Skip to content

Fix HtmlToDjot container and list block serialization #173

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
dereuromark merged 3 commits into from
Apr 1, 2026
Merged

Fix HtmlToDjot container and list block serialization #173

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
daa4753
Fix HtmlToDjot container and list block serialization
dereuromark Apr 1, 2026
710751c
Fix HtmlToDjot list serializer docblock
dereuromark Apr 1, 2026
7ab7de6
Cover HtmlToDjot container and list helper paths
dereuromark Apr 1, 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
128 changes: 106 additions & 22 deletions src/Converter/HtmlToDjot.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -219,8 +219,9 @@ protected function processNode(DOMNode $node): string

return match ($tagName) {
'section' => $this->processSection($node),
'html', 'body', 'article', 'main', 'header', 'footer', 'nav', 'aside',
'address', 'dialog', 'fieldset', 'form', 'hgroup', 'menu', 'search' => $this->processBlock($node),
'html', 'body' => $this->processBlock($node),
'article', 'main', 'header', 'footer', 'nav', 'aside',
'address', 'dialog', 'fieldset', 'form', 'hgroup', 'menu', 'search' => $this->processGenericBlockContainer($node),
'details' => $this->processDetails($node),
'div' => $this->processDiv($node),
'p' => $this->processParagraph($node),
Expand Down Expand Up @@ -541,8 +542,25 @@ protected function processDetails(DOMElement $node): string
return $this->processCollapsibleAdmonition($node);
}

// Otherwise treat as regular block
return $this->processBlock($node);
return $this->processGenericBlockContainer($node);
}

protected function processGenericBlockContainer(DOMElement $node): string
{
$tagName = strtolower($node->tagName);
$attrs = $this->formatBlockAttributes($node);

if ($tagName !== 'details' && $attrs === '') {
return $this->processBlock($node);
}

$content = trim($this->processBlock($node));
$output = $attrs . '::: ' . $tagName . "\n";
if ($content !== '') {
$output .= $content . "\n";
}

return $output . ":::\n\n";
}

/**
Expand Down Expand Up @@ -1208,8 +1226,9 @@ protected function processList(DOMElement $node): string

$prefix = $isOrdered ? $counter . $marker . ' ' : $marker . ' ' . $checkbox;

// Process list item content, separating text from nested lists
$textContent = '';
// Process list item content, separating nested lists from other content
$contentParts = [];
$inlineBuffer = '';
$nestedContent = '';

foreach ($child->childNodes as $liChild) {
Expand All @@ -1221,33 +1240,56 @@ protected function processList(DOMElement $node): string
} elseif ($childTag === 'input' && $liChild->getAttribute('type') === 'checkbox') {
// Skip checkbox inputs (handled via $checkbox prefix)
continue;
} elseif (in_array($childTag, $this->blockElements, true)) {
$this->flushListItemInlineBuffer($contentParts, $inlineBuffer);
$content = trim($this->processNode($liChild));
if ($content !== '') {
$contentParts[] = $content;
}
} else {
$textContent .= $this->processNode($liChild);
$inlineBuffer .= $this->processNode($liChild);
}
} else {
$textContent .= $this->processNode($liChild);
$inlineBuffer .= $this->processNode($liChild);
}
}

$textContent = trim($textContent);

// Handle multi-line text content
$lines = explode("\n", $textContent);
$firstLine = array_shift($lines);
$output .= $indent . $prefix . $firstLine . "\n";
$this->flushListItemInlineBuffer($contentParts, $inlineBuffer);

// Add list item attributes on next line (indented)
$liAttrs = $this->getElementAttributes($child);
if ($liAttrs !== '') {
$output .= $indent . str_repeat(' ', strlen($prefix)) . '{' . $liAttrs . "}\n";
}
$continuation = $indent . str_repeat(' ', strlen($prefix));

if ($lines) {
$continuation = str_repeat(' ', strlen($prefix));
foreach ($lines as $line) {
if (trim($line) !== '') {
$output .= $indent . $continuation . $line . "\n";
if ($contentParts === []) {
$output .= $indent . $prefix . "\n";
if ($liAttrs !== '') {
$output .= $continuation . '{' . $liAttrs . "}\n";
}
} else {
$firstPart = array_shift($contentParts);
$firstPartLines = preg_split('/\R/', $firstPart) ?: [''];
$firstLine = array_shift($firstPartLines);

if ($this->isListItemBlockPart($firstPart)) {
$output .= $indent . $prefix . "\n\n";
if ($liAttrs !== '') {
$output .= $continuation . '{' . $liAttrs . "}\n";
}
$output .= $this->indentListItemPart($firstPart, $continuation) . "\n";
} else {
$output .= $indent . $prefix . $firstLine . "\n";
if ($liAttrs !== '') {
$output .= $continuation . '{' . $liAttrs . "}\n";
}
foreach ($firstPartLines as $line) {
if (trim($line) !== '') {
$output .= $continuation . $line . "\n";
}
}
}

foreach ($contentParts as $part) {
$output .= "\n" . $this->indentListItemPart($part, $continuation) . "\n";
}
}

Expand All @@ -1271,6 +1313,41 @@ protected function processListItem(DOMElement $node): string
return $this->processChildren($node);
}

