Changed encoding used by IntegrityCheck

CHANGELOG.md

@@ -18,6 +18,7 @@ Note that this project **does not** adhere to [Semantic Versioning](http://semve
 ### Fixed
 
 - We fixed an issue where clicking on headings in the entry preview could lead to an exception. [#8292](https://github.com/JabRef/jabref/issues/8292)
+- We fixed an issue where IntegrityCheck used the system's character encoding instead of the one set by the library or in preferences [#8022](https://github.com/JabRef/jabref/issues/8022)
 - We fixed an issue about empty metadata in library properties when called from the right click menu. [#8358](https://github.com/JabRef/jabref/issues/8358)
 
 ### Removed

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

@@ -42,6 +42,7 @@ public void execute() {
         IntegrityCheck check = new IntegrityCheck(database,
                 Globals.prefs.getFilePreferences(),
                 Globals.prefs.getCitationKeyPatternPreferences(),
+                Globals.prefs.getGeneralPreferences().getDefaultEncoding(),
                 Globals.journalAbbreviationRepository,
                 Globals.prefs.getEntryEditorPreferences().shouldAllowIntegerEditionBibtex());
 

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

@@ -1,5 +1,6 @@
 package org.jabref.logic.integrity;
 
+import java.nio.charset.Charset;
 import java.util.ArrayList;
 import java.util.List;
 
@@ -20,6 +21,7 @@ public class IntegrityCheck {
     public IntegrityCheck(BibDatabaseContext bibDatabaseContext,
                           FilePreferences filePreferences,
                           CitationKeyPatternPreferences citationKeyPatternPreferences,
+                          Charset defaultEncoding,
                           JournalAbbreviationRepository journalAbbreviationRepository,
                           boolean allowIntegerEdition) {
         this.bibDatabaseContext = bibDatabaseContext;
@@ -41,8 +43,8 @@ public IntegrityCheck(BibDatabaseContext bibDatabaseContext,
         if (bibDatabaseContext.isBiblatexMode()) {
             entryCheckers.addAll(List.of(
                     new JournalInAbbreviationListChecker(StandardField.JOURNALTITLE, journalAbbreviationRepository),
-                    new UTF8Checker())
-            );
+                    new UTF8Checker(bibDatabaseContext.getMetaData().getEncoding().orElse(defaultEncoding))
+            ));
         } else {
             entryCheckers.addAll(List.of(
                     new JournalInAbbreviationListChecker(StandardField.JOURNAL, journalAbbreviationRepository),

src/main/java/org/jabref/logic/integrity/UTF8Checker.java

@@ -14,16 +14,30 @@
 import org.jabref.model.entry.field.Field;
 
 public class UTF8Checker implements EntryChecker {
+    private final Charset charset;
+
+    /**
+     * Creates a UTF8Checker that,
+     * <ol>
+     * <li>decode a String into a bytes array</li>
+     * <li>attempts to decode the bytes array to a character array using the UTF-8 Charset</li>
+     * </ol>
+     *
+     * @param charset the charset used to decode BibEntry fields
+     */
+    public UTF8Checker(Charset charset) {
+        this.charset = charset;
+    }
 
     /**
      * Detect any non UTF-8 encoded field
+     *
      * @param entry the BibEntry of BibLatex.
      * @return return the warning of UTF-8 check for BibLatex.
      */
     @Override
     public List<IntegrityMessage> check(BibEntry entry) {
         List<IntegrityMessage> results = new ArrayList<>();
-        Charset charset = Charset.forName(System.getProperty("file.encoding"));
         for (Map.Entry<Field, String> field : entry.getFieldMap().entrySet()) {
             boolean utfOnly = UTF8EncodingChecker(field.getValue().getBytes(charset));
             if (!utfOnly) {

src/test/java/org/jabref/logic/integrity/IntegrityCheckTest.java

@@ -1,6 +1,7 @@
 package org.jabref.logic.integrity;
 
 import java.io.IOException;
+import java.nio.charset.StandardCharsets;
 import java.nio.file.Files;
 import java.nio.file.Path;
 import java.util.Collections;
@@ -139,6 +140,7 @@ void testEntryIsUnchangedAfterChecks() {
         new IntegrityCheck(context,
                 mock(FilePreferences.class),
                 createCitationKeyPatternPreferences(),
+                StandardCharsets.UTF_8,
                 JournalAbbreviationLoader.loadBuiltInRepository(), false)
                 .check();
 
