feat(conversion): add PDF to Excel (XLSX) conversion (#5778)

app/core/build.gradle

@@ -66,6 +66,7 @@ dependencies {
     implementation 'javax.xml.bind:jaxb-api:2.3.1'
     implementation 'com.sun.xml.bind:jaxb-impl:2.3.9'
     implementation 'com.sun.xml.bind:jaxb-core:2.3.0.1'
+    implementation 'org.apache.poi:poi-ooxml:5.5.1'
 
     // https://mvnrepository.com/artifact/technology.tabula/tabula
     implementation ('technology.tabula:tabula:1.0.5')  {

app/core/src/main/java/stirling/software/SPDF/controller/api/converters/ConvertPDFToExcelController.java

@@ -0,0 +1,127 @@
+package stirling.software.SPDF.controller.api.converters;
+
+import java.io.ByteArrayOutputStream;
+import java.util.List;
+import java.util.Locale;
+
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.poi.ss.usermodel.Cell;
+import org.apache.poi.ss.usermodel.Row;
+import org.apache.poi.ss.usermodel.Sheet;
+import org.apache.poi.ss.usermodel.Workbook;
+import org.apache.poi.ss.util.WorkbookUtil;
+import org.apache.poi.xssf.usermodel.XSSFWorkbook;
+import org.springframework.http.ContentDisposition;
+import org.springframework.http.HttpHeaders;
+import org.springframework.http.MediaType;
+import org.springframework.http.ResponseEntity;
+import org.springframework.web.bind.annotation.ModelAttribute;
+
+import io.swagger.v3.oas.annotations.Operation;
+
+import lombok.RequiredArgsConstructor;
+import lombok.extern.slf4j.Slf4j;
+
+import stirling.software.SPDF.model.api.PDFWithPageNums;
+import stirling.software.common.annotations.AutoJobPostMapping;
+import stirling.software.common.annotations.api.ConvertApi;
+import stirling.software.common.service.CustomPDFDocumentFactory;
+import stirling.software.common.util.GeneralUtils;
+
+import technology.tabula.ObjectExtractor;
+import technology.tabula.Page;
+import technology.tabula.RectangularTextContainer;
+import technology.tabula.Table;
+import technology.tabula.extractors.SpreadsheetExtractionAlgorithm;
+
+@ConvertApi
+@Slf4j
+@RequiredArgsConstructor
+public class ConvertPDFToExcelController {
+
+    private final CustomPDFDocumentFactory pdfDocumentFactory;
+
+    @AutoJobPostMapping(value = "/pdf/xlsx", consumes = MediaType.MULTIPART_FORM_DATA_VALUE)
+    @Operation(
+            summary = "Convert a PDF to an Excel spreadsheet (XLSX)",
+            description =
+                    "Extracts tabular data from each page of a PDF and writes it into an Excel"
+                            + " workbook, one sheet per table. Input:PDF Output:XLSX Type:SISO")
+    public ResponseEntity<byte[]> pdfToExcel(@ModelAttribute PDFWithPageNums request)
+            throws Exception {
+        String baseName =
+                GeneralUtils.removeExtension(request.getFileInput().getOriginalFilename());
+
+        try (PDDocument document = pdfDocumentFactory.load(request);
+                XSSFWorkbook workbook = new XSSFWorkbook();
+                ObjectExtractor extractor = new ObjectExtractor(document)) {
+
+            List<Integer> pages = request.getPageNumbersList(document, true);
+            SpreadsheetExtractionAlgorithm sea = new SpreadsheetExtractionAlgorithm();
+            int sheetCount = 0;
+
+            for (int pageNum : pages) {
+                Page page = extractor.extract(pageNum);
+                List<Table> tables = sea.extract(page);
+
+                for (int tableIdx = 0; tableIdx < tables.size(); tableIdx++) {
+                    Table table = tables.get(tableIdx);
+                    String sheetName =
+                            tables.size() == 1
+                                    ? String.format(Locale.ROOT, "Page %d", pageNum)
+                                    : String.format(
+                                            Locale.ROOT,
+                                            "Page %d Table %d",
+                                            pageNum,
+                                            tableIdx + 1);
+
+                    sheetName = getUniqueSheetName(workbook, sheetName);
+                    Sheet sheet = workbook.createSheet(sheetName);
+                    List<List<RectangularTextContainer>> rows = table.getRows();
+
+                    for (int rowIdx = 0; rowIdx < rows.size(); rowIdx++) {
+                        Row excelRow = sheet.createRow(rowIdx);
+                        List<RectangularTextContainer> cells = rows.get(rowIdx);
+                        for (int cellIdx = 0; cellIdx < cells.size(); cellIdx++) {
+                            Cell excelCell = excelRow.createCell(cellIdx);
+                            excelCell.setCellValue(cells.get(cellIdx).getText());
+                        }
+                    }
+                    sheetCount++;
+                }
+            }
+
+            if (sheetCount == 0) {
+                return ResponseEntity.noContent().build();
+            }
+
+            ByteArrayOutputStream baos = new ByteArrayOutputStream();
+            workbook.write(baos);
+
+            HttpHeaders headers = new HttpHeaders();
+            headers.setContentDisposition(
+                    ContentDisposition.builder("attachment").filename(baseName + ".xlsx").build());
+            headers.setContentType(
+                    MediaType.parseMediaType(
+                            "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"));
+
+            return ResponseEntity.ok().headers(headers).body(baos.toByteArray());
+        }
+    }
+
+    private String getUniqueSheetName(Workbook workbook, String baseName) {
+        String safeName = WorkbookUtil.createSafeSheetName(baseName);
+        String uniqueName = safeName;
+        int count = 1;
+        while (workbook.getSheet(uniqueName) != null) {
+            String suffix = " (" + count + ")";
+            if (safeName.length() + suffix.length() > 31) {
+                uniqueName = safeName.substring(0, 31 - suffix.length()) + suffix;
+            } else {
+                uniqueName = safeName + suffix;
+            }
+            count++;
+        }
+        return uniqueName;
+    }
+}

