MID-11535 Add encoding and utf-8-bom support for GUI CSV export

gui/admin-gui/src/main/java/com/evolveum/midpoint/gui/api/component/button/CsvDownloadInlineMenuItem.java

@@ -11,6 +11,7 @@
 import java.util.List;
 
 import com.evolveum.midpoint.gui.impl.component.data.provider.StreamingCsvDataExporter;
+import com.evolveum.midpoint.model.api.authentication.CompiledGuiProfile;
 
 import org.apache.wicket.extensions.markup.html.repeater.data.table.export.AbstractDataExporter;
 import org.apache.wicket.extensions.markup.html.repeater.data.table.export.IExportableColumn;
@@ -48,7 +49,8 @@ protected IModel<String> getConfirmationMessage(final Long exportSizeLimit) {
 
     @Override
     protected AbstractDataExporter getDataExporter() {
-        return new StreamingCsvDataExporter(component.getPageBase()) {
+        String encoding = resolveExportEncoding();
+        return new StreamingCsvDataExporter(component.getPageBase(), encoding) {
             @Serial private static final long serialVersionUID = 1L;
 
             @Override
@@ -82,4 +84,17 @@ protected <T> IModel<T> wrapModel(IModel<T> model) {
             }
         };
     }
+
+    private String resolveExportEncoding() {
+        try {
+            CompiledGuiProfile profile = WebComponentUtil.getPageBase(component).getCompiledGuiProfile();
+            if (profile.getDefaultExportSettings() != null
+                    && profile.getDefaultExportSettings().getEncoding() != null) {
+                return profile.getDefaultExportSettings().getEncoding();
+            }
+        } catch (Exception ex) {
+            LOGGER.warn("Unable to get export encoding setting, falling back to utf-8", ex);
+        }
+        return "utf-8";
+    }
 }

gui/admin-gui/src/main/java/com/evolveum/midpoint/gui/impl/component/data/provider/StreamingCsvDataExporter.java

@@ -41,17 +41,43 @@ public class StreamingCsvDataExporter extends CSVDataExporter {
     private static final String DOT_CLASS = StreamingCsvDataExporter.class.getName() + ".";
     private static final String OPERATION_EXPORT_DATA = DOT_CLASS + "exportData";
 
+    private static final String UTF_8_BOM_ENCODING = "utf-8-bom";
+    private static final byte[] UTF8_BOM = { (byte) 0xEF, (byte) 0xBB, (byte) 0xBF };
+
     private final PageBase pageBase;
+    private final String configuredEncoding;
 
-    public StreamingCsvDataExporter(PageBase pageBase) {
+    public StreamingCsvDataExporter(PageBase pageBase, String encoding) {
         this.pageBase = pageBase;
+        this.configuredEncoding = encoding;
+        setCharacterSet(resolveEffectiveCharset(encoding));
+    }
+
+    public StreamingCsvDataExporter(PageBase pageBase) {
+        this(pageBase, null);
+    }
+
+    private static String resolveEffectiveCharset(String encoding) {
+        if (encoding == null || UTF_8_BOM_ENCODING.equalsIgnoreCase(encoding)) {
+            return "utf-8";
+        }
+        return encoding;
+    }
+
+    private boolean isUtf8Bom() {
+        return UTF_8_BOM_ENCODING.equalsIgnoreCase(configuredEncoding);
     }
 
     @Override
     public <T> void exportData(IDataProvider<T> dataProvider,
             List<IExportableColumn<T, ?>> columns, OutputStream outputStream)
             throws IOException {
 
+        if (isUtf8Bom()) {
+            outputStream.write(UTF8_BOM);
+            outputStream.flush();
+        }
+
         if (!(dataProvider instanceof IterativeExportSupport)
                 || !((IterativeExportSupport<?>) dataProvider).supportsIterativeExport()) {
             // Fall back to standard export if provider doesn't support iterative export

infra/schema/src/main/resources/xml/ns/public/common/common-gui-3.xsd

@@ -3871,6 +3871,21 @@
                     </xsd:appinfo>
                 </xsd:annotation>
             </xsd:element>
+            <xsd:element name="encoding" type="xsd:string" minOccurs="0" maxOccurs="1">
+                <xsd:annotation>
+                    <xsd:documentation>
+                        Character encoding for exported CSV files.
+                        Default is "utf-8". Use "utf-8-bom" to prepend a UTF-8 BOM
+                        (byte order mark) to the exported file, which helps applications
+                        like Microsoft Excel on non-UTF-8 locale systems correctly
+                        recognize the file as UTF-8.
+                    </xsd:documentation>
+                    <xsd:appinfo>
+                        <a:displayName>GuiExportSettingsType.encoding</a:displayName>
+                        <a:since>4.10.4</a:since>
+                    </xsd:appinfo>
+                </xsd:annotation>
+            </xsd:element>
             <!-- TODO: later: default data language, sync/async, whether to show detail dialog or just run the export, etc. -->
         </xsd:sequence>
         <xsd:attribute name="id" type="xsd:long"/>