2018-12-14 16:43:03 +00:00
/**
* @author n1474335 [n1474335@gmail.com]
* @copyright Crown Copyright 2018
* @license Apache-2.0
*/
import Operation from "../Operation" ;
2019-03-02 16:12:21 +00:00
import OperationError from "../errors/OperationError" ;
2018-12-14 16:43:03 +00:00
import Utils from "../Utils" ;
2019-01-01 15:12:01 +00:00
import { scanForFileTypes , extractFile } from "../lib/FileType" ;
2019-01-14 18:55:10 +00:00
import { FILE_SIGNATURES } from "../lib/FileSignatures" ;
2018-12-14 16:43:03 +00:00
/**
* Extract Files operation
*/
class ExtractFiles extends Operation {
/**
* ExtractFiles constructor
*/
constructor () {
super ();
this . name = "Extract Files" ;
this . module = "Default" ;
2019-03-27 23:07:43 +00:00
this . description = "Performs file carving to attempt to extract files from the input.<br><br>This operation is currently capable of carving out the following formats:<ul><li>JPG</li><li>EXE</li><li>ZIP</li><li>PDF</li><li>PNG</li><li>BMP</li><li>FLV</li><li>RTF</li><li>DOCX, PPTX, XLSX</li><li>EPUB</li><li>GZIP</li><li>ZLIB</li><li>ELF, BIN, AXF, O, PRX, SO</li></ul>" ;
2018-12-14 16:43:03 +00:00
this . infoURL = "https://forensicswiki.org/wiki/File_Carving" ;
this . inputType = "ArrayBuffer" ;
this . outputType = "List<File>" ;
this . presentType = "html" ;
2019-01-14 18:55:10 +00:00
this . args = Object . keys ( FILE_SIGNATURES ). map ( cat => {
return {
name : cat ,
type : "boolean" ,
value : cat === "Miscellaneous" ? false : true
};
2019-03-02 16:12:21 +00:00
}). concat ([
{
name : "Ignore failed extractions" ,
type : "boolean" ,
value : "true"
}
]);
2018-12-14 16:43:03 +00:00
}
/**
* @param {ArrayBuffer} input
* @param {Object[]} args
* @returns {List<File>}
*/
run ( input , args ) {
2019-01-14 18:55:10 +00:00
const bytes = new Uint8Array ( input ),
2019-03-02 16:12:21 +00:00
categories = [],
ignoreFailedExtractions = args . pop ( 1 );
2019-01-14 18:55:10 +00:00
args . forEach (( cat , i ) => {
if ( cat ) categories . push ( Object . keys ( FILE_SIGNATURES )[ i ]);
});
2018-12-14 16:43:03 +00:00
// Scan for embedded files
2019-01-14 18:55:10 +00:00
const detectedFiles = scanForFileTypes ( bytes , categories );
2018-12-14 16:43:03 +00:00
// Extract each file that we support
const files = [];
2019-03-09 06:25:27 +00:00
const errors = [];
2018-12-18 17:44:42 +00:00
detectedFiles . forEach ( detectedFile => {
2018-12-14 16:43:03 +00:00
try {
2018-12-18 17:44:42 +00:00
files . push ( extractFile ( bytes , detectedFile . fileDetails , detectedFile . offset ));
2019-01-11 17:44:13 +00:00
} catch ( err ) {
2019-03-02 16:12:21 +00:00
if ( ! ignoreFailedExtractions && err . message . indexOf ( "No extraction algorithm available" ) < 0 ) {
2019-03-09 06:25:27 +00:00
errors . push (
2019-03-02 16:12:21 +00:00
`Error while attempting to extract ${ detectedFile . fileDetails . name } ` +
`at offset ${ detectedFile . offset } :\n` +
` ${ err . message } `
);
}
2019-01-11 17:44:13 +00:00
}
2018-12-14 16:43:03 +00:00
});
2019-03-09 06:25:27 +00:00
if ( errors . length ) {
throw new OperationError ( errors . join ( "\n\n" ));
}
2018-12-14 16:43:03 +00:00
return files ;
}
2019-03-09 06:25:27 +00:00
2018-12-14 16:43:03 +00:00
/**
* Displays the files in HTML for web apps.
*
* @param {File[]} files
* @returns {html}
*/
async present ( files ) {
return await Utils . displayFilesAsHTML ( files );
}
}
export default ExtractFiles ;