources";
     public static final String CONFIG_DIR = "src/main/resources/config";
     public static final String JAVALIN_TEMPLATE_DIR = "src/main/resources/templates";
     public static final String JAVALIN_STATIC_FILES_DIR = "src/main/resources/static";
     public static final String JCAS_SPEECHES_TYPESYSTEM_DIR = "src/main/resources/speeches/TypeSystem";
     public static final String MEMBER_IMAGES_DIR = "src/main/resources/membersOfParliamentImages/";
+    public static final String TEMP_EXPORT_DIR = "src/main/resources/tempExport/";
 
     public static void main(String[] args) throws Exception {
         UPLOAD_MEMBER_PHOTOS = Arrays.asList(args).contains("uploadMemberPhotos");

src/main/java/org/texttechnologylab/project/gruppe_05_1/database/MongoPprUtils.java

@@ -11,6 +11,7 @@ import com.mongodb.client.model.Projections;
 import io.javalin.http.Context;
 import org.bson.Document;
 import org.bson.conversions.Bson;
+import org.texttechnologylab.project.gruppe_05_1.database.domainimpl.mdb.Speaker_MongoDB_Impl;
 import org.texttechnologylab.project.gruppe_05_1.database.domainimpl.mdb.Speech_MongoDB_Impl;
 import org.texttechnologylab.project.gruppe_05_1.domain.html.HtmlSpeech;
 import org.texttechnologylab.project.gruppe_05_1.domain.html.Parlamentarier;
@@ -297,6 +298,15 @@ public class MongoPprUtils {
         return readParlamentarierDetailsFromSpeaker(doc);
     }
 
+    public static Speaker_MongoDB_Impl getSpeakerById(String id) {
+        Logger.debug("ID: " + id);
+         Document doc = MongoDBHandler.findFirstDocumentInCollection(getSpeakerCollection(), "_id", id);
+        Logger.debug("Speaker: " + doc);
+        Speaker_MongoDB_Impl speaker = new Speaker_MongoDB_Impl().createSpeakerMongoDBImpl(doc);
+        Logger.debug("Speaker parsed" + speaker);
+        return speaker;
+    }
+
 
     /**
      * Holt die Details eines Parlamentariers
@@ -623,7 +633,7 @@ public class MongoPprUtils {
      * @param key: Rede ID
      * @return
      */
-    public static HtmlSpeech getSpeechByKey(String key) {
+    public static HtmlSpeech getHTMLSpeechByKey(String key) {
         Document filter = new Document("speechKey", key);
         Document speechDoc = getSpeechCollection().find(filter).first();
         if (speechDoc == null) {
@@ -634,6 +644,18 @@ public class MongoPprUtils {
         return new HtmlSpeech(speechDoc);
     }
 
+    public static Speech getSpeechByKey(String key) {
+        Document filter = new Document("speechKey", key);
+        Document speechDoc = getSpeechCollection().find(filter).first();
+
+        if (speechDoc == null) {
+            Logger.error("Rede " + key + " nicht gefunden");
+            return null;
+        }
+
+        return new Speech_MongoDB_Impl(speechDoc, true);
+    }
+
     // getMemberPhoto
 
     /**

src/main/java/org/texttechnologylab/project/gruppe_05_1/database/domainimpl/mdb/Speaker_MongoDB_Impl.java

@@ -5,15 +5,60 @@ import org.texttechnologylab.project.gruppe_05_1.database.MongoDBHandler;
 import org.texttechnologylab.project.gruppe_05_1.database.MongoOperations;
 import org.texttechnologylab.project.gruppe_05_1.domain.speaker.Membership;
 import org.texttechnologylab.project.gruppe_05_1.domain.speaker.Speaker;
+import org.texttechnologylab.project.gruppe_05_1.util.Logger;
 
