Check duplicate DOI (#6333)

Co-authored-by: Jonas Moosmann <j.moosmann@gmx.de>
Co-authored-by: Stefan Kolb <stefan-kolb@web.de>
Co-authored-by: Stefan Kufer <stefan.kufer@diva-e.com>

CHANGELOG.md

@@ -18,6 +18,7 @@ Note that this project **does not** adhere to [Semantic Versioning](http://semve
 - We added support for basic markdown in custom formatted previews [#6194](https://github.com/JabRef/jabref/issues/6194)
 - We now show the number of items found and selected to import in the online search dialog. [#6248](https://github.com/JabRef/jabref/pull/6248)
 - We created a new install screen for macOS. [#5759](https://github.com/JabRef/jabref/issues/5759)
+- We added a new integrity check for duplicate DOIs. [koppor#339](https://github.com/koppor/jabref/issues/339)
 - We implemented an option to download fulltext files while importing. [#6381](https://github.com/JabRef/jabref/pull/6381)
 - We added a progress-indicator showing the average progress of background tasks to the toolbar. Clicking it reveals a pop-over with a list of running background tasks. [6443](https://github.com/JabRef/jabref/pull/6443)
 - We fixed the bug when strike the delete key in the text field. [#6421](https://github.com/JabRef/jabref/issues/6421)

src/main/java/org/jabref/gui/integrity/IntegrityCheckAction.java

@@ -53,6 +53,7 @@ protected List<IntegrityMessage> call() {
                 List<IntegrityMessage> result = new ArrayList<>();
 
                 ObservableList<BibEntry> entries = database.getDatabase().getEntries();
+                result.addAll(check.checkDatabase(database.getDatabase()));
                 for (int i = 0; i < entries.size(); i++) {
                     if (isCancelled()) {
                         break;

src/main/java/org/jabref/logic/integrity/ASCIICharacterChecker.java

@@ -4,14 +4,13 @@
 import java.util.List;
 import java.util.Map;
 
-import org.jabref.logic.integrity.IntegrityCheck.Checker;
 import org.jabref.logic.l10n.Localization;
 import org.jabref.model.entry.BibEntry;
 import org.jabref.model.entry.field.Field;
 
 import com.google.common.base.CharMatcher;
 
-public class ASCIICharacterChecker implements Checker {
+public class ASCIICharacterChecker implements EntryChecker {
 
     /**
      * Detect any non ASCII encoded characters, e.g., umlauts or unicode in the fields

src/main/java/org/jabref/logic/integrity/BibStringChecker.java

@@ -6,20 +6,19 @@
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
 
-import org.jabref.logic.integrity.IntegrityCheck.Checker;
 import org.jabref.logic.l10n.Localization;
 import org.jabref.model.entry.BibEntry;
 import org.jabref.model.entry.field.Field;
 import org.jabref.model.entry.field.FieldProperty;
 
-public class BibStringChecker implements Checker {
+/**
+ * Checks, if there is an even number of unescaped #
+ */
+public class BibStringChecker implements EntryChecker {
 
     // Detect # if it doesn't have a \ in front of it or if it starts the string
     private static final Pattern UNESCAPED_HASH = Pattern.compile("(?<!\\\\)#|^#");
 
-    /**
-     * Checks, if there is an even number of unescaped #
-     */
     @Override
     public List<IntegrityMessage> check(BibEntry entry) {
         List<IntegrityMessage> results = new ArrayList<>();

src/main/java/org/jabref/logic/integrity/BibTeXEntryTypeChecker.java

@@ -3,7 +3,6 @@
 import java.util.Collections;
 import java.util.List;
 
-import org.jabref.logic.integrity.IntegrityCheck.Checker;
 import org.jabref.logic.l10n.Localization;
 import org.jabref.model.entry.BibEntry;
 import org.jabref.model.entry.field.InternalField;
@@ -12,7 +11,7 @@
 /**
  * BibTeX mode only checker
  */
-public class BibTeXEntryTypeChecker implements Checker {
+public class BibTeXEntryTypeChecker implements EntryChecker {
     /**
      * Will check if the current library uses any entry types from another mode.
      * For example it will warn the user if he uses entry types defined for Biblatex inside a BibTeX library.

src/main/java/org/jabref/logic/integrity/BibtexKeyChecker.java

@@ -4,7 +4,6 @@
 import java.util.List;
 import java.util.Optional;
 
-import org.jabref.logic.integrity.IntegrityCheck.Checker;
 import org.jabref.logic.l10n.Localization;
 import org.jabref.model.entry.BibEntry;
 import org.jabref.model.entry.field.InternalField;
@@ -14,14 +13,14 @@
 /**
  * Currently only checks the key if there is an author, year, and title present.
  */
-public class BibtexKeyChecker implements Checker {
+public class BibtexKeyChecker implements EntryChecker {
 
