webapp/bookstack
1
0
Fork 0
mirror of https://github.com/BookStackApp/BookStack.git synced 2025-07-28 17:02:04 +03:00
Code Activity

Includes: Switched page to new system

Browse Source 
- Added mulit-level depth parsing.
- Updating usage of HTML doc in page content to be efficient.
- Removed now redundant PageContentTest cases.
- Made some include system fixes based upon testing.
This commit is contained in:
Dan Brown
2023-11-27 19:54:47 +00:00
parent 4874dc1304
commit 71c93c8878
7 changed files with 60 additions and 148 deletions
Download Patch File Download Diff File Expand all files Collapse all files

113
app/Entities/Tools/PageContent.php
View File

@ -275,21 +275,33 @@ class PageContent
*/
public function render(bool $blankIncludes = false): string
{
$content = $this->page->html ?? '';
$html = $this->page->html ?? '';
if (empty($html)) {
return $html;
}
$doc = new HtmlDocument($html);
$contentProvider = function (int $id) use ($blankIncludes) {
if ($blankIncludes) {
return '';
}
return Page::visible()->find($id)->html ?? '';
};
$parser = new PageIncludeParser($doc, $contentProvider);
$nodesAdded = 1;
for ($includeDepth = 0; $includeDepth < 3 && $nodesAdded !== 0; $includeDepth++) {
$nodesAdded = $parser->parse();
}
if (!config('app.allow_content_scripts')) {
$content = HtmlContentFilter::removeScripts($content);
HtmlContentFilter::removeScriptsFromDocument($doc);
}
if ($blankIncludes) {
$content = $this->blankPageIncludes($content);
} else {
for ($includeDepth = 0; $includeDepth < 3; $includeDepth++) {
$content = $this->parsePageIncludes($content);
}
}
return $content;
return $doc->getBodyInnerHtml();
}
/**
@ -337,83 +349,4 @@ class PageContent
return $tree->toArray();
}
/**
* Remove any page include tags within the given HTML.
*/
protected function blankPageIncludes(string $html): string
{
return preg_replace("/{{@\s?([0-9].*?)}}/", '', $html);
}
/**
* Parse any include tags "{{@<page_id>#section}}" to be part of the page.
*/
protected function parsePageIncludes(string $html): string
{
$matches = [];
preg_match_all("/{{@\s?([0-9].*?)}}/", $html, $matches);
foreach ($matches[1] as $index => $includeId) {
$fullMatch = $matches[0][$index];
$splitInclude = explode('#', $includeId, 2);
// Get page id from reference
$pageId = intval($splitInclude[0]);
if (is_nan($pageId)) {
continue;
}
// Find page to use, and default replacement to empty string for non-matches.
/** @var ?Page $matchedPage */
$matchedPage = Page::visible()->find($pageId);
$replacement = '';
if ($matchedPage && count($splitInclude) === 1) {
// If we only have page id, just insert all page html and continue.
$replacement = $matchedPage->html;
} elseif ($matchedPage && count($splitInclude) > 1) {
// Otherwise, if our include tag defines a section, load that specific content
$innerContent = $this->fetchSectionOfPage($matchedPage, $splitInclude[1]);
$replacement = trim($innerContent);
}
$themeReplacement = Theme::dispatch(
ThemeEvents::PAGE_INCLUDE_PARSE,
$includeId,
$replacement,
clone $this->page,
$matchedPage ? (clone $matchedPage) : null,
);
// Perform the content replacement
$html = str_replace($fullMatch, $themeReplacement ?? $replacement, $html);
}
return $html;
}
/**
* Fetch the content from a specific section of the given page.
*/
protected function fetchSectionOfPage(Page $page, string $sectionId): string
{
$topLevelTags = ['table', 'ul', 'ol', 'pre'];
$doc = new HtmlDocument($page->html);
// Search included content for the id given and blank out if not exists.
$matchingElem = $doc->getElementById($sectionId);
if ($matchingElem === null) {
return '';
}
// Otherwise replace the content with the found content
// Checks if the top-level wrapper should be included by matching on tag types
$isTopLevel = in_array(strtolower($matchingElem->nodeName), $topLevelTags);
if ($isTopLevel) {
return $doc->getNodeOuterHtml($matchingElem);
}
return $doc->getNodeInnerHtml($matchingElem);
}
}

2
app/Entities/Tools/PageIncludeContent.php
View File

@ -14,7 +14,7 @@ class PageIncludeContent
*/
protected array $contents = [];
protected bool $isTopLevel;
protected bool $isTopLevel = false;
public function __construct(
string $html,

24
app/Entities/Tools/PageIncludeParser.php
View File

@ -20,19 +20,19 @@ class PageIncludeParser
protected array $toCleanup = [];
public function __construct(
protected string $pageHtml,
protected HtmlDocument $doc,
protected Closure $pageContentForId,
) {
}
/**
* Parse out the include tags.
* Returns the count of new content DOM nodes added to the document.
*/
public function parse(): string
public function parse(): int
{
$doc = new HtmlDocument($this->pageHtml);
$tags = $this->locateAndIsolateIncludeTags($doc);
$nodesAdded = 0;
$tags = $this->locateAndIsolateIncludeTags();
foreach ($tags as $tag) {
$htmlContent = $this->pageContentForId->call($this, $tag->getPageId());
@ -48,12 +48,14 @@ class PageIncludeParser
}
}
$this->replaceNodeWithNodes($tag->domNode, $content->toDomNodes());
$replacementNodes = $content->toDomNodes();
$nodesAdded += count($replacementNodes);
$this->replaceNodeWithNodes($tag->domNode, $replacementNodes);
}
$this->cleanup();
return $doc->getBodyInnerHtml();
return $nodesAdded;
}
/**
@ -61,9 +63,9 @@ class PageIncludeParser
* own nodes in the DOM for future targeted manipulation.
* @return PageIncludeTag[]
*/
protected function locateAndIsolateIncludeTags(HtmlDocument $doc): array
protected function locateAndIsolateIncludeTags(): array
{
$includeHosts = $doc->queryXPath("//body//*[text()[contains(., '{{@')]]");
$includeHosts = $this->doc->queryXPath("//*[text()[contains(., '{{@')]]");
$includeTags = [];
/** @var DOMNode $node */
@ -125,7 +127,7 @@ class PageIncludeParser
foreach ($replacements as $replacement) {
if ($replacement->ownerDocument !== $targetDoc) {
$replacement = $targetDoc->adoptNode($replacement);
$replacement = $targetDoc->importNode($replacement, true);
}
$toReplace->parentNode->insertBefore($replacement, $toReplace);
@ -190,7 +192,7 @@ class PageIncludeParser
return $parent;
}
$parent = $parent->parentElement;
$parent = $parent->parentNode;
} while ($parent !== null);
return null;