-import java.util.ArrayList;
-import java.util.HashMap;
-import java.util.List;
-import java.util.Map;
+import java.io.File;
+import java.io.FileOutputStream;
+import java.io.IOException;
+import java.time.LocalDate;
+import java.util.*;
 
+import static org.texttechnologylab.project.gruppe_05_1.Main.TEMP_EXPORT_DIR;
 import static org.texttechnologylab.project.gruppe_05_1.database.MongoPprUtils.getMemberPhoto;
 
 public class Speaker_MongoDB_Impl extends Speaker implements MongoOperations<Speaker> {
+    public Speaker_MongoDB_Impl createSpeakerMongoDBImpl(Document mongoDocument) {
+        this.setId(mongoDocument.getString("_id"));
+        this.setName(mongoDocument.getString("name"));
+        this.setFirstName(mongoDocument.getString("firstName"));
+        this.setTitle(mongoDocument.getString("title"));
+        Logger.debug("First part parsed succesfully");
+        this.setGeburtsdatum(parseTimestampSafely(mongoDocument.getDate("geburtsdatum")));
+        this.setGeburtsort(mongoDocument.getString("geburtsort"));
+        this.setSterbedatum(parseTimestampSafely(mongoDocument.getDate("sterbedatum")));
+        this.setGeschlecht(mongoDocument.getString("geschlecht"));
+        this.setBeruf(mongoDocument.getString("beruf"));
+        this.setAkademischertitel(mongoDocument.getString("akademischertitel"));
+        this.setFamilienstand(mongoDocument.getString("familienstand"));
+        this.setReligion(mongoDocument.getString("religion"));
+        this.setVita(mongoDocument.getString("vita"));
+        this.setParty(mongoDocument.getString("party"));
+
+        List<Document> memberships = (List<Document>) mongoDocument.get("memberships");
+        List<Membership> membershipList = new ArrayList<>();
+        for (Document membership : memberships) {
+            Membership membershipObj = new Membership();
+            membershipObj.setRole(membership.getString("role"));
+            membershipObj.setMember(membership.getString("member"));
+            membershipObj.setBegin(parseTimestampSafely(membership.getDate("begin")));
+            membershipObj.setEnd(parseTimestampSafely(membership.getDate("end")));
+            membershipObj.setLabel(membership.getString("label"));
+            membershipObj.setWp(membership.getInteger("wp"));
+            membershipList.add(membershipObj);
+        }
+        this.setMemberships(membershipList);
+
+        return this;
+    }
+
+    public LocalDate parseTimestampSafely(Date timestamp) {
+        try {
+            Logger.debug("Parsing timestamp: " + timestamp);
+            return LocalDate.parse(timestamp.toString());
+        } catch (Exception e) {
+            return null;
+        }
+    }
     @Override
     public Document createEntity(Speaker entity) {
 
@@ -48,4 +93,42 @@ public class Speaker_MongoDB_Impl extends Speaker implements MongoOperations<Spe
         }
         return result;
     }
+
+    public String toTeX() {
+        // Save image to file
+        // Decode the Base64 string to a byte array
+        byte[] imageBytes = Base64.getDecoder().decode(getMemberPhoto(this.getId()));
+
+        // Define the output PNG file
+        File outputFile = new File(TEMP_EXPORT_DIR + "speaker_photo_" + this.getId() + ".png");
+
+        // Write the decoded byte array to the file
+        try (FileOutputStream fos = new FileOutputStream(outputFile)) {
+            fos.write(imageBytes);
+            System.out.println("PNG file has been saved successfully.");
+        } catch (IOException e) {
+            Logger.error("Failed to save member PNG file.");
+            Logger.error(e.getMessage());
+        }
+
+        // Spkeaer metadata LaTeX code with image, Full Name + title, party, religion, dob, dod, pob, gender, ID
+        StringBuilder tex = new StringBuilder();
+        // image on the left, metadata on the right
+        tex.append("\\begin{minipage}{0.5\\textwidth}\n");
+        tex.append("\\includegraphics[width=0.5\\textwidth]{").append(outputFile.getName()).append("}\n");
+        tex.append("\\end{minipage}\n");
+        tex.append("\\begin{minipage}{0.5\\textwidth}\n");
+        tex.append("\\begin{tabular}{r l}\n");
+        tex.append("Name & ").append(this.getTitle()).append(" ").append(this.getFirstName()).append(" ").append(this.getName()).append("\\\\\n");
+        tex.append("Fraktion & ").append(this.getParty()).append("\\\\\n");
+        tex.append("Religion & ").append(this.getReligion()).append("\\\\\n");
+        tex.append("Geburtsdatum & ").append(this.getGeburtsdatum()).append("\\\\\n");
+        if (this.getSterbedatum() != null) {
+            tex.append("Sterbedatum & ").append(this.getSterbedatum()).append("\\\\\n"); // only show if available
+        }
+        tex.append("Geburtsort & ").append(this.getGeburtsort()).append("\\\\\n");
+        tex.append("\\end{tabular}\n");
+        tex.append("\\end{minipage}\n");
+        return tex.toString();
+    }
 }

