Specify data type in html tags using attributes #3444

Author: PouriaSeyfi

src/PhpSpreadsheet/Reader/Html.php

@@ -564,6 +564,13 @@ private function processDomElementDataFormat(Worksheet $sheet, int $row, string
         }
     }
 
+    private function processDomElementDataType(Worksheet $sheet, int $row, string $column, array $attributeArray): void
+    {
+        if (isset($attributeArray['data-type'])) {
+            $sheet->getCell($column . $row)->setDataType($attributeArray['data-type']);
+        }
+    }
+
     private function processDomElementThTd(Worksheet $sheet, int &$row, string &$column, string &$cellContent, DOMElement $child, array &$attributeArray): void
     {
         while (isset($this->rowspan[$column . $row])) {
@@ -582,6 +589,7 @@ private function processDomElementThTd(Worksheet $sheet, int &$row, string &$col
         $this->processDomElementAlign($sheet, $row, $column, $attributeArray);
         $this->processDomElementVAlign($sheet, $row, $column, $attributeArray);
         $this->processDomElementDataFormat($sheet, $row, $column, $attributeArray);
+        $this->processDomElementDataType($sheet, $row, $column, $attributeArray);
 
         if (isset($attributeArray['rowspan'], $attributeArray['colspan'])) {
             //create merging rowspan and colspan

tests/PhpSpreadsheetTests/Reader/Html/HtmlTest.php

@@ -2,6 +2,7 @@
 
 namespace PhpOffice\PhpSpreadsheetTests\Reader\Html;
 
+use PhpOffice\PhpSpreadsheet\Cell\DataType;
 use PhpOffice\PhpSpreadsheet\Reader\Exception as ReaderException;
 use PhpOffice\PhpSpreadsheet\Reader\Html;
 use PhpOffice\PhpSpreadsheet\Style\Alignment;
@@ -363,4 +364,20 @@ public function testBorderWithColspan(): void
             self::assertEquals(Border::BORDER_THIN, $border->getBorderStyle());
         }
     }
+
+    public function testDataType(): void
+    {
+        $html = '<table>
+                    <tr>
+                        <td data-type="b">1</td>
+                        <td data-type="s">12345678987654321</td>
+                    </tr>
+                </table>';
+        $reader = new Html();
+        $spreadsheet = $reader->loadFromString($html);
+        $firstSheet = $spreadsheet->getSheet(0);
+
+        self::assertEquals(DataType::TYPE_BOOL, $firstSheet->getCell('A1')->getDataType());
+        self::assertEquals(DataType::TYPE_STRING, $firstSheet->getCell('B1')->getDataType());
+    }
 }