david
28b02db2ea
git-svn-id: https://192.168.0.254/svn/Proyectos.Incam_SGD/tags/3.7.0.2_original@1 eb19766c-00d9-a042-a3a0-45cb8ec72764
90 lines
2.8 KiB
Plaintext
90 lines
2.8 KiB
Plaintext
SEARCH2 - HOWTO WRITE AN EXTRACTOR
|
|
==================================
|
|
|
|
Note: The most up-to-date version of this can be found on the wiki at http://wiki.knowledgetree.com/Search2
|
|
|
|
All extractors are located in the search2/indexing/extractors folder.
|
|
|
|
Naming Convention
|
|
-----------------
|
|
|
|
The extractor must be a class descendant from DocumentExtractor and must be suffixed with the text 'Extractor'. The filename for the class
|
|
should have the same name as the class, but with the extension '.inc.php'.
|
|
|
|
Example
|
|
-------
|
|
|
|
The simplest extractor is the following:
|
|
|
|
class SomeExtractor extends DocumentExtractor
|
|
{
|
|
public function getDisplayName()
|
|
{
|
|
return _kt('Some Extractor');
|
|
}
|
|
|
|
public function getSupportedMimeTypes()
|
|
{
|
|
return array('text/plain','text/csv');
|
|
}
|
|
|
|
public function extractTextContent()
|
|
{
|
|
$content = file_get_contents($this->sourcefile);
|
|
if (false === $content)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
$result = file_put_contents($this->targetfile, $this->filter($content));
|
|
|
|
return false !== $result;
|
|
}
|
|
|
|
public function diagnose()
|
|
{
|
|
return null;
|
|
}
|
|
}
|
|
|
|
The filename is 'SomeExtractor.inc.php'.
|
|
|
|
Note that the DocumentExtractor class has some attributes that can be referenced:
|
|
1) sourcefile - the source filename from which the text must be extracted
|
|
2) targetfile - the target filename where the text that is extracted should be saved.
|
|
|
|
The class requires 4 methods:
|
|
1) getDisplayName() - provides the system with a friendly name for the extractor which will be displayed to users.
|
|
2) getSupportedMimeTypes() - tells the system what mime types the extractor supports.
|
|
3) extractTextContent() - the function that does the work. It must read from sourcefile and write to targetfile.
|
|
4) diagnose() - it must return null if there are no problems. Otherwise, it should return a string with an error/informational message.
|
|
|
|
Writing an extractor based on a command line application
|
|
--------------------------------------------------------
|
|
|
|
To illustrate how this can be done, the PDFExtractor is displayed:
|
|
|
|
class PDFExtractor extends ApplicationExtractor
|
|
{
|
|
public function __construct()
|
|
{
|
|
parent::__construct('extractors','pdftotext','pdftotext','PDF Text Extractor','-nopgbrk -enc UTF-8 {source} {target}');
|
|
}
|
|
|
|
public function getSupportedMimeTypes()
|
|
{
|
|
return array('application/pdf');
|
|
}
|
|
}
|
|
|
|
Note that the constructor takes the parameters:
|
|
|
|
function __construct($section, $appname, $command, $displayname, $params)
|
|
|
|
The application path is resolved from $section/$appname in the config.ini. If it is not found in the config.ini, the $command is
|
|
used by default. If you rely on $command, it should be accessible via the PATH environment variable.
|
|
|
|
$displayname is the friendly name that will be displayed in the dashboard.
|
|
|
|
Note that $params should contain {source} and {target} placeholders. These will be replaced by the system.
|