src/main/java/org/texttechnologylab/project/gruppe_05_1/database/domainimpl/mdb/Speech_MongoDB_Impl.java

@@ -9,6 +9,7 @@ import org.texttechnologylab.project.gruppe_05_1.database.domainimpl.mdb.speechl
 import org.texttechnologylab.project.gruppe_05_1.database.domainimpl.mdb.speechline.Line_MongoDB_Impl;
 import org.texttechnologylab.project.gruppe_05_1.database.domainimpl.mdb.speechline.Speaker_MongoDB_Impl;
 import org.texttechnologylab.project.gruppe_05_1.xml.speeches.Impls.Speech_File_Impl;
+import org.texttechnologylab.project.gruppe_05_1.xml.speeches.Interfaces.Content;
 import org.texttechnologylab.project.gruppe_05_1.xml.speeches.Interfaces.Speech;
 
 
@@ -80,7 +81,16 @@ public class Speech_MongoDB_Impl  extends Speech_File_Impl implements Speech {
     public String toTeX() {
         StringBuilder tex = new StringBuilder();
 
-        tex.append("");
+        tex.append("\\subsection*{NLP Metadata}\n");
+
+        tex.append("[Graphs] //TODO: Implement\n");
+
+        tex.append("\\subsection*{Speech Content}\n");
+
+        // Add content block of speeches
+        for (Content content: this.getSpeechContents()) {
+            tex.append(content.toTeX());
+        }
 
 
         return tex.toString();

src/main/java/org/texttechnologylab/project/gruppe_05_1/database/domainimpl/mdb/speechline/Comment_MongoDB_Impl.java

@@ -14,4 +14,8 @@ public class Comment_MongoDB_Impl extends Comment_File_Impl implements Comment {
                 mongoDocument.getString("commentatorName"),
                 mongoDocument.getString("comment"));
     }
+
+    public String toTeX() {
+        return "\\textcolor{blue}{Kommentar}: " + this.getComment() + "\\\\\n";
+    }
 }

src/main/java/org/texttechnologylab/project/gruppe_05_1/database/domainimpl/mdb/speechline/Line_MongoDB_Impl.java

@@ -12,4 +12,8 @@ public class Line_MongoDB_Impl extends Line_File_Impl implements Line {
                 mongoDocument.getInteger("speechId"),
                 mongoDocument.getString("content"));
     }
+
+    public String toTeX() {
+        return this.getContent() + "\\\\\n";
+    }
 }

src/main/java/org/texttechnologylab/project/gruppe_05_1/database/domainimpl/mdb/speechline/Speaker_MongoDB_Impl.java