frontend/public/locales/en-GB/translation.toml

@@ -4649,6 +4649,13 @@ prompt = "Choose page to extract table"
 submit = "Extract"
 title = "PDF to CSV"
 
+[PDFToXLSX]
+header = "PDF to Excel"
+prompt = "Choose pages to extract tables"
+submit = "Convert"
+title = "PDF to Excel (XLSX)"
+tags = "spreadsheet,excel,xlsx,table,extract,convert"
+
 [PDFToHTML]
 credit = "This service uses pdftohtml for file conversion."
 header = "PDF to HTML"

frontend/src/core/constants/convertConstants.ts

@@ -28,6 +28,7 @@ export const CONVERSION_ENDPOINTS = {
   'pdf-office-presentation': '/api/v1/convert/pdf/presentation',
   'pdf-office-text': '/api/v1/convert/pdf/text',
   'pdf-csv': '/api/v1/convert/pdf/csv',
+  'pdf-xlsx': '/api/v1/convert/pdf/xlsx',
   'pdf-markdown': '/api/v1/convert/pdf/markdown',
   'pdf-html': '/api/v1/convert/pdf/html',
   'pdf-xml': '/api/v1/convert/pdf/xml',
@@ -54,6 +55,7 @@ export const ENDPOINT_NAMES = {
   'pdf-office-presentation': 'pdf-to-presentation',
   'pdf-office-text': 'pdf-to-text',
   'pdf-csv': 'pdf-to-csv',
+  'pdf-xlsx': 'pdf-to-xlsx',
   'pdf-markdown': 'pdf-to-markdown',
   'pdf-html': 'pdf-to-html',
   'pdf-xml': 'pdf-to-xml',
@@ -116,6 +118,7 @@ export const TO_FORMAT_OPTIONS = [
   { value: 'cbz', label: 'CBZ', group: 'Archive' },
   { value: 'cbr', label: 'CBR', group: 'Archive' },
   { value: 'csv', label: 'CSV', group: 'Spreadsheet' },
+  { value: 'xlsx', label: 'XLSX', group: 'Spreadsheet' },
   { value: 'pptx', label: 'PPTX', group: 'Presentation' },
   { value: 'odp', label: 'ODP', group: 'Presentation' },
   { value: 'txt', label: 'TXT', group: 'Text' },
@@ -137,7 +140,7 @@ export const TO_FORMAT_OPTIONS = [
 export const CONVERSION_MATRIX: Record<string, string[]> = {
   'any': ['pdf'], // Mixed files always convert to PDF
   'image': ['pdf'], // Multiple images always convert to PDF
-  'pdf': ['png', 'jpg', 'gif', 'tiff', 'bmp', 'webp', 'docx', 'odt', 'pptx', 'odp', 'csv', 'txt', 'rtf', 'md', 'html', 'xml', 'pdfa', 'pdfx', 'cbz', 'cbr', 'epub', 'azw3'],
+  'pdf': ['png', 'jpg', 'gif', 'tiff', 'bmp', 'webp', 'docx', 'odt', 'pptx', 'odp', 'csv', 'xlsx', 'txt', 'rtf', 'md', 'html', 'xml', 'pdfa', 'pdfx', 'cbz', 'cbr', 'epub', 'azw3'],
   'cbz': ['pdf'],
   'docx': ['pdf'], 'doc': ['pdf'], 'odt': ['pdf'],
   'xlsx': ['pdf'], 'xls': ['pdf'], 'ods': ['pdf'],
@@ -162,6 +165,7 @@ export const EXTENSION_TO_ENDPOINT: Record<string, Record<string, string>> = {
     'docx': 'pdf-to-word', 'odt': 'pdf-to-word',
     'pptx': 'pdf-to-presentation', 'odp': 'pdf-to-presentation',
     'csv': 'pdf-to-csv',
+    'xlsx': 'pdf-to-xlsx',
     'txt': 'pdf-to-text', 'rtf': 'pdf-to-text', 'md': 'pdf-to-markdown',
     'html': 'pdf-to-html', 'xml': 'pdf-to-xml',
     'pdfa': 'pdf-to-pdfa',

