mirror of
https://github.com/PHPOffice/PhpSpreadsheet.git
synced 2026-09-03 14:10:27 +00:00
oleibman
09584d2950
Fix #1284, which was closed as stale in 2019, but which I will now reopen. Html Reader converts *Unicode* whitespace characters in a DOM text node to space. However, Html treats only space, tab, CR, LF, vertical tab, and form-feed as whitespace. Using a regular expression with the `u` (Unicode) modifier causes a number of other characters to be converted to space inappropriately. The issue mentions "ideographic space" in particular, stating that it is used for formatting and should be preserved. "Non-breaking space" is also used in the same way and should also be preserved. An exception is made for a text node consisting of a single non-breaking space, since that is used as a placeholder by Html Writer; my own guess is that this is the reason why the Unicode modifier was used in the first place.
37 lines
1.6 KiB
PHP
37 lines
1.6 KiB
PHP
<?php
|
|
|
|
declare(strict_types=1);
|
|
|
|
namespace PhpOffice\PhpSpreadsheetTests\Reader\Html;
|
|
|
|
use PhpOffice\PhpSpreadsheet\Spreadsheet;
|
|
use PhpOffice\PhpSpreadsheetTests\Functional\AbstractFunctional;
|
|
|
|
class Issue1284Test extends AbstractFunctional
|
|
{
|
|
public function testIssue1284(): void
|
|
{
|
|
$ideographicSpace = "\u{3000}";
|
|
$nbsp = "\u{a0}";
|
|
$spreadsheetOld = new Spreadsheet();
|
|
$osheet = $spreadsheetOld->getActiveSheet();
|
|
$osheet->getCell('A1')->setValue('# item 1');
|
|
$osheet->getCell('A2')->setValue("$ideographicSpace# item 2");
|
|
$osheet->getCell('A3')->setValue("$ideographicSpace$ideographicSpace# item 3");
|
|
$osheet->getCell('A4')->setValue("$nbsp# item\t4");
|
|
$osheet->getCell('A5')->setValue("$nbsp$nbsp# item 5");
|
|
|
|
$spreadsheet = $this->writeAndReload($spreadsheetOld, 'Html');
|
|
$spreadsheetOld->disconnectWorksheets();
|
|
|
|
$sheet = $spreadsheet->getActiveSheet();
|
|
self::assertSame('# item 1', $sheet->getCell('A1')->getValue(), 'nothing changed');
|
|
self::assertSame("$ideographicSpace# item 2", $sheet->getCell('A2')->getValue(), 'nothing changed including 1 ideographic space');
|
|
self::assertSame("$ideographicSpace$ideographicSpace# item 3", $sheet->getCell('A3')->getValue(), 'nothing changed including 2 ideographic spaces');
|
|
self::assertSame("$nbsp# item 4", $sheet->getCell('A4')->getValue(), 'nbsp unchanged, 2 spaces reduced to 1, tab changed to space');
|
|
self::assertSame("$nbsp$nbsp# item 5", $sheet->getCell('A5')->getValue(), 'many spaces reduced to 1');
|
|
|
|
$spreadsheet->disconnectWorksheets();
|
|
}
|
|
}
|