Clientbase
/
PhpSpreadsheet
mirror of https://github.com/basemaster/PhpSpreadsheet.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Avoid Duplicate Titles When Reading Multiple HTML Files (#1829) 

This issue arose while researching issue #1823. The issue was not a bug;
it just required clarification to the author of how to use the software.
But, while researching, I discovered that loading html into 2
sheets of a spreadsheet has a problem if the html title tag is the same
for the 2 sheets. PhpSpreadsheet would be able to save the resulting file,
but Excel would not be able to read it properly because of the duplicate title.
The worksheet setTitle method allows for disambiguation is such a circumstance.
The html reader passed a parameter indicating "don't disambiguate", but I can't
see any harm in changing that to "disambiguate". An extremely simple fix,
with tests to back it up.
This commit is contained in:
oleibman 2021-02-27 06:10:04 -08:00 committed by GitHub
parent 25f7dcb9fd
commit cb23cca3ec
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 30 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/PhpSpreadsheet/Reader/Html.php
View File

@ -320,7 +320,7 @@ class Html extends BaseReader
{
if ($child->nodeName === 'title') {
$this->processDomElement($child, $sheet, $row, $column, $cellContent);
$sheet->setTitle($cellContent, true, false);
$sheet->setTitle($cellContent, true, true);
$cellContent = '';
} else {
$this->processDomElementSpanEtc($sheet, $row, $column, $cellContent, $child, $attributeArray);

29
tests/PhpSpreadsheetTests/Reader/Html/HtmlLoadStringTest.php
View File

@ -89,4 +89,33 @@ class HtmlLoadStringTest extends TestCase
$spreadsheet = $reader->loadFromString($html, $spreadsheet);
self::assertEquals(2, $spreadsheet->getSheetCount());
}
public function testCanLoadDuplicateTitle(): void
{
$html = <<<'EOF'
<html>
<head>
<title>Sheet</title>
</head>
<body>
<table><tr><td>1</td></tr></table>
</body>
</html>
EOF;
$reader = new \PhpOffice\PhpSpreadsheet\Reader\Html();
$spreadsheet = $reader->loadFromString($html);
$reader->setSheetIndex(1);
$reader->loadFromString($html, $spreadsheet);
$reader->setSheetIndex(2);
$reader->loadFromString($html, $spreadsheet);
$sheet = $spreadsheet->getSheet(0);
self::assertEquals(1, $sheet->getCell('A1')->getValue());
self::assertEquals('Sheet', $sheet->getTitle());
$sheet = $spreadsheet->getSheet(1);
self::assertEquals(1, $sheet->getCell('A1')->getValue());
self::assertEquals('Sheet 1', $sheet->getTitle());
$sheet = $spreadsheet->getSheet(2);
self::assertEquals(1, $sheet->getCell('A1')->getValue());
self::assertEquals('Sheet 2', $sheet->getTitle());
}
}