@@ -13,4 +13,8 @@ public class Speaker_MongoDB_Impl extends Speaker_File_Impl implements Speaker {
                 mongoDocument.getString("speakerName"),
                 mongoDocument.getString("fraction"));
     }
+
+    public String toTeX() {
+        return "\\textcolor{blue}{Redner/Rednerin}: " + this.getSpeakerName() + "\\\\\n";
+    }
 }

src/main/java/org/texttechnologylab/project/gruppe_05_1/export/TeXUtil.java

@@ -0,0 +1,119 @@
+package org.texttechnologylab.project.gruppe_05_1.export;
+
+import org.texttechnologylab.project.gruppe_05_1.database.domainimpl.mdb.Speaker_MongoDB_Impl;
+import org.texttechnologylab.project.gruppe_05_1.util.Logger;
+import org.texttechnologylab.project.gruppe_05_1.xml.speeches.Interfaces.Speech;
+
+import java.io.*;
+import java.nio.charset.StandardCharsets;
+import java.nio.file.FileVisitResult;
+import java.nio.file.Files;
+import java.nio.file.Path;
+import java.nio.file.SimpleFileVisitor;
+import java.nio.file.attribute.BasicFileAttributes;
+import java.time.LocalDateTime;
+import java.time.format.DateTimeFormatter;
+import java.util.Arrays;
+import java.util.Base64;
+
+import static org.texttechnologylab.project.gruppe_05_1.Main.RESOURCES_DIR;
+import static org.texttechnologylab.project.gruppe_05_1.Main.TEMP_EXPORT_DIR;
+import static org.texttechnologylab.project.gruppe_05_1.database.MongoPprUtils.*;
+
+public class TeXUtil {
+    private static String BEGIN_DOCUMENT = "\\begin{document}";
+    private static String END_DOCUMENT = "\\end{document}";
+
+    public static String getSpeechToTexComponent(String speechId) {
+        Speech speech = getSpeechByKey(speechId);
+
+        Logger.debug("Speech ID: " + speechId);
+        Logger.debug("Speech: " + speech);
+
+        Speaker_MongoDB_Impl speaker = getSpeakerById(String.valueOf(speech.getSpeakerId()));
+
+        Logger.debug("Speaker: " + speaker);
+
+        StringBuilder tex = new StringBuilder();
+
+        tex.append(speaker.toTeX());
+
+        tex.append(speech.toTeX());
+
+        Logger.debug("TeX: " + tex);
+
+        return tex.toString();
+    }
+
+    public static String getExportedSpeechBase64StringBySpeechId(String speechId) throws IOException, InterruptedException {
+        // Read preamble from resources directory tex/preamble.tex
+        String preamble = Files.readString(new File(RESOURCES_DIR, "tex/preamble.tex").toPath()).replace("$$EXPORTCATEGORY$$", "Speech " + speechId);
+        return convertTexToBase64PDF(preamble + BEGIN_DOCUMENT + getSpeechToTexComponent(speechId) + END_DOCUMENT);
+    }
+
+    public static String convertTexToBase64PDF(String tex) throws IOException, InterruptedException {
+        // Create a temporary directory
+        File tempDir = new File(TEMP_EXPORT_DIR);
+        if (!tempDir.exists()) {
+            tempDir.mkdir();
+        }
+
+        // Format tex string to UTF-8
+        tex = new String(tex.getBytes("UTF-8"));
+        tex = tex.replaceAll("[^\\x00-\\x7F]", "");  // Replace all non-ASCII characters
+
+        // Local datetime stamp
+        String dateTime = DateTimeFormatter.ofPattern("yyyy-MM-dd_HH-mm-ss").format(LocalDateTime.now());
+        // Write the LaTeX content to a temporary .tex file
+        File texFile = new File(tempDir, "speech_export" + dateTime + ".tex");
+        try (BufferedWriter writer = new BufferedWriter(new FileWriter(texFile, StandardCharsets.UTF_8))) {
+            writer.write(tex);
+        }
+
+        // Run pdflatex to generate the .pdf file
+        String command = "pdflatex -output-directory=" + tempDir.getAbsolutePath() + " " + texFile.getAbsolutePath();
+        Process process = Runtime.getRuntime().exec(command);
+
+
+        BufferedReader stdInput = new BufferedReader(new InputStreamReader(process.getInputStream()));
+        System.out.println("Standard Output:");
+        String s;
+        while ((s = stdInput.readLine()) != null) {
+            Logger.debug(s);
+        }
+        Logger.debug("LaTeX Process ended with exit code " + process.waitFor());
+
+        // Path to the generated PDF file
+        File pdfFile = new File(tempDir, "speech_export" + dateTime + ".pdf");
+
+        // Check if the PDF was created
+        if (!pdfFile.exists()) {
+            throw new IOException("PDF generation failed.");
+        }
+
+        // Read the PDF file into a byte array
+        byte[] pdfBytes = Files.readAllBytes(pdfFile.toPath());
+
+        // Convert the byte array to a Base64 encoded string
+        return Base64.getEncoder().encodeToString(pdfBytes);
+    }
+
+    public static void deleteTeXTempDirContents() throws IOException {
+        // Walk through the directory
+        Files.walkFileTree(Path.of(TEMP_EXPORT_DIR), new SimpleFileVisitor<Path>() {
+            @Override
+            public FileVisitResult visitFile(Path file, BasicFileAttributes attrs) throws IOException {
+                // Delete file
+                Files.delete(file);
+                return FileVisitResult.CONTINUE;
+            }
+
+            @Override
+            public FileVisitResult postVisitDirectory(Path dir, IOException exc) throws IOException {
+                // Delete the directory after its contents are deleted
+                Files.delete(dir);
+                return FileVisitResult.CONTINUE;
+            }
+        });
+    }
+}