/**
* @param list<string> $contentParts
* @param string $inlineBuffer
*/
protected function flushListItemInlineBuffer(array &$contentParts, string &$inlineBuffer): void
{
$inlineContent = trim($inlineBuffer);
if ($inlineContent !== '') {
$contentParts[] = $inlineContent;
}
$inlineBuffer = '';
}

protected function isListItemBlockPart(string $content): bool
{
return str_contains($content, "\n")
|| str_starts_with($content, '>')
|| str_starts_with($content, '```')
|| str_starts_with($content, ':::')
|| str_starts_with($content, '|')
|| str_starts_with($content, '#');
}

protected function indentListItemPart(string $content, string $indent): string
{
$lines = preg_split('/\R/', $content) ?: [];
$output = [];

foreach ($lines as $line) {
$output[] = $line === '' ? '' : $indent . $line;
}

return implode("\n", $output);
}

/**
* Check if a list item contains a checkbox input
*/
Expand Down Expand Up @@ -2088,6 +2165,13 @@ protected function cleanup(string $djot): string
continue;
}

// Preserve indented continuation lines inside list items
if ($inList && preg_match('/^\s{2,}\S/', $line)) {
$result[] = $line;

continue;
}

// Preserve indentation for definition content (indented lines after `: term`)
if ($inDefinitionList && preg_match('/^ /', $line)) {
$result[] = $line;
Expand Down
76 changes: 76 additions & 0 deletions tests/TestCase/Converter/HtmlToDjotTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -582,6 +582,69 @@ public function testNestedListWithBlankLine(): void
$this->assertMatchesRegularExpression('/- Item 2\n\n\s+- Nested 1/', $result);
}

public function testListItemWithMultipleParagraphsKeepsParagraphBreaks(): void
{
$html = '<ul><li><p>One</p><p>Two</p></li></ul>';
$result = $this->converter->convert($html);

$this->assertSame("- One\n\n Two\n", $result);
$htmlBack = (new DjotConverter())->convert($result);
$this->assertStringContainsString("<li>\n<p>One</p>\n<p>Two</p>\n</li>", $htmlBack);
}

public function testListItemWithBlockquoteKeepsNestedBlockquote(): void
{
$html = '<ul><li><p>One</p><blockquote><p>Quote</p></blockquote></li></ul>';
$result = $this->converter->convert($html);

$this->assertSame("- One\n\n > Quote\n", $result);
$htmlBack = (new DjotConverter())->convert($result);
$this->assertStringContainsString("<li>\n<p>One</p>\n<blockquote>", $htmlBack);
$this->assertStringContainsString('<p>Quote</p>', $htmlBack);
}

public function testListItemWithOnlyCodeBlockKeepsIndentedCodeFence(): void
{
$html = '<ul><li><pre><code>code</code></pre></li></ul>';
$result = $this->converter->convert($html);

$this->assertSame("- \n\n ```\n code\n ```\n", $result);
$htmlBack = (new DjotConverter())->convert($result);
$this->assertStringContainsString("<li>\n<pre><code>code", $htmlBack);
}

public function testEmptyListItemWithAttributesKeepsIndentedAttributeBlock(): void
{
$html = '<ul><li id="empty"></li></ul>';
$result = $this->converter->convert($html);

$this->assertSame("- \n {#empty}\n", $result);
}

public function testListItemWithDetailsKeepsIndentedTaggedContainer(): void
{
$html = '<ul><li><details><summary>Title</summary><p>Body</p></details></li></ul>';
$result = $this->converter->convert($html);

$this->assertSame("- \n\n ::: details\n Title\n\n Body\n :::\n", $result);
}

public function testListItemWithHeadingKeepsIndentedHeadingBlock(): void
{
$html = '<ul><li><h2>Head</h2></li></ul>';
$result = $this->converter->convert($html);

$this->assertSame("- \n\n ## Head\n", $result);
}

public function testHtml5BlockContainerWithoutAttributesFallsBackToPlainBlock(): void
{
$html = '<article><p>X</p></article>';
$result = $this->converter->convert($html);

$this->assertSame("X\n", $result);
}

public function testDeeplyNestedList(): void
{
$html = '<ul><li>Level 1<ul><li>Level 2<ul><li>Level 3</li></ul></li></ul></li></ul>';
Expand Down Expand Up @@ -1013,6 +1076,7 @@ public function testDetailsElement(): void
$html = '<details><summary>Click to expand</summary><p>Hidden content here</p></details>';
$result = $this->converter->convert($html);

$this->assertStringContainsString("::: details\n", $result);
$this->assertStringContainsString('Click to expand', $result);
$this->assertStringContainsString('Hidden content here', $result);
}
Expand Down Expand Up @@ -1084,10 +1148,22 @@ public function testHtml5BlockElementsWithAttributes(): void
$html = '<details class="faq" id="q1"><summary>Question?</summary><p>Answer.</p></details>';
$result = $this->converter->convert($html);

$this->assertStringContainsString('{#q1 .faq}', $result);
$this->assertStringContainsString("::: details\n", $result);
$this->assertStringContainsString('Question?', $result);
$this->assertStringContainsString('Answer.', $result);
}

public function testHtml5BlockContainerWithAttributesUsesTaggedFencedDiv(): void
{
$html = '<article id="a1" data-kind="post"><p>X</p></article>';
$result = $this->converter->convert($html);

$this->assertStringContainsString('{#a1 data-kind=post}', $result);
$this->assertStringContainsString("::: article\n", $result);
$this->assertStringContainsString("X\n", $result);
}

// ==================== Round-trip Table Separators ====================

public function testTableSeparatorWidthsRoundTrip(): void
Expand Down
Loading