     @Override
     public List<IntegrityMessage> check(BibEntry entry) {
         Optional<String> author = entry.getField(StandardField.AUTHOR);
         Optional<String> title = entry.getField(StandardField.TITLE);
         Optional<String> year = entry.getField(StandardField.YEAR);
-        if (!author.isPresent() || !title.isPresent() || !year.isPresent()) {
+        if (author.isEmpty() || title.isEmpty() || year.isEmpty()) {
             return Collections.emptyList();
         }
 

src/main/java/org/jabref/logic/integrity/BibtexKeyDuplicationChecker.java

@@ -5,13 +5,12 @@
 import java.util.Objects;
 import java.util.Optional;
 
-import org.jabref.logic.integrity.IntegrityCheck.Checker;
 import org.jabref.logic.l10n.Localization;
 import org.jabref.model.database.BibDatabase;
 import org.jabref.model.entry.BibEntry;
 import org.jabref.model.entry.field.StandardField;
 
-public class BibtexKeyDuplicationChecker implements Checker {
+public class BibtexKeyDuplicationChecker implements EntryChecker {
 
     private final BibDatabase database;
 

src/main/java/org/jabref/logic/integrity/BibtexkeyDeviationChecker.java

@@ -7,13 +7,12 @@
 
 import org.jabref.logic.bibtexkeypattern.BibtexKeyGenerator;
 import org.jabref.logic.bibtexkeypattern.BibtexKeyPatternPreferences;
-import org.jabref.logic.integrity.IntegrityCheck.Checker;
 import org.jabref.logic.l10n.Localization;
 import org.jabref.model.database.BibDatabaseContext;
 import org.jabref.model.entry.BibEntry;
 import org.jabref.model.entry.field.InternalField;
 
-public class BibtexkeyDeviationChecker implements Checker {
+public class BibtexkeyDeviationChecker implements EntryChecker {
 
     private final BibDatabaseContext bibDatabaseContext;
     private final BibtexKeyPatternPreferences bibtexKeyPatternPreferences;
@@ -26,7 +25,7 @@ public BibtexkeyDeviationChecker(BibDatabaseContext bibDatabaseContext, BibtexKe
     @Override
     public List<IntegrityMessage> check(BibEntry entry) {
         Optional<String> valuekey = entry.getCiteKeyOptional();
-        if (!valuekey.isPresent()) {
+        if (valuekey.isEmpty()) {
             return Collections.emptyList();
         }
 

src/main/java/org/jabref/logic/integrity/DatabaseChecker.java

@@ -0,0 +1,10 @@
+package org.jabref.logic.integrity;
+
+import java.util.List;
+
+import org.jabref.model.database.BibDatabase;
+
+@FunctionalInterface
+public interface DatabaseChecker {
+    List<IntegrityMessage> check(BibDatabase database);
+}

src/main/java/org/jabref/logic/integrity/DoiDuplicationChecker.java

@@ -0,0 +1,35 @@
+package org.jabref.logic.integrity;
+
+import java.util.ArrayList;
+import java.util.List;
+import java.util.stream.Collectors;
+
+import javafx.collections.ObservableList;
+
+import org.jabref.logic.l10n.Localization;
+import org.jabref.model.database.BibDatabase;
+import org.jabref.model.entry.BibEntry;
+import org.jabref.model.entry.field.StandardField;
+import org.jabref.model.entry.identifier.DOI;
+
+import com.google.common.collect.BiMap;
+import com.google.common.collect.HashBiMap;
+
+public class DoiDuplicationChecker implements DatabaseChecker {
+
+    @Override
+    public List<IntegrityMessage> check(BibDatabase database) {
+        ObservableList<BibEntry> bibEntries = database.getEntries();
+        BiMap<DOI, List<BibEntry>> duplicateMap = HashBiMap.create(bibEntries.size());
+        for (BibEntry bibEntry : bibEntries) {
+            bibEntry.getDOI().ifPresent(doi ->
+                    duplicateMap.computeIfAbsent(doi, absentDoi -> new ArrayList<>()).add(bibEntry));
+        }
+
+        return duplicateMap.inverse().keySet().stream()
+                           .filter(list -> list.size() > 1)
+                           .flatMap(list -> list.stream())
+                           .map(item -> new IntegrityMessage(Localization.lang("Same DOI used in multiple entries"), item, StandardField.DOI))
+                           .collect(Collectors.toList());
+    }
+}

src/main/java/org/jabref/logic/integrity/DOIValidityChecker.java → src/main/java/org/jabref/logic/integrity/DoiValidityChecker.java

@@ -6,8 +6,7 @@
 import org.jabref.model.entry.identifier.DOI;
 import org.jabref.model.strings.StringUtil;
 
