mirror of
https://github.com/silverstripe/silverstripe-textextraction
synced 2024-06-26 06:29:33 +02:00
f341010d7a
- Added namespaces, use statements - Added missing docblocks etc - Uses SS4's new Cache system - Uses proper environment vars - Cannot instantiate 'FileTextCache' (interface) as a service. This can be configured through YML, so default to FileTextCache_Cache - Modded YML config to make it run. - Fixes to allow TIKA to actually get file contents. - Addresses issues raised by @robbieaverill - Rebased against github.com/silverstripe/silverstripe-textextraction:master - Replaced `SS_Log` with Monolog.
95 lines
2.7 KiB
PHP
95 lines
2.7 KiB
PHP
<?php
|
|
|
|
namespace SilverStripe\TextExtraction\Extractor;
|
|
|
|
use SilverStripe\TextExtraction\Extractor\FileTextExtractor;
|
|
|
|
/**
|
|
* Text extractor that uses php function strip_tags to get just the text. OK for indexing, not the best for readable text.
|
|
* @author mstephens
|
|
*
|
|
*/
|
|
class HTMLTextExtractor extends FileTextExtractor
|
|
{
|
|
|
|
/**
|
|
*
|
|
* @return boolean
|
|
*/
|
|
public function isAvailable()
|
|
{
|
|
return true;
|
|
}
|
|
|
|
/**
|
|
*
|
|
* @param string $extension
|
|
* @return array
|
|
*/
|
|
public function supportsExtension($extension)
|
|
{
|
|
return in_array(
|
|
strtolower($extension), array("html", "htm", "xhtml")
|
|
);
|
|
}
|
|
|
|
/**
|
|
*
|
|
* @param string $mime
|
|
* @return string
|
|
*/
|
|
public function supportsMime($mime)
|
|
{
|
|
return strtolower($mime) === 'text/html';
|
|
}
|
|
|
|
/**
|
|
* Lower priority because its not the most clever HTML extraction. If there is something better, use it
|
|
*
|
|
* @config
|
|
* @var integer
|
|
*/
|
|
private static $priority = 10;
|
|
|
|
/**
|
|
* Extracts content from regex, by using strip_tags()
|
|
* combined with regular expressions to remove non-content tags like <style> or <script>,
|
|
* as well as adding line breaks after block tags.
|
|
*
|
|
* @param string $path
|
|
* @return string
|
|
*/
|
|
public function getContent($path)
|
|
{
|
|
$content = file_get_contents($path);
|
|
// Yes, yes, regex'ing HTML is evil.
|
|
// Since we don't care about well-formedness or markup here, it does the job.
|
|
$content = 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(
|
|
' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', "$0", "$0", "$0", "$0", "$0", "$0", "$0", "$0",
|
|
), $content
|
|
);
|
|
return strip_tags($content);
|
|
}
|
|
|
|
}
|