Save documents and authors in reference list of the PDF file

src/main/java/com/dre0059/articleprocessor/controller/FileUploadController.java

@@ -3,6 +3,7 @@ package com.dre0059.articleprocessor.controller;
 import com.dre0059.articleprocessor.GrobidClient;
 import com.dre0059.articleprocessor.service.HeaderService;
 
+import com.dre0059.articleprocessor.service.ReferenceService;
 import org.springframework.http.ResponseEntity;
 import org.springframework.stereotype.Controller;
 import org.springframework.ui.Model;
@@ -18,18 +19,12 @@ import java.io.IOException;
 public class FileUploadController {
     private final GrobidClient grobidClient;
     private final HeaderService headerService;
+    private final ReferenceService referenceService;
 
-    //private final DocumentRepository metadataRepository;
-    //private final ReferenceRepository referenceRepository;
-    //private final MetadataParser metadataParser;
-    //private static final Logger logger = LoggerFactory.getLogger(FileUploadController.class);
-
-    public FileUploadController(GrobidClient grobidClient, HeaderService headerService/*, DocumentRepository metadataRepository, ReferenceRepository referenceRepository, MetadataParser metadataParser*/) {
+    public FileUploadController(GrobidClient grobidClient, HeaderService headerService, ReferenceService referenceService) {
         this.grobidClient = grobidClient;
         this.headerService = headerService;
-      //  this.metadataRepository = metadataRepository;
-        //this.referenceRepository = referenceRepository;
-        //this.metadataParser = metadataParser;
+        this.referenceService = referenceService;
     }
 
     @GetMapping("/upload")
@@ -61,9 +56,10 @@ public class FileUploadController {
             String references = grobidClient.processReferences(tmpFile);
 
             headerService.processHeader(header);
+            referenceService.extractReferences(references);
 
             System.out.println(header);
-            //System.out.println(references);
+            System.out.println(references);
 
             tmpFile.delete();
 

src/main/java/com/dre0059/articleprocessor/service/HeaderService.java

@@ -22,6 +22,7 @@ public class HeaderService {
 
     private final DocumentRepository documentRepository;
     private final AuthorRepository authorRepository;
+    private final ReferenceService referenceService;
 
     //public Dokument(String title, Integer year, String doi, String abstractText, Integer pages, String publisher) {
 
@@ -36,9 +37,10 @@ public class HeaderService {
     private String author;
 
     @Autowired
-    public HeaderService(DocumentRepository documentRepository, AuthorRepository authorRepository) {
+    public HeaderService(DocumentRepository documentRepository, AuthorRepository authorRepository, ReferenceService referenceService) {
         this.documentRepository = documentRepository;
         this.authorRepository = authorRepository;
+        this.referenceService = referenceService;
     }
 
     public void processHeader(String header){
@@ -85,6 +87,10 @@ public class HeaderService {
 
         dokument.setAuthors(savedAuthors);
         this.documentRepository.save(dokument);
+
+        // set the document, which has the list of references
+        referenceService.setFromDocument(dokument);
+
     }
 
     private String parseHeaderFields(String header, String field){

src/main/java/com/dre0059/articleprocessor/service/ReferenceService.java

@@ -5,14 +5,140 @@ import com.dre0059.articleprocessor.repository.*;
 import jakarta.transaction.Transactional;
 import org.springframework.beans.factory.annotation.Autowired;
 import org.springframework.stereotype.Service;
+import org.w3c.dom.Document;
+import org.w3c.dom.Node;
+import org.w3c.dom.NodeList;
+import org.xml.sax.InputSource;
+import org.xml.sax.SAXException;
+
+import javax.xml.parsers.DocumentBuilder;
+import javax.xml.parsers.DocumentBuilderFactory;
+import javax.xml.parsers.ParserConfigurationException;
+import javax.xml.xpath.XPath;
+import javax.xml.xpath.XPathConstants;
+import javax.xml.xpath.XPathExpressionException;
+import javax.xml.xpath.XPathFactory;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.StringReader;
+import java.util.ArrayList;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+
+// TODO :
+//  1. uložiť prepojenie toDocument a fromDocument do tabuľky referencie
+//  2. vytiahnuť orderNumber z referencie (toto riešiť cez GROBID)
+//  3. aktuálne sa mi toDocument ukladá vždy ako nový.. ja ho potrebujem vyhľadať a na základe toho uložiť alebo prepojiť
 