-public class DOIValidityChecker implements ValueChecker {
-
+public class DoiValidityChecker implements ValueChecker {
     @Override
     public Optional<String> checkValue(String value) {
         if (StringUtil.isBlank(value)) {

src/main/java/org/jabref/logic/integrity/EntryChecker.java

@@ -0,0 +1,10 @@
+package org.jabref.logic.integrity;
+
+import java.util.List;
+
+import org.jabref.model.entry.BibEntry;
+
+@FunctionalInterface
+public interface EntryChecker {
+    List<IntegrityMessage> check(BibEntry entry);
+}

src/main/java/org/jabref/logic/integrity/EntryLinkChecker.java

@@ -7,14 +7,13 @@
 import java.util.Objects;
 import java.util.Set;
 
-import org.jabref.logic.integrity.IntegrityCheck.Checker;
 import org.jabref.logic.l10n.Localization;
 import org.jabref.model.database.BibDatabase;
 import org.jabref.model.entry.BibEntry;
 import org.jabref.model.entry.field.Field;
 import org.jabref.model.entry.field.FieldProperty;
 
-public class EntryLinkChecker implements Checker {
+public class EntryLinkChecker implements EntryChecker {
 
     private final BibDatabase database;
 
@@ -28,14 +27,14 @@ public List<IntegrityMessage> check(BibEntry entry) {
         for (Entry<Field, String> field : entry.getFieldMap().entrySet()) {
             Set<FieldProperty> properties = field.getKey().getProperties();
             if (properties.contains(FieldProperty.SINGLE_ENTRY_LINK)) {
-                if (!database.getEntryByKey(field.getValue()).isPresent()) {
+                if (database.getEntryByKey(field.getValue()).isEmpty()) {
                     result.add(new IntegrityMessage(Localization.lang("Referenced BibTeX key does not exist"), entry,
                             field.getKey()));
                 }
             } else if (properties.contains(FieldProperty.MULTIPLE_ENTRY_LINK)) {
                 List<String> keys = new ArrayList<>(Arrays.asList(field.getValue().split(",")));
                 for (String key : keys) {
-                    if (!database.getEntryByKey(key).isPresent()) {
+                    if (database.getEntryByKey(key).isEmpty()) {
                         result.add(new IntegrityMessage(
                                 Localization.lang("Referenced BibTeX key does not exist") + ": " + key, entry,
                                 field.getKey()));

src/main/java/org/jabref/logic/integrity/FieldChecker.java

@@ -9,7 +9,7 @@
 import org.jabref.model.entry.field.Field;
 import org.jabref.model.util.OptionalUtil;
 
-public class FieldChecker implements IntegrityCheck.Checker {
+public class FieldChecker implements EntryChecker {
     protected final Field field;
     private final ValueChecker checker;
 
@@ -21,7 +21,7 @@ public FieldChecker(Field field, ValueChecker checker) {
     @Override
     public List<IntegrityMessage> check(BibEntry entry) {
         Optional<String> value = entry.getField(field);
-        if (!value.isPresent()) {
+        if (value.isEmpty()) {
             return Collections.emptyList();
         }
 

src/main/java/org/jabref/logic/integrity/FieldCheckers.java

@@ -39,7 +39,7 @@ private static Multimap<Field, ValueChecker> getAllMap(BibDatabaseContext databa
         fieldCheckers.put(StandardField.BOOKTITLE, new BooktitleChecker());
         fieldCheckers.put(StandardField.TITLE, new BracketChecker());
         fieldCheckers.put(StandardField.TITLE, new TitleChecker(databaseContext));
-        fieldCheckers.put(StandardField.DOI, new DOIValidityChecker());
+        fieldCheckers.put(StandardField.DOI, new DoiValidityChecker());
         fieldCheckers.put(StandardField.EDITION, new EditionChecker(databaseContext, allowIntegerEdition));
         fieldCheckers.put(StandardField.FILE, new FileChecker(databaseContext, filePreferences));
         fieldCheckers.put(StandardField.HOWPUBLISHED, new HowPublishedChecker(databaseContext));

src/main/java/org/jabref/logic/integrity/HTMLCharacterChecker.java

@@ -6,19 +6,18 @@
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
 
-import org.jabref.logic.integrity.IntegrityCheck.Checker;
 import org.jabref.logic.l10n.Localization;
 import org.jabref.model.entry.BibEntry;
 import org.jabref.model.entry.field.Field;
 import org.jabref.model.entry.field.FieldProperty;
 
-public class HTMLCharacterChecker implements Checker {
-    // Detect any HTML encoded character,
+/**
+ * Checks, if there are any HTML encoded characters in nonverbatim fields.
+ */
+public class HTMLCharacterChecker implements EntryChecker {
+    // Detect any HTML encoded character
     private static final Pattern HTML_CHARACTER_PATTERN = Pattern.compile("&[#\\p{Alnum}]+;");
 
-    /**
-     * Checks, if there are any HTML encoded characters in nonverbatim fields.
-     */
     @Override
     public List<IntegrityMessage> check(BibEntry entry) {
         List<IntegrityMessage> results = new ArrayList<>();