Fix issue #4962, remove trailing whitespace in caption field when set to uploadMediaDetails (#5085)

* add methods to check and remove trailing whitespace

* fix filter to check and remove trailing whitespace

* fix filter to check and remove trailing space first

* add test and fix filter() and removeTrailingWhitespace()

* caption trailing whitespace: change solution to remove trailing whitespaces when set to uploadMediaDetails

* update code documentation

* add more tests include instance tab, carriage return and Japanese whitespace

* Caption field: Stop blocking Japanese Space, convert to English Space when set to uploadMediaDetails

* Change method name from convertJapSpaceToEngSpace to convertIdeographicSpaceToLatinSpace

* Change pattern name from JapSpacePattern to ideographicSpacePattern

app/src/main/java/fr/free/nrw/commons/upload/UploadMediaDetailAdapter.java

@@ -34,6 +34,7 @@ import java.util.HashMap;
 import java.util.List;
 import java.util.Locale;
 import java.util.Objects;
+import java.util.regex.Pattern;
 import javax.inject.Inject;
 import timber.log.Timber;
 
@@ -197,7 +198,7 @@ public class UploadMediaDetailAdapter extends RecyclerView.Adapter<UploadMediaDe
 
             removeButton.setOnClickListener(v -> removeDescription(uploadMediaDetail, position));
             captionListener = new AbstractTextWatcher(
-                captionText -> uploadMediaDetails.get(position).setCaptionText(captionText));
+                captionText -> uploadMediaDetails.get(position).setCaptionText(convertIdeographicSpaceToLatinSpace(removeTrailingWhitespace(captionText))));
             descriptionListener = new AbstractTextWatcher(
                 descriptionText -> uploadMediaDetails.get(position).setDescriptionText(descriptionText));
             captionItemEditText.addTextChangedListener(captionListener);
@@ -418,10 +419,45 @@ public class UploadMediaDetailAdapter extends RecyclerView.Adapter<UploadMediaDe
                 languageHistoryListView.setAdapter(recentLanguagesAdapter);
             }
         }
+
+        /**
+         * Checks if the source string contains trailing whitespace
+         * @param source input string
+         * @return true if contains trailing whitespace and false otherwise
+         */
+        public Boolean checkTrailingWhitespace(String source) {
+            int len = source.length();
+            if (len == 0) {
+                return false;
+            }
+            return Character.isWhitespace(source.charAt(len - 1));
+        }
+
+        /**
+         * Removes any trailing whitespace from the source text.
+         * @param source input string
+         * @return a string without trailing whitespace
+         */
+        public String removeTrailingWhitespace(String source) {
+            while (checkTrailingWhitespace(source)) {
+                source = source.substring(0, source.length() - 1);
+            }
+            return source;
+        }
+
+        /**
+         * Convert Ideographic space to Latin space
+         * @param source the source text
+         * @return a string with Latin spaces instead of Ideographic spaces
+         */
+        public String convertIdeographicSpaceToLatinSpace(String source) {
+            Pattern ideographicSpacePattern = Pattern.compile("\\x{3000}");
+            return ideographicSpacePattern.matcher(source).replaceAll(" ");
+        }
+
     }
 
     public interface Callback {
-
         void showAlert(int mediaDetailDescription, int descriptionInfo);
     }
 

app/src/main/java/fr/free/nrw/commons/upload/UploadMediaDetailInputFilter.java

@@ -17,7 +17,7 @@ public class UploadMediaDetailInputFilter implements InputFilter {
      */
     public UploadMediaDetailInputFilter() {
         patterns = new Pattern[]{
-            Pattern.compile("[\\x{00A0}\\x{1680}\\x{180E}\\x{2000}-\\x{200B}\\x{2028}\\x{2029}\\x{202F}\\x{205F}\\x{3000}]"),
+            Pattern.compile("[\\x{00A0}\\x{1680}\\x{180E}\\x{2000}-\\x{200B}\\x{2028}\\x{2029}\\x{202F}\\x{205F}]"),
             Pattern.compile("[\\x{202A}-\\x{202E}]"),
             Pattern.compile("\\p{Cc}"),
             Pattern.compile("\\x{FEFF}"),