 @Service
 public class ReferenceService {
+
+    private final DocumentRepository documentRepository;
+    private final AuthorRepository authorRepository;
+
+    //private String title;
+    private Integer year;
+    private String doi;
+    private String abstractText;
+    private Integer pages;
+    private String publisher;
+
+    private String author;
+    private List<Author> authorList = new ArrayList<>();
+
+    private Dokument fromDocument;
+    private Dokument toDocument;
+
+
     @Autowired
-    private ReferenceRepository referenceRepository;
+    public ReferenceService(DocumentRepository documentRepository, AuthorRepository authorRepository) {
+        this.documentRepository = documentRepository;
+        this.authorRepository = authorRepository;
+    }
+
+    public void setFromDocument(Dokument fromDocument) {
+        this.fromDocument = fromDocument;
+    }
+
+    public void extractReferences(String xmlTeiReferences) {
+        List<Author> databaseAuthors = this.authorRepository.findAll();
+        Map<String, Author> authorMap = new HashMap<>();
+
+        for (Author author : databaseAuthors) {
+            String key = author.getLastname().toLowerCase() + "," + author.getFirstname().toLowerCase();
+            authorMap.put(key, author);
+        }
+
+        try {
+            DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
+            factory.setNamespaceAware(true);
+            DocumentBuilder builder = factory.newDocumentBuilder();
+
+            InputSource inputSource = new InputSource(new StringReader(xmlTeiReferences));
+            Document doc = builder.parse(inputSource);
+
+            XPathFactory xpathFactory = XPathFactory.newInstance();
+            XPath xpath = xpathFactory.newXPath();
+            xpath.setNamespaceContext(new TEINamespaceContext());
 
-    @Transactional
-    public Reference saveReference(Reference reference) {
-        return referenceRepository.save(reference);
+            NodeList biblNodes = (NodeList) xpath.evaluate("//tei:biblStruct", doc, XPathConstants.NODESET);
+
+            for (int i = 0; i < biblNodes.getLength(); i++) {
+                Node biblNode = biblNodes.item(i);
+                Dokument toDokument = new Dokument();
+
+                // Extract title - toDocument
+                String title = xpath.evaluate(".//tei:title[@level='m' or @level='a']", biblNode);
+                toDokument.setTitle(title);
+
+                // Extract authors
+                NodeList authorNodes = (NodeList) xpath.evaluate(".//tei:author/tei:persName", biblNode, XPathConstants.NODESET);
+                List<Author> authors = new ArrayList<>();
+
+                for (int j = 0; j < authorNodes.getLength(); j++) {
+                    Node authorNode = authorNodes.item(j);
+
+                    String firstName = xpath.evaluate(".//tei:forename", authorNode);
+                    String lastName = xpath.evaluate(".//tei:surname", authorNode);
+
+                    String authorKey = lastName.toLowerCase() + "," + firstName.toLowerCase();
+
+                    if (authorMap.containsKey(authorKey)) {
+                        authors.add(authorMap.get(authorKey));
+                        System.out.println("Author: " + authorMap.get(authorKey) + " already exists in database.");
+                    } else {
+                        Author newAuthor = new Author(firstName, lastName);
+                        authors.add(newAuthor);
+                        authorMap.put(authorKey, newAuthor);
+                    }
+
+                    toDokument.setAuthors(authors);
+
+                    // Extract year of publication
+                    String yearStr = xpath.evaluate(".//tei:date[@type='published']/@when", biblNode);
+                    if (yearStr != null && !yearStr.isEmpty()) {
+                        try {
+                            toDokument.setPublicationYear(Integer.valueOf(yearStr));
+                        } catch (NumberFormatException e) {
+                            System.out.println("Error during converting year." + yearStr);
+                        }
+                    }
+
+                    // Extract publisher
+                    String publisher = xpath.evaluate(".//tei:publisher", biblNode);
+                    toDokument.setPublisher(publisher);
+
+                    this.documentRepository.save(toDokument);
+                    this.authorRepository.saveAll(authors);
+
+                }
+
+            }
+        } catch (Exception e) {
+            e.printStackTrace();
+        }
+    }
     }
-}
+
+

src/main/java/com/dre0059/articleprocessor/service/TEINamespaceContext.java

+package com.dre0059.articleprocessor.service;
+
+import javax.xml.namespace.NamespaceContext;
+import java.util.Iterator;
+
+public class TEINamespaceContext implements NamespaceContext {
+    @Override
+    public String getNamespaceURI(String prefix) {
+        if ("tei".equals(prefix)) {
+            return "http://www.tei-c.org/ns/1.0";
+        }
+        return null;
+    }
+
+    @Override
+    public String getPrefix(String namespaceURI) { return null; }
+    @Override
+    public Iterator<String> getPrefixes(String namespaceURI) { return null; }
+}

src/main/java/com/dre0059/articleprocessor/service/TEIparser.java

-package com.dre0059.articleprocessor.service;
+/*package com.dre0059.articleprocessor.service;
 
 import com.dre0059.articleprocessor.model.Author;
 import com.dre0059.articleprocessor.model.Dokument;
@@ -60,4 +60,6 @@ public class TEIparser {
         }
     }
 
-}
\ No newline at end of file
+}
+
+ */
\ No newline at end of file