Refactor: Move string normalization from StringNormalizer to StringUtil

- Moved normalize() method to StringUtil
- use Pattern.compile for NORMALIZE_PATTERN
- Update shouldUpdateField() method in MergingIdBasedFetcher to use StringUtil.normalize()

Author: BojiZhang

src/main/java/org/jabref/logic/importer/fetcher/MergingIdBasedFetcher.java

@@ -12,6 +12,7 @@
 import org.jabref.model.entry.BibEntry;
 import org.jabref.model.entry.field.Field;
 import org.jabref.model.entry.field.StandardField;
+import org.jabref.model.strings.StringUtil;
 
 import org.mariadb.jdbc.internal.logging.Logger;
 import org.mariadb.jdbc.internal.logging.LoggerFactory;
@@ -116,13 +117,12 @@ private Set<Field> updateFieldsFromSource(BibEntry sourceEntry,
                           .collect(Collectors.toSet());
     }
 
-    private boolean shouldUpdateField(Field field, BibEntry sourceEntry,
-                                      BibEntry targetEntry) {
+    private boolean shouldUpdateField(Field field, BibEntry sourceEntry, BibEntry targetEntry) {
         String sourceValue = sourceEntry.getField(field)
-                                        .map(StringNormalizer::normalize)
+                                        .map(StringUtil::normalize)
                                         .orElse("");
         String targetValue = targetEntry.getField(field)
-                                        .map(StringNormalizer::normalize)
+                                        .map(StringUtil::normalize)
                                         .orElse("");
         return !sourceValue.equals(targetValue);
     }
@@ -136,18 +136,3 @@ private void updateField(Field field, BibEntry sourceEntry,
     }
 }
 
-class StringNormalizer {
-    public static String normalize(String value) {
-        if (value == null) {
-            return "";
-        }
-        return value.trim()
-                    .replaceAll("\\s+", " ")
-                    .replaceAll("\\r\\n|\\r|\\n", " ")
-                    .replaceAll("\\s*-+\\s*", "-")
-                    .replaceAll("\\s*,\\s*", ", ")
-                    .replaceAll("\\s*;\\s*", "; ")
-                    .replaceAll("\\s*:\\s*", ": ");
-    }
-}
-

src/main/java/org/jabref/model/strings/StringUtil.java

@@ -25,6 +25,12 @@ public class StringUtil {
     // contains all possible line breaks, not omitting any break such as "\\n"
     private static final Pattern LINE_BREAKS = Pattern.compile("\\r\\n|\\r|\\n");
     private static final Pattern BRACED_TITLE_CAPITAL_PATTERN = Pattern.compile("\\{[A-Z]+\\}");
+    private static final Pattern NORMALIZE_PATTERN = Pattern.compile(
+             "\\s+|" +           // multiple whitespace
+                    "\\s*-+\\s*|" +     // hyphens with surrounding spaces
+                    "\\s*,\\s*|" +      // commas with surrounding spaces
+                    "\\s*;\\s*|" +      // semicolons with surrounding spaces
+                    "\\s*:\\s*");       // colons with surrounding spaces
     private static final UnicodeToReadableCharMap UNICODE_CHAR_MAP = new UnicodeToReadableCharMap();
 
     public static String booleanToBinaryString(boolean expression) {
@@ -755,4 +761,43 @@ public static String removeStringAtTheEnd(String string, String stringToBeRemove
     public static boolean endsWithIgnoreCase(String string, String suffix) {
         return StringUtils.endsWithIgnoreCase(string, suffix);
     }
+
+    /**
+     * Normalizes a string by standardizing whitespace and punctuation. This includes:
+     * - Trimming outer whitespace
+     * - Converting multiple whitespace characters to a single space
+     * - Converting line breaks to spaces
+     * - Standardizing formatting around punctuation (hyphens, commas, semicolons, colons)
+     *
+     * @param value The string to normalize
+     * @return The normalized string, or empty string if input is null
+     */
+    public static String normalize(String value) {
+        if (value == null) {
+            return "";
+        }
+
+        String withoutLineBreaks = LINE_BREAKS.matcher(value).replaceAll(" ");
+
+        String trimmed = withoutLineBreaks.trim();
+        return NORMALIZE_PATTERN.matcher(trimmed).replaceAll(match -> {
+            String matchStr = match.group();
+            if (matchStr.matches("\\s+")) {
+                return " ";
+            }
+            if (matchStr.matches("\\s*-+\\s*")) {
+                return "-";
+            }
+            if (matchStr.matches("\\s*,\\s*")) {
+                return ", ";
+            }
+            if (matchStr.matches("\\s*;\\s*")) {
+                return "; ";
+            }
+            if (matchStr.matches("\\s*:\\s*")) {
+                return ": ";
+            }
+            return matchStr;
+        });
+    }
 }