src/main/java/org/texttechnologylab/project/gruppe_05_1/rest/RESTHandler.java

@@ -65,5 +65,9 @@ public class RESTHandler {
         app.get("/reden/{id}/{redeId}", SpeechController::showSpeech);      // zeige eine bestimmte Rede des Parlamentariers an
 
         app.get("/reden", SpeechController::listAllSpeeches);      // zeige alle Reden an (Filtern möglich)
+
+        app.get("/export/speech/{id}", SpeechesExportController::exportSpeech);      // exportiere eine Rede als PDF
+        //app.get("/portfolio/{id}/export", SpeechesExportController::exportSpeechesFromParlamentarier);      // exportiere alle Reden eines Parlamentariers als PDF
+        //app.get("/topic/{topic}/export", SpeechesExportController::exportSpeechesWithTopic);      // exportiere alle Reden zu einem Thema als PDF
     }
 }

src/main/java/org/texttechnologylab/project/gruppe_05_1/rest/SpeechController.java

@@ -72,7 +72,7 @@ public class SpeechController {
 
         Map<String, Object> attributes = new HashMap<>();
 
-        HtmlSpeech speech = MongoPprUtils.getSpeechByKey(redeId);
+        HtmlSpeech speech = MongoPprUtils.getHTMLSpeechByKey(redeId);
         if (speech == null) {
             attributes.put("error", "Rede " + redeId + " nicht vorhanden");
             ctx.render("speech.ftl", attributes);

src/main/java/org/texttechnologylab/project/gruppe_05_1/rest/SpeechesExportController.java

