Allow HTML Reader to load from string

We often want to export a table as an excel sheet. The system renders the
html and it seems like a waste of time to write it to the file system to
use the reader. This allows us to render the html and then just pass it to
a reader

Closes #1136

CHANGELOG.md

@@ -14,6 +14,7 @@ and this project adheres to [Semantic Versioning](https://semver.org).
 - HLookup needs an ordered list even if range_lookup is set to false [Issue #1055](https://github.com/PHPOffice/PhpSpreadsheet/issues/1055) and [PR #1076](https://github.com/PHPOffice/PhpSpreadsheet/pull/1076)
 - Improve performance of IF function calls via ranch pruning to avoid resolution of every branches [#844](https://github.com/PHPOffice/PhpSpreadsheet/pull/844)
 - MATCH function supports `*?~` Excel functionality, when match_type=0 - [Issue #1116](https://github.com/PHPOffice/PhpSpreadsheet/issues/1116)
+- Allow HTML Reader to accept HTML as a string [Issue #1136](https://github.com/PHPOffice/PhpSpreadsheet/pull/1136)
 
 ### Fixed
 

docs/topics/reading-and-writing-to-file.md

@@ -875,3 +875,31 @@ $writer->save('write.xls');
 ```
 
 Notice that it is ok to load an xlsx file and generate an xls file.
+
+## Generating Excel files from HTML content
+
+If you are generating an Excel file from pre-rendered HTML content you can do so
+automatically using the HTML Reader. This is most useful when you are generating 
+Excel files from web application content that would be downloaded/sent to a user.
+
+For example:
+
+```php
+$htmlString = '<table>
+                  <tr>
+                      <td>Hello World</td>
+                  </tr>
+                  <tr>
+                      <td>Hello<br />World</td>
+                  </tr>
+                  <tr>
+                      <td>Hello<br>World</td>
+                  </tr>
+              </table>';
+
+$reader = new \PhpOffice\PhpSpreadsheet\Reader\Html();
+$spreadsheet = $reader->loadFromString($htmlString);
+
+$writer = \PhpOffice\PhpSpreadsheet\IOFactory::createWriter($spreadsheet, 'Xls');
+$writer->save('write.xls'); 
+```

src/PhpSpreadsheet/Reader/Html.php

@@ -592,28 +592,64 @@ class Html extends BaseReader
             throw new Exception($pFilename . ' is an Invalid HTML file.');
         }
 
-        // Create new sheet
+        // Create a new DOM object
-        while ($spreadsheet->getSheetCount() <= $this->sheetIndex) {
-            $spreadsheet->createSheet();
-        }
-        $spreadsheet->setActiveSheetIndex($this->sheetIndex);
-
-        //    Create a new DOM object
         $dom = new DOMDocument();
-        //    Reload the HTML file into the DOM object
+        // Reload the HTML file into the DOM object
         $loaded = $dom->loadHTML(mb_convert_encoding($this->securityScanner->scanFile($pFilename), 'HTML-ENTITIES', 'UTF-8'));
         if ($loaded === false) {
             throw new Exception('Failed to load ' . $pFilename . ' as a DOM Document');
         }
 
-        //    Discard white space
+        return $this->loadDocument($dom, $spreadsheet);
-        $dom->preserveWhiteSpace = false;
+    }
+
+    /**
+     * Spreadsheet from content.
+     *
+     * @param string $content
+     *
+     * @throws Exception
+     *
+     * @return Spreadsheet
+     */
+    public function loadFromString($content): Spreadsheet
+    {
+        //    Create a new DOM object
+        $dom = new DOMDocument();
+        //    Reload the HTML file into the DOM object
+        $loaded = $dom->loadHTML(mb_convert_encoding($this->securityScanner->scan($content), 'HTML-ENTITIES', 'UTF-8'));
+        if ($loaded === false) {
+            throw new Exception('Failed to load content as a DOM Document');
+        }
+
+        return $this->loadDocument($dom, new Spreadsheet());
+    }
+
+    /**
+     * Loads PhpSpreadsheet from DOMDocument into PhpSpreadsheet instance.
+     *
+     * @param DOMDocument $document
+     * @param Spreadsheet $spreadsheet
+     *
+     * @throws \PhpOffice\PhpSpreadsheet\Exception
+     *
+     * @return Spreadsheet
+     */
+    private function loadDocument(DOMDocument $document, Spreadsheet $spreadsheet): Spreadsheet
+    {
+        while ($spreadsheet->getSheetCount() <= $this->sheetIndex) {
+            $spreadsheet->createSheet();
+        }
+        $spreadsheet->setActiveSheetIndex($this->sheetIndex);
+
+        // Discard white space
+        $document->preserveWhiteSpace = false;
 
         $row = 0;
         $column = 'A';
         $content = '';
         $this->rowspan = [];
-        $this->processDomElement($dom, $spreadsheet->getActiveSheet(), $row, $column, $content);
+        $this->processDomElement($document, $spreadsheet->getActiveSheet(), $row, $column, $content);
 
         // Return
         return $spreadsheet;

tests/PhpSpreadsheetTests/Reader/HtmlTest.php

@@ -299,6 +299,36 @@ class HtmlTest extends TestCase
         unlink($filename);
     }
 
+    public function testCanLoadFromString()
+    {
+        $html = '<table>
+                    <tr>
+                        <td>Hello World</td>
+                    </tr>
+                    <tr>
+                        <td>Hello<br />World</td>
+                    </tr>
+                    <tr>
+                        <td>Hello<br>World</td>
+                    </tr>
+                </table>';
+        $spreadsheet = (new Html())->loadFromString($html);
+        $firstSheet = $spreadsheet->getSheet(0);
+
+        $cellStyle = $firstSheet->getStyle('A1');
+        self::assertFalse($cellStyle->getAlignment()->getWrapText());
+
+        $cellStyle = $firstSheet->getStyle('A2');
+        self::assertTrue($cellStyle->getAlignment()->getWrapText());
+        $cellValue = $firstSheet->getCell('A2')->getValue();
+        $this->assertContains("\n", $cellValue);
+
+        $cellStyle = $firstSheet->getStyle('A3');
+        self::assertTrue($cellStyle->getAlignment()->getWrapText());
+        $cellValue = $firstSheet->getCell('A3')->getValue();
+        $this->assertContains("\n", $cellValue);
+    }
+
     /**
      * @param string $html
      *