frontend/src/core/data/useTranslatedToolRegistry.tsx

@@ -916,6 +916,7 @@ export function useTranslatedToolCatalog(): TranslatedToolCatalog {
           "markdown-to-pdf",
           "file-to-pdf",
           "pdf-to-csv",
+          "pdf-to-xlsx",
           "pdf-to-markdown",
           "pdf-to-pdfa",
           "eml-to-pdf",

frontend/src/core/hooks/tools/convert/useConvertOperation.ts

@@ -21,8 +21,8 @@ export const shouldProcessFilesSeparately = (
     (parameters.fromExtension === 'pdf' && isImageFormat(parameters.toExtension)) ||
     // PDF to PDF/A and PDF/X conversions (each PDF should be processed separately)
     (parameters.fromExtension === 'pdf' && (parameters.toExtension === 'pdfa' || parameters.toExtension === 'pdfx')) ||
-    // PDF to text-like formats should be one output per input
+    // PDF to text-like/spreadsheet formats should be one output per input
-    (parameters.fromExtension === 'pdf' && ['txt', 'rtf', 'csv'].includes(parameters.toExtension)) ||
+    (parameters.fromExtension === 'pdf' && ['txt', 'rtf', 'csv', 'xlsx'].includes(parameters.toExtension)) ||
   // PDF to CBR conversions (each PDF should generate its own archive)
   (parameters.fromExtension === 'pdf' && parameters.toExtension === 'cbr') ||
     // PDF to EPUB/AZW3 conversions (each PDF should generate its own ebook)
@@ -85,6 +85,8 @@ export const buildConvertFormData = (parameters: ConvertParameters, selectedFile
     formData.append("outputFormat", pdfxOptions?.outputFormat || 'pdfx');
   } else if (fromExtension === 'pdf' && toExtension === 'csv') {
     formData.append("pageNumbers", "all");
+  } else if (fromExtension === 'pdf' && toExtension === 'xlsx') {
+    formData.append("pageNumbers", "all");
   } else if (fromExtension === 'cbr' && toExtension === 'pdf') {
     formData.append("optimizeForEbook", cbrOptions.optimizeForEbook.toString());
   } else if (fromExtension === 'pdf' && toExtension === 'cbr') {

frontend/src/core/tests/helpers/conversionEndpointDiscovery.ts

@@ -107,6 +107,13 @@ const ALL_CONVERSION_ENDPOINTS: ConversionEndpoint[] = [
     description: 'Extract CSV data from PDF',
     apiPath: '/api/v1/convert/pdf/csv'
   },
+  {
+    endpoint: 'pdf-to-xlsx',
+    fromFormat: 'pdf',
+    toFormat: 'xlsx',
+    description: 'Extract Excel spreadsheet from PDF',
+    apiPath: '/api/v1/convert/pdf/xlsx'
+  },
   {
     endpoint: 'pdf-to-markdown',
     fromFormat: 'pdf',

frontend/src/core/utils/urlMapping.ts

@@ -23,6 +23,7 @@ export const URL_TO_TOOL_MAP: Record<string, ToolId> = {
   '/html-to-pdf': 'convert',
   '/markdown-to-pdf': 'convert',
   '/pdf-to-csv': 'convert',
+  '/pdf-to-xlsx': 'convert',
   '/pdf-to-img': 'convert',
   '/pdf-to-markdown': 'convert',
   '/pdf-to-pdfa': 'convert',

frontend/src/proprietary/components/shared/config/configSections/AdminEndpointsSection.tsx

@@ -143,6 +143,7 @@ export default function AdminEndpointsSection() {
     'ocr-pdf',
     'overlay-pdf',
     'pdf-to-csv',
+    'pdf-to-xlsx',
     'pdf-to-epub',
     'pdf-to-html',
     'pdf-to-img',