tonyair/silverstripe-textextraction
1
0
Fork 0
mirror of https://github.com/silverstripe/silverstripe-textextraction synced 2024-10-22 09:06:00 +00:00
Code Issues Projects Releases Wiki Activity

API Using paths instead of File objects in extractors

Browse Source 
Makes coupling to File objects optional, by choosing
to use the FileTextExtractable extension.
This commit is contained in:
Ingo Schommer 2012-08-22 18:25:12 +02:00
parent 7de717b0bd
commit 977c4e49c9
4 changed files with 22 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
code/extensions/FileTextExtractable.php
View File

@ -27,10 +27,10 @@ class FileTextExtractable extends DataExtension {
if (!$forceParse && $this->owner->FileContentCache) return $this->owner->FileContentCache;
// Determine which extractor can process this file.
$extractor = FileTextExtractor::for_file($this->owner);
$extractor = FileTextExtractor::for_file($this->owner->FullPath);
if (!$extractor) return null;
$text = $extractor->getContent($this->owner);
$text = $extractor->getContent($this->owner->FullPath);
if (!$text) return null;
$this->owner->FileContentCache = $text;

21
code/extractors/FileTextExtractor.php
View File

@ -17,11 +17,11 @@ abstract class FileTextExtractor extends Object {
protected static $sorted_extractor_classes = null;
/**
* @param DataObject $file
* @param String $path
* @return FileTextExtractor
*/
static function for_file($file) {
$extension = strtolower($file->getExtension());
static function for_file($path) {
$extension = pathinfo($path, PATHINFO_EXTENSION);
if (!self::$sorted_extractor_classes) {
// Generate the sorted list of extractors on demand.
@ -41,6 +41,14 @@ abstract class FileTextExtractor extends Object {
}
}
/**
* Checks if the extractor is supported on the current environment,
* for example if the correct binaries or libraries are available.
*
* @return boolean
*/
abstract function isAvailable();
/**
* Return an array of content types that the extractor can handle.
* @return unknown_type
@ -48,11 +56,12 @@ abstract class FileTextExtractor extends Object {
abstract function supportedExtensions();
/**
* Given a file object, extract the contents as text
* @param $file
* Given a file path, extract the contents as text.
*
* @param $path
* @return unknown_type
*/
abstract function getContent($file);
abstract function getContent($path);
}
?>

5
code/extractors/HTMLTextExtractor.php
View File

@ -16,9 +16,8 @@ class HTMLTextExtractor extends FileTextExtractor {
*/
public static $priority = 10;
function getContent($file) {
$filename = Director::baseFolder() . "/" . $file->Filename;
$content = file_get_contents($filename);
function getContent($path) {
$content = file_get_contents($path);
return strip_tags($content);
}
}

7
code/extractors/PDFTextExtractor.php
View File

@ -24,10 +24,9 @@ class PDFTextExtractor extends FileTextExtractor {
return ( $path ? $path . '/' : '' ) . $prog;
}
function getContent($file) {
$filename = Director::baseFolder() . "/" . $file->Filename;
if (!$filename) return ""; // no file
$content = `{$this->bin('pdftotext')} "$filename" -`;
function getContent($path) {
if (!$path) return ""; // no file
$content = `{$this->bin('pdftotext')} "$path" -`;
return $content;
}
}