Repository navigation
Expand file tree
/
Copy pathPageIncludeParser.php
More file actions
223 lines (187 loc) · 7.12 KB
/
Copy pathPageIncludeParser.php
File metadata and controls
223 lines (187 loc) · 7.12 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
<?php
namespace BookStack\Entities\Tools;
use BookStack\Util\HtmlDocument;
use Closure;
use DOMDocument;
use DOMElement;
use DOMNode;
class PageIncludeParser
{
protected static string $includeTagRegex = "/{{@\s?([0-9].*?)}}/";
/**
* Nodes to clean up and remove if left empty after a parsing operation.
* @var DOMNode[]
*/
protected array $toCleanup = [];
/**
* @param Closure(PageIncludeTag $tag): PageContent $pageContentForId
*/
public function __construct(
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(): int
{
$nodesAdded = 0;
$tags = $this->locateAndIsolateIncludeTags();
foreach ($tags as $tag) {
/** @var PageIncludeContent $content */
$content = $this->pageContentForId->call($this, $tag);
if (!$content->isInline()) {
$parentP = $this->getParentParagraph($tag->domNode);
$isWithinParentP = $parentP === $tag->domNode->parentNode;
if ($parentP && $isWithinParentP) {
$this->splitNodeAtChildNode($tag->domNode->parentNode, $tag->domNode);
} else if ($parentP) {
$this->moveTagNodeToBesideParent($tag, $parentP);
}
}
$replacementNodes = $content->toDomNodes();
$nodesAdded += count($replacementNodes);
$this->replaceNodeWithNodes($tag->domNode, $replacementNodes);
}
$this->cleanup();
return $nodesAdded;
}
/**
* Locate include tags within the given document, isolating them to their
* own nodes in the DOM for future targeted manipulation.
* @return PageIncludeTag[]
*/
protected function locateAndIsolateIncludeTags(): array
{
$includeHosts = $this->doc->queryXPath("//*[text()[contains(., '{{@')]]");
$includeTags = [];
/** @var DOMNode $node */
foreach ($includeHosts as $node) {
/** @var DOMNode $childNode */
foreach ($node->childNodes as $childNode) {
if ($childNode->nodeName === '#text') {
array_push($includeTags, ...$this->splitTextNodesAtTags($childNode));
}
}
}
return $includeTags;
}
/**
* Takes a text DOMNode and splits its text content at include tags
* into multiple text nodes within the original parent.
* Returns found PageIncludeTag references.
* @return PageIncludeTag[]
*/
protected function splitTextNodesAtTags(DOMNode $textNode): array
{
$includeTags = [];
$text = $textNode->textContent;
preg_match_all(static::$includeTagRegex, $text, $matches, PREG_OFFSET_CAPTURE);
$currentOffset = 0;
foreach ($matches[0] as $index => $fullTagMatch) {
$tagOuterContent = $fullTagMatch[0];
$tagInnerContent = $matches[1][$index][0];
$tagStartOffset = $fullTagMatch[1];
if ($currentOffset < $tagStartOffset) {
$previousText = substr($text, $currentOffset, $tagStartOffset - $currentOffset);
$textNode->parentNode->insertBefore($this->doc->createTextNode($previousText), $textNode);
}
$node = $textNode->parentNode->insertBefore($this->doc->createTextNode($tagOuterContent), $textNode);
$includeTags[] = new PageIncludeTag($tagInnerContent, $node);
$currentOffset = $tagStartOffset + strlen($tagOuterContent);
}
if ($currentOffset > 0) {
$textNode->textContent = substr($text, $currentOffset);
}
return $includeTags;
}
/**
* Replace the given node with all those in $replacements
* @param DOMNode[] $replacements
*/
protected function replaceNodeWithNodes(DOMNode $toReplace, array $replacements): void
{
/** @var DOMDocument $targetDoc */
$targetDoc = $toReplace->ownerDocument;
foreach ($replacements as $replacement) {
if ($replacement->ownerDocument !== $targetDoc) {
$replacement = $targetDoc->importNode($replacement, true);
}
$toReplace->parentNode->insertBefore($replacement, $toReplace);
}
$toReplace->parentNode->removeChild($toReplace);
}
/**
* Move a tag node to become a sibling of the given parent.
* Will attempt to guess a position based upon the tag content within the parent.
*/
protected function moveTagNodeToBesideParent(PageIncludeTag $tag, DOMNode $parent): void
{
$parentText = $parent->textContent;
$tagPos = strpos($parentText, $tag->tagContent);
$before = $tagPos < (strlen($parentText) / 2);
$this->toCleanup[] = $tag->domNode->parentNode;
if ($before) {
$parent->parentNode->insertBefore($tag->domNode, $parent);
} else {
$parent->parentNode->insertBefore($tag->domNode, $parent->nextSibling);
}
}
/**
* Splits the given $parentNode at the location of the $domNode within it.
* Attempts to replicate the original $parentNode, moving some of their parent
* children in where needed, before adding the $domNode between.
*/
protected function splitNodeAtChildNode(DOMElement $parentNode, DOMNode $domNode): void
{
$children = [...$parentNode->childNodes];
$splitPos = array_search($domNode, $children, true);
if ($splitPos === false) {
$splitPos = count($children) - 1;
}
$parentClone = $parentNode->cloneNode();
if (!($parentClone instanceof DOMElement)) {
return;
}
$parentNode->parentNode->insertBefore($parentClone, $parentNode);
$parentClone->removeAttribute('id');
for ($i = 0; $i < $splitPos; $i++) {
/** @var DOMNode $child */
$child = $children[$i];
$parentClone->appendChild($child);
}
$parentNode->parentNode->insertBefore($domNode, $parentNode);
$this->toCleanup[] = $parentNode;
$this->toCleanup[] = $parentClone;
}
/**
* Get the parent paragraph of the given node, if existing.
*/
protected function getParentParagraph(DOMNode $parent): ?DOMElement
{
do {
if (strtolower($parent->nodeName) === 'p' && $parent instanceof DOMElement) {
return $parent;
}
$parent = $parent->parentNode;
} while ($parent !== null);
return null;
}
/**
* Clean up after a parse operation.
* Removes stranded elements we may have left during the parse.
*/
protected function cleanup(): void
{
foreach ($this->toCleanup as $element) {
$element->normalize();
while ($element->parentNode && !$element->hasChildNodes()) {
$parent = $element->parentNode;
$parent->removeChild($element);
$element = $parent;
}
}
}
}