@@ -172,6 +174,7 @@ private void assertWrong(BibDatabaseContext context) {
         List<IntegrityMessage> messages = new IntegrityCheck(context,
                 mock(FilePreferences.class),
                 createCitationKeyPatternPreferences(),
+                StandardCharsets.UTF_8,
                 JournalAbbreviationLoader.loadBuiltInRepository(), false)
                 .check();
         assertNotEquals(Collections.emptyList(), messages);
@@ -183,20 +186,12 @@ private void assertCorrect(BibDatabaseContext context) {
         List<IntegrityMessage> messages = new IntegrityCheck(context,
                 filePreferencesMock,
                 createCitationKeyPatternPreferences(),
+                StandardCharsets.UTF_8,
                 JournalAbbreviationLoader.loadBuiltInRepository(), false
         ).check();
         assertEquals(Collections.emptyList(), messages);
     }
 
-    private void assertCorrect(BibDatabaseContext context, boolean allowIntegerEdition) {
-        List<IntegrityMessage> messages = new IntegrityCheck(context,
-                mock(FilePreferences.class),
-                createCitationKeyPatternPreferences(),
-                JournalAbbreviationLoader.loadBuiltInRepository(),
-                allowIntegerEdition).check();
-        assertEquals(Collections.emptyList(), messages);
-    }
-
     private CitationKeyPatternPreferences createCitationKeyPatternPreferences() {
         final GlobalCitationKeyPattern keyPattern = GlobalCitationKeyPattern.fromPattern("[auth][year]");
         return new CitationKeyPatternPreferences(

src/test/java/org/jabref/logic/integrity/UTF8CheckerTest.java

@@ -1,6 +1,7 @@
 package org.jabref.logic.integrity;
 
 import java.io.UnsupportedEncodingException;
+import java.nio.charset.Charset;
 import java.nio.charset.StandardCharsets;
 import java.util.Collections;
 import java.util.List;
@@ -24,28 +25,25 @@ public class UTF8CheckerTest {
      */
     @Test
     void fieldAcceptsUTF8() {
-        UTF8Checker checker = new UTF8Checker();
+        UTF8Checker checker = new UTF8Checker(StandardCharsets.UTF_8);
         entry.setField(StandardField.TITLE, "Only ascii characters!'@12");
         assertEquals(Collections.emptyList(), checker.check(entry));
     }
 
     /**
      * fieldDoesNotAcceptUmlauts to check UTF8Checker's result set
-     * when the entry is encoded in Non-Utf-8 charset and the System
+     * when the entry is encoded in Non-Utf-8 charset and the Library
      * environment is Non UTF-8.
      * Finally we need to reset the environment charset.
      * @throws UnsupportedEncodingException initial a String in charset GBK
      * Demo: new String(StringDemo.getBytes(), "GBK");
      */
     @Test
     void fieldDoesNotAcceptUmlauts() throws UnsupportedEncodingException {
-        String defaultCharset = System.getProperty("file.encoding");
-        System.getProperties().put("file.encoding", "GBK");
-        UTF8Checker checker = new UTF8Checker();
+        UTF8Checker checker = new UTF8Checker(Charset.forName("GBK"));
         String NonUTF8 = new String("你好，这条语句使用GBK字符集".getBytes(), "GBK");
         entry.setField(StandardField.MONTH, NonUTF8);
         assertEquals(List.of(new IntegrityMessage("Non-UTF-8 encoded field found", entry, StandardField.MONTH)), checker.check(entry));
-        System.getProperties().put("file.encoding", defaultCharset);
     }
 
     /**