@@ -0,0 +1,44 @@
+package org.texttechnologylab.project.gruppe_05_1.rest;
+
+import io.javalin.http.Context;
+import io.javalin.openapi.HttpMethod;
+import io.javalin.openapi.OpenApi;
+import io.javalin.openapi.OpenApiResponse;
+import org.texttechnologylab.project.gruppe_05_1.util.Logger;
+
+import java.io.ByteArrayInputStream;
+import java.io.IOException;
+import java.util.Base64;
+
+import static org.texttechnologylab.project.gruppe_05_1.export.TeXUtil.*;
+
+public class SpeechesExportController {
+    @OpenApi(
+            summary = "Get a speech as a PDF",
+            description = "Returns a LaTeX generated pdf of a selected speech",
+            operationId = "getSpeechExport",
+            path = "/export/speech/{id}",
+            methods = HttpMethod.GET,
+            tags = {"Export", "Speeches", "PDF"},
+            responses = {
+                    @OpenApiResponse(status = "200")
+            })
+    public static void exportSpeech(Context ctx) throws IOException {
+        byte[] pdfBytes = new byte[0];
+        try {
+            pdfBytes = Base64.getDecoder().decode(getExportedSpeechBase64StringBySpeechId(ctx.pathParam("id")));
+        } catch (Exception e) {
+            Logger.error("Failed to generate Export of Speech with ID " + ctx.pathParam("id"));
+            Logger.error(e.getMessage());
+        }
+
+        // Set the response content type to PDF
+        ctx.contentType("application/pdf");
+
+        // Send the PDF as a response
+        ctx.result(new ByteArrayInputStream(pdfBytes));
+
+        // delete the temporary folder
+        deleteTeXTempDirContents();
+    }
+}

src/main/java/org/texttechnologylab/project/gruppe_05_1/xml/speeches/Impls/Comment_File_Impl.java

@@ -42,4 +42,9 @@ public class Comment_File_Impl implements Content, Comment {
     public MongoDBEntryType getType() {
         return MongoDBEntryType.SPEECH_COMMENT;
     }
+
+    @Override
+    public String toTeX() {
+        return "\\textcolor{blue}{Kommentar}: " + this.getComment() + "\\\n";
+    }
 }

src/main/java/org/texttechnologylab/project/gruppe_05_1/xml/speeches/Impls/Line_File_Impl.java

@@ -34,4 +34,9 @@ public class Line_File_Impl implements Content, Line {
     public MongoDBEntryType getType() {
         return MongoDBEntryType.SPEECH_LINE;
     }
+
+    @Override
+    public String toTeX() {
+        return this.getContent() + "\\\n";
+    }
 }

src/main/java/org/texttechnologylab/project/gruppe_05_1/xml/speeches/Impls/Speaker_File_Impl.java

@@ -49,4 +49,9 @@ public class Speaker_File_Impl implements Content, Speaker {
     public MongoDBEntryType getType() {
         return MongoDBEntryType.SPEECH_SPEAKER;
     }
+
+    @Override
+    public String toTeX() {
+        return "\\textcolor{blue}{Redner/Rednerin}: " + this.getSpeakerName() + "\\\n";
+    }
 }

src/main/java/org/texttechnologylab/project/gruppe_05_1/xml/speeches/Impls/Speech_File_Impl.java

@@ -103,4 +103,22 @@ public class Speech_File_Impl implements Speech {
         return null;
     }
 
+    @Override
+    public String toTeX() {
+        StringBuilder tex = new StringBuilder();
+
+        tex.append("\\NLP Metadata\\\n");
+
+        tex.append("[Graphs] //TODO: Implement\n");
+
+        tex.append("\\subsection*{Speech Content}\n");
+
+        // Add content block of speeches
+        for (Content content: this.getSpeechContents()) {
+            tex.append(content.toTeX());
+        }
+
+
+        return tex.toString();
+    }
 }

src/main/java/org/texttechnologylab/project/gruppe_05_1/xml/speeches/Interfaces/Content.java

@@ -24,4 +24,11 @@ public interface Content {
      * @return The speech ID.
      */
     int getSpeechId();
+
+    /**
+     * Returns the content as LaTeX.
+     *
+     * @return The content.
+     */
+    String toTeX();
 }

src/main/java/org/texttechnologylab/project/gruppe_05_1/xml/speeches/Interfaces/Speech.java

@@ -85,4 +85,6 @@ public interface Speech {
     String getFullText();
 
     JCas toCas() throws UIMAException;
+
+    String toTeX();
 }