D3Public/daux.io
8
0
Fork 0
Code Pull Requests Releases Activity

First checkin of search for static websites

Browse Source
This commit is contained in:
djohnanderson
2016-02-15 12:14:48 -08:00
parent f3457658a8
commit 61388e1c51
15 changed files with 938 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

68
libs/Format/HTML/Generator.php Normal file → Executable file
View File

@ -59,7 +59,59 @@ class Generator implements \Todaymade\Daux\Format\Base\Generator, LiveGenerator
);
$output->writeLn("Generating ...");
$this->generateRecursive($this->daux->tree, $destination, $params, $output, $width);
$text_search = ($input->getOption('text_search'));
$params['text_search'] = $text_search;
if ($text_search) {
$index_pages = [];
}
$this->generateRecursive($this->daux->tree, $destination, $params, $output, $width, $index_pages);
if ($text_search) {
$tipuesearch_directory = $this->daux->local_base . DIRECTORY_SEPARATOR . 'tipuesearch' . DIRECTORY_SEPARATOR;
file_put_contents($tipuesearch_directory . 'tipuesearch_content.json', json_encode(['pages' => $index_pages]));
GeneratorHelper::copyRecursive ($tipuesearch_directory, $destination . DIRECTORY_SEPARATOR . 'tipuesearch');
}
}
/**
* Remove HTML tags, including invisible text such as style and
* script code, and embedded objects. Add line breaks around
* block-level tags to prevent word joining after tag removal.
* Also collapse whitespace to single space and trim result.
* modified from: http://nadeausoftware.com/articles/2007/09/php_tip_how_strip_html_tags_web_page
*/
private function strip_html_tags($text)
{
$text = preg_replace(
array(
// Remove invisible content
'@<head[^>]*?>.*?</head>@siu',
'@<style[^>]*?>.*?</style>@siu',
'@<script[^>]*?.*?</script>@siu',
'@<object[^>]*?.*?</object>@siu',
'@<embed[^>]*?.*?</embed>@siu',
'@<applet[^>]*?.*?</applet>@siu',
'@<noframes[^>]*?.*?</noframes>@siu',
'@<noscript[^>]*?.*?</noscript>@siu',
'@<noembed[^>]*?.*?</noembed>@siu',
// Add line breaks before and after blocks
'@</?((address)|(blockquote)|(center)|(del))@iu',
'@</?((div)|(h[1-9])|(ins)|(isindex)|(p)|(pre))@iu',
'@</?((dir)|(dl)|(dt)|(dd)|(li)|(menu)|(ol)|(ul))@iu',
'@</?((table)|(th)|(td)|(caption))@iu',
'@</?((form)|(button)|(fieldset)|(legend)|(input))@iu',
'@</?((label)|(select)|(optgroup)|(option)|(textarea))@iu',
'@</?((frameset)|(frame)|(iframe))@iu',
),
array(
' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ',
"\n\$0", "\n\$0", "\n\$0", "\n\$0", "\n\$0", "\n\$0",
"\n\$0", "\n\$0",
),
$text );
return trim (preg_replace('/\s+/', ' ', strip_tags($text)));
}
/**
@ -73,7 +125,7 @@ class Generator implements \Todaymade\Daux\Format\Base\Generator, LiveGenerator
* @param string $base_url
* @throws \Exception
*/
private function generateRecursive(Directory $tree, $output_dir, $params, $output, $width, $base_url = '')
private function generateRecursive(Directory $tree, $output_dir, $params, $output, $width, &$index_pages, $base_url = '')
{
DauxHelper::rebaseConfiguration($params, $base_url);
@ -85,7 +137,7 @@ class Generator implements \Todaymade\Daux\Format\Base\Generator, LiveGenerator
if ($node instanceof Directory) {
$new_output_dir = $output_dir . DIRECTORY_SEPARATOR . $key;
mkdir($new_output_dir);
$this->generateRecursive($node, $new_output_dir, $params, $output, $width, '../' . $base_url);
$this->generateRecursive($node, $new_output_dir, $params, $output, $width, $index_pages, '../' . $base_url);
// Rebase configuration again as $params is a shared object
DauxHelper::rebaseConfiguration($params, $base_url);
@ -94,7 +146,7 @@ class Generator implements \Todaymade\Daux\Format\Base\Generator, LiveGenerator
"- " . $node->getUrl(),
$output,
$width,
function() use ($node, $output_dir, $key, $params) {
function() use ($node, $output_dir, $key, $params, &$index_pages) {
if ($node instanceof Raw) {
copy($node->getPath(), $output_dir . DIRECTORY_SEPARATOR . $key);
return;
@ -102,6 +154,14 @@ class Generator implements \Todaymade\Daux\Format\Base\Generator, LiveGenerator
$generated = $this->generateOne($node, $params);
file_put_contents($output_dir . DIRECTORY_SEPARATOR . $key, $generated->getContent());
if (isset($index_pages)) {
array_push($index_pages, [
'title' => $node->getTitle(),
'text' => utf8_encode($this->strip_html_tags($generated->getContent())),
'tags' => "",
'url' => $node->getUrl()
]);
}
}
);
}