HTM-1963: Add Excel extract output and integration tests

Author: mprins

src/main/java/org/tailormap/api/service/CreateLayerExtractService.java

@@ -51,6 +51,7 @@
 import org.springframework.stereotype.Service;
 import org.springframework.transaction.annotation.Transactional;
 import org.tailormap.api.controller.LayerExtractController;
+import org.tailormap.api.geotools.data.excel.ExcelDataStoreFactory;
 import org.tailormap.api.geotools.featuresources.FeatureSourceFactoryHelper;
 import org.tailormap.api.persistence.TMFeatureType;
 import org.tailormap.api.util.UUIDv7;
@@ -65,7 +66,6 @@ public class CreateLayerExtractService {
   private final SseEventBus eventBus;
   private final JsonMapper jsonMapper;
   private final FeatureSourceFactoryHelper featureSourceFactoryHelper;
-
   private final FilterFactory ff = CommonFactoryFinder.getFilterFactory(GeoTools.getDefaultHints());
 
   // we can safely use the tmp dir as a default here because we are running in a docker container so access is limited
@@ -223,7 +223,8 @@ public void createLayerExtract(
       logger.debug("Filtered source counts {}", featCount);
       final AtomicInteger featsAdded = new AtomicInteger();
 
-      FileDataStore outputDataStore = getExtractDataStore(extractOutputFormat, outputFileName, clientId);
+      FileDataStore outputDataStore =
+          getExtractDataStore(extractOutputFormat, outputFileName, clientId, inputTmFeatureType.getName());
       SimpleFeatureType fType =
           DataUtilities.createSubType(inputFeatureSource.getSchema(), attributes.toArray(new String[0]));
       outputDataStore.createSchema(fType);
@@ -268,7 +269,10 @@ public void createLayerExtract(
   }
 
   private FileDataStore getExtractDataStore(
-      LayerExtractController.ExtractOutputFormat extractOutputFormat, String outputFileName, String clientId)
+      LayerExtractController.ExtractOutputFormat extractOutputFormat,
+      String outputFileName,
+      String clientId,
+      String typeName)
       throws IOException {
 
     final File outputFile = Files.createFile(Path.of(exportFilesLocation, outputFileName))
@@ -302,8 +306,17 @@ private FileDataStore getExtractDataStore(
             true);
         return (FileDataStore) new CSVDataStoreFactory().createNewDataStore(params);
       }
+      case XLSX -> {
+        Map<String, Serializable> params = Map.of(
+            ExcelDataStoreFactory.FILE_PARAM.key,
+            outputFile,
+            ExcelDataStoreFactory.SHEET_PARAM.key,
+            // typeName could hve a prefix; for Excel sheet names ':' is disallowed, max length is 31
+            typeName.substring(typeName.lastIndexOf(":") + 1, Math.min(typeName.length(), 31)));
+        return (FileDataStore) new ExcelDataStoreFactory().createNewDataStore(params);
+      }
       // TODO implement
-      case GEOJSON, XLSX, SHAPE -> {
+      case GEOJSON, SHAPE -> {
         emitError(clientId, "Output format " + extractOutputFormat + " is not yet supported");
         logger.error("Output format {} is not yet supported", extractOutputFormat);
         throw new IOException("Unsupported output format: " + extractOutputFormat);

src/test/java/org/tailormap/api/controller/LayerExtractControllerIntegrationTest.java

@@ -12,6 +12,7 @@
 import static org.hamcrest.Matchers.greaterThanOrEqualTo;
 import static org.hamcrest.Matchers.not;
 import static org.hamcrest.Matchers.startsWith;
+import static org.junit.jupiter.api.Assertions.assertAll;
 import static org.junit.jupiter.api.Assertions.assertEquals;
 import static org.springframework.security.test.web.servlet.request.SecurityMockMvcRequestPostProcessors.csrf;
 import static org.springframework.test.web.servlet.request.MockMvcRequestBuilders.get;
@@ -22,8 +23,14 @@
 import static org.tailormap.api.controller.TestUrls.layerBegroeidTerreindeelPostgis;
 import static org.tailormap.api.controller.TestUrls.layerProxiedWithAuthInPublicApp;
 
