mirror of
https://github.com/PHPOffice/PhpSpreadsheet.git
synced 2026-08-30 12:07:56 +00:00
oleibman
5de82981d8
* 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.
37 lines
1.5 KiB
PHP
37 lines
1.5 KiB
PHP
<?php
|
|
|
|
namespace PhpOffice\PhpSpreadsheetTests\Reader\Html;
|
|
|
|
use PhpOffice\PhpSpreadsheet\Reader\Html;
|
|
use PHPUnit\Framework\TestCase;
|
|
|
|
class Issue2942Test extends TestCase
|
|
{
|
|
public function testLoadFromString(): void
|
|
{
|
|
$content = '<table><tbody><tr><td>éàâèî</td></tr></tbody></table>';
|
|
$reader = new Html();
|
|
$spreadsheet = $reader->loadFromString($content);
|
|
$sheet = $spreadsheet->getActiveSheet();
|
|
self::assertSame('éàâèî', $sheet->getCell('A1')->getValue());
|
|
}
|
|
|
|
public function testLoadFromFile(): void
|
|
{
|
|
$file = 'tests/data/Reader/HTML/utf8chars.html';
|
|
$reader = new Html();
|
|
$spreadsheet = $reader->loadSpreadsheetFromFile($file);
|
|
$sheet = $spreadsheet->getActiveSheet();
|
|
self::assertSame('Test Utf-8 characters voilà', $sheet->getTitle());
|
|
self::assertSame('éàâèî', $sheet->getCell('A1')->getValue());
|
|
self::assertSame('αβγδε', $sheet->getCell('B1')->getValue());
|
|
self::assertSame('𐐁𐐂𐐃 & だけち', $sheet->getCell('A2')->getValue());
|
|
self::assertSame('אבגדה', $sheet->getCell('B2')->getValue());
|
|
self::assertSame('𪔀𪔁𪔂', $sheet->getCell('C2')->getValue());
|
|
self::assertSame('᠐᠑᠒', $sheet->getCell('A3')->getValue());
|
|
self::assertSame('അആ', $sheet->getCell('B3')->getValue());
|
|
self::assertSame('กขฃ', $sheet->getCell('C3')->getValue());
|
|
self::assertSame('✀✐✠', $sheet->getCell('D3')->getValue());
|
|
}
|
|
}
|