Skip to content

fix: Correctly handle parse errors in html tables #25

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
acoulton merged 2 commits into from
Mar 10, 2026
Merged

fix: Correctly handle parse errors in html tables #25

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3a25bda
test: Fix test data for cell containing `<time>`
acoulton Mar 10, 2026
b254318
fix: Correctly handle parse errors in html tables
acoulton Mar 10, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,10 @@ This project adheres to [Semantic Versioning](http://semver.org/).

## Unreleased

## 1.3.3 / 2026-03-10

* Fix handling and reporting parse errors when parsing an html table.

## 1.3.2 / 2025-05-06

* Support PHP 8.4 (thanks @mharmuth)
Expand Down
45 changes: 26 additions & 19 deletions src/TableParser/HTML/HTMLStringTableParser.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,9 +7,12 @@
namespace Ingenerator\BehatTableAssert\TableParser\HTML;


use Behat\Gherkin\Node\TableNode;
use Dom\HTMLDocument;
use Ingenerator\BehatTableAssert\TableNode\PaddedTableNode;
use LibXMLError;
use Masterminds\HTML5;
use function Dom\import_simplexml;

/**
* Parses an HTML string for a <table> element into a TableNode. The table must have a single row
Expand Down Expand Up @@ -90,33 +93,37 @@ public function parse($html)
*/
protected function parseHTMLString($html)
{
$old_use_internal_errors = \libxml_use_internal_errors(TRUE);
try {
$html5 = new HTML5();
$dom = $html5->loadHTML(
'<!DOCTYPE html><html>'
.'<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"></head>'
.'<body>'.\trim($html).'</body>'
.'</html>'
);
$html5 = new HTML5();
$dom = $html5->loadHTML(
'<!DOCTYPE html><html>'
.'<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"></head>'
.'<body>'.\trim($html).'</body>'
.'</html>',
);

$table_elem = $dom->getElementsByTagName('body')->item(0)->firstChild;
$table = \simplexml_import_dom($table_elem);
if ($errors = \libxml_get_errors()) {
$this->throwInvalidHTMLException($html, $errors);
}
} finally {
\libxml_clear_errors();
\libxml_use_internal_errors($old_use_internal_errors);
$table_elem = $dom->getElementsByTagName('body')->item(0)->firstChild;

if (!$table_elem instanceof \DOMElement) {
throw new \InvalidArgumentException(
sprintf("Expected html root element but got %s\n\n===HTML===\n%s", get_debug_type($table_elem), $html),
);
}
$table = \simplexml_import_dom($table_elem);
if ($errors = $html5->getErrors()) {
throw new \InvalidArgumentException(
sprintf(
"Invalid HTML:\n%s\n\n===HTML===\n%s",
implode("\n", array_map(fn($err) => ' - '.$err, $errors)),
$html,
),
);
}

return $table;
}

/**
* @param string $html
* @param LibXMLError[] $errors
* @deprecated no longer called by the library
*/
protected function throwInvalidHTMLException($html, $errors)
{
Expand Down
35 changes: 7 additions & 28 deletions test/TableParser/HTML/HTMLStringTableParserTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,37 +35,16 @@ public function test_it_throws_when_parsing_non_or_empty_string($value)
}

/**
* @testWith ["random", false]
* ["random", true]
* ["<div></div>", false]
* ["<table><thead><tr><td>1</td></tr></thead><tbody></tbody></table>", false]
* @testWith ["random text", "Expected html root element but got DOMText"]
* ["<div><17sd>illegal tag name</17sd></div>", "Invalid HTML:\n - Line 1, Col 113: Illegal tag opening"]
* ["<div></div>", "Expected a <table> but got div"]
*/
public function test_it_always_restores_state_of_libxml_error_handling(
$html,
$use_errors_before
) {
$old_setting = \libxml_use_internal_errors($use_errors_before);
try {
$this->newSubject()->parse($html);
} catch (\Exception $e) { /* ignore */
}
$errors_after = \libxml_get_errors();
$use_errors_after = \libxml_use_internal_errors($old_setting);

$this->assertSame([], $errors_after, 'Should clear libxml errors');
$this->assertEquals(
$use_errors_before,
$use_errors_after,
'Should restore libxml_use_internal_errors'
);
}

public function test_it_throws_when_parsing_html_that_is_not_a_table()
public function test_it_throws_when_parsing_html_that_is_not_a_table_or_not_valid(string $input, string $expect_msg)
{
$this->expectException(\InvalidArgumentException::class);
$this->expectExceptionMessage('Expected a <table>');
$this->expectExceptionMessage($expect_msg);

$this->newSubject()->parse('<div></div>');
$this->newSubject()->parse($input);
}

public function test_it_throws_when_parsing_table_without_thead()
Expand Down Expand Up @@ -224,7 +203,7 @@ public function provider_valid_html_tables()
'<table>'.
'<thead><tr><td>Header</td><th>Date</th></tr></thead>'.
'<tbody>'.
'<tr><td>Cell1</td><time datetime="2016-08-30T12:00:00Z">30 Aug 2016</time></tr>'.
'<tr><td>Cell1</td><td><time datetime="2016-08-30T12:00:00Z">30 Aug 2016</time></td></tr>'.
'</tbody></table>',
[
['Header', 'Date'],
Expand Down
Loading