Files
oleibman 5de82981d8 Html Reader Not Handling non-ASCII Data Correctly (#2943)
* Html Reader Not Handling non-ASCII Data Correctly

Fix #2942. Code was changed by #2894 because PHP8.2 will deprecate how it was being done. See linked issue for more details. Dom loadhtml assumes ISO-8859-1 in the absence of a charset attribute or equivalent, and there is no way to override that assumption. Sigh. The suggested replacements are unsuitable in one way or another. I think this will work with minimal disruption (replace ampersand, less than, and greater than with entities representing illegal characters, then use htmlentities, then restore ampersand, less than, and greater than).

* Better Implementation

Use regexp to escape non-ASCII. Less kludgey, less reliant on the vagaries of the PHP maintainers.

* Additional Tests

Test non-ASCII outside of cell contents: sheet title, image alt attribute.

* Apply Same Change in Second Location

Forgot to change loadFromString.

* Additional Test

Confirm escaped ampersand is handled correctly.
2022-07-16 22:08:44 -07:00

85 lines
3.0 KiB
PHP

<?php
namespace PhpOffice\PhpSpreadsheetTests\Reader\Html;
use PhpOffice\PhpSpreadsheet\Worksheet\Drawing;
use PHPUnit\Framework\TestCase;
class HtmlImageTest extends TestCase
{
public function testCanInsertImage(): void
{
$imagePath = realpath(__DIR__ . '/../../../data/Reader/HTML/image.jpg');
$html = '<table>
<tr>
<td><img src="' . $imagePath . '" alt="test image voilà"></td>
</tr>
</table>';
$filename = HtmlHelper::createHtml($html);
$spreadsheet = HtmlHelper::loadHtmlIntoSpreadsheet($filename, true);
$firstSheet = $spreadsheet->getSheet(0);
/** @var Drawing $drawing */
$drawing = $firstSheet->getDrawingCollection()[0];
self::assertEquals($imagePath, $drawing->getPath());
self::assertEquals('A1', $drawing->getCoordinates());
self::assertEquals('test image voilà', $drawing->getName());
self::assertEquals('100', $drawing->getWidth());
self::assertEquals('100', $drawing->getHeight());
}
public function testCanInsertImageWidth(): void
{
$imagePath = realpath(__DIR__ . '/../../../data/Reader/HTML/image.jpg');
$html = '<table>
<tr>
<td><img src="' . $imagePath . '" alt="test image" width="50"></td>
</tr>
</table>';
$filename = HtmlHelper::createHtml($html);
$spreadsheet = HtmlHelper::loadHtmlIntoSpreadsheet($filename, true);
$firstSheet = $spreadsheet->getSheet(0);
/** @var Drawing $drawing */
$drawing = $firstSheet->getDrawingCollection()[0];
self::assertEquals('50', $drawing->getWidth());
self::assertEquals('50', $drawing->getHeight());
}
public function testCanInsertImageHeight(): void
{
$imagePath = realpath(__DIR__ . '/../../../data/Reader/HTML/image.jpg');
$html = '<table>
<tr>
<td><img src="' . $imagePath . '" height="75"></td>
</tr>
</table>';
$filename = HtmlHelper::createHtml($html);
$spreadsheet = HtmlHelper::loadHtmlIntoSpreadsheet($filename, true);
$firstSheet = $spreadsheet->getSheet(0);
/** @var Drawing $drawing */
$drawing = $firstSheet->getDrawingCollection()[0];
self::assertEquals('', $drawing->getName());
self::assertEquals('75', $drawing->getWidth());
self::assertEquals('75', $drawing->getHeight());
}
public function testImageWithourSrc(): void
{
$html = '<table>
<tr>
<td><img></td>
</tr>
</table>';
$filename = HtmlHelper::createHtml($html);
$spreadsheet = HtmlHelper::loadHtmlIntoSpreadsheet($filename, true);
$firstSheet = $spreadsheet->getSheet(0);
self::assertCount(0, $firstSheet->getDrawingCollection());
}
}