+import java.io.ByteArrayInputStream;
 import java.io.IOException;
+import java.io.InputStream;
 import java.nio.charset.StandardCharsets;
+import org.apache.poi.ss.usermodel.CellType;
+import org.apache.poi.ss.usermodel.Sheet;
+import org.apache.poi.ss.usermodel.Workbook;
+import org.apache.poi.ss.usermodel.WorkbookFactory;
 import org.awaitility.Awaitility;
 import org.junit.jupiter.api.BeforeEach;
 import org.junit.jupiter.api.MethodOrderer;
@@ -256,6 +263,90 @@ void should_export_wfs_to_csv_with_authentication() throws Exception {
     });
   }
 
+  @Test
+  void should_export_large_filter_to_excel() throws Exception {
+    final String extractUrl = apiBasePath + layerBegroeidTerreindeelPostgis + extractPath + sseClientId;
+    mockMvc.perform(post(extractUrl)
+            .accept(MediaType.APPLICATION_JSON)
+            .with(setServletPath(extractUrl))
+            .with(csrf())
+            .param("attributes", "")
+            .param("outputFormat", "xlsx")
+            .param("filter", StaticTestData.get("large_cql_filter"))
+            .acceptCharset(StandardCharsets.UTF_8)
+            .characterEncoding(StandardCharsets.UTF_8)
+            .contentType(MediaType.APPLICATION_FORM_URLENCODED))
+        .andExpect(status().isAccepted());
+
+    // The SseEventBus may dispatch events slightly after the POST returns.
+    // Awaitility polls the buffered SSE response until the expected content appears.
+    Awaitility.await()
+        .atMost(10, SECONDS)
+        .untilAsserted(() -> assertThat(
+            sseResult.getResponse().getContentAsString(), containsString("Extract task received")));
+
+    Awaitility.await().pollInterval(5, SECONDS).atMost(30, SECONDS).untilAsserted(() -> {
+      final String stream = sseResult.getResponse().getContentAsString();
+      assertThat(count_completed_messages(stream), greaterThanOrEqualTo(1));
+    });
+
+    final String lastCompletedEventJson =
+        getLastCompletedEventJson(sseResult.getResponse().getContentAsString());
+    assertThat(lastCompletedEventJson.length(), greaterThanOrEqualTo(100));
+
+    final String extractedDownloadId = getDownloadId(lastCompletedEventJson);
+    assertThat(extractedDownloadId, containsString(".xlsx"));
+
+    final String downloadUrl = apiBasePath + layerBegroeidTerreindeelPostgis + downloadPath + extractedDownloadId;
+    MvcResult download = mockMvc.perform(get(downloadUrl).with(setServletPath(downloadUrl)))
+        .andExpect(status().isOk())
+        .andExpect(result -> {
+          String contentType = result.getResponse().getContentType();
+          assertThat(
+              contentType,
+              containsString("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"));
+
+          String contentDisposition = result.getResponse().getHeader("Content-Disposition");
+          assertThat(contentDisposition, containsString("attachment; filename="));
+          assertThat(contentDisposition, containsString(extractedDownloadId));
+        })
+        .andReturn();
+
+    // open the Excel file and check that we have the expected content
+    try (InputStream inp = new ByteArrayInputStream(download.getResponse().getContentAsByteArray());
+        Workbook wb = WorkbookFactory.create(inp)) {
+      Sheet sheet = wb.getSheetAt(0);
+
+      assertEquals(
+          18 + /*header row*/ 1,
+          sheet.getPhysicalNumberOfRows(),
+          () -> "Expected " + 18 + /*header row*/ 1
+              + " rows in the Excel sheet, including header and 18 data rows");
+
+      assertAll(
+          "Check header and first data row",
+          () -> assertEquals(
+              "begroeidterreindeel",
+              sheet.getSheetName(),
+              "Expected sheet name to be begroeidterreindeel"),
+          () -> assertEquals(
+              14, sheet.getRow(0).getPhysicalNumberOfCells(), "Expected 14 columns in the header row"));
+
+      assertAll(
+          "Check first data row",
+          () -> assertEquals(
+              CellType.NUMERIC,
+              sheet.getRow(1).getCell(0).getCellType(),
+              "Expected first cell in header to be numeric (with date format)"),
+          () -> assertEquals(
+              CellType.STRING,
+              sheet.getRow(1).getCell(1).getCellType(),
+              "Expected second cell in header to be a string"),
+          () -> assertEquals("geenWaarde", sheet.getRow(1).getCell(1).getStringCellValue()),
+          () -> assertEquals("G0344", sheet.getRow(1).getCell(2).getStringCellValue()));
+    }
+  }
+
   /**
    * Parse the last non-empty line from the SSE stream that looks something like:
    * {@code data:{"details":{"message":"Extract task