2018-12-14 17:43:03 +01:00
/ * *
* @ author n1474335 [ n1474335 @ gmail . com ]
* @ copyright Crown Copyright 2018
* @ license Apache - 2.0
* /
2019-07-09 13:23:59 +02:00
import Operation from "../Operation.mjs" ;
import OperationError from "../errors/OperationError.mjs" ;
import Utils from "../Utils.mjs" ;
import { scanForFileTypes , extractFile } from "../lib/FileType.mjs" ;
import { FILE _SIGNATURES } from "../lib/FileSignatures.mjs" ;
2018-12-14 17:43:03 +01:00
/ * *
* Extract Files operation
* /
class ExtractFiles extends Operation {
/ * *
* ExtractFiles constructor
* /
constructor ( ) {
super ( ) ;
2021-02-17 16:01:42 +01:00
// Get the first extension for each signature that can be extracted
let supportedExts = Object . keys ( FILE _SIGNATURES ) . map ( cat => {
return FILE _SIGNATURES [ cat ]
. filter ( sig => sig . extractor )
. map ( sig => sig . extension . toUpperCase ( ) ) ;
} ) ;
// Flatten categories and remove duplicates
supportedExts = [ ] . concat ( ... supportedExts ) . unique ( ) ;
2018-12-14 17:43:03 +01:00
this . name = "Extract Files" ;
this . module = "Default" ;
2021-02-17 16:01:42 +01:00
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 >
$ { supportedExts . join ( "</li><li>" ) }
< / l i >
< / u l > ` ;
2020-11-29 15:19:42 +01:00
this . infoURL = "https://forensicswiki.xyz/wiki/index.php?title=File_Carving" ;
2018-12-14 17:43:03 +01:00
this . inputType = "ArrayBuffer" ;
this . outputType = "List<File>" ;
this . presentType = "html" ;
2019-01-14 19:55:10 +01:00
this . args = Object . keys ( FILE _SIGNATURES ) . map ( cat => {
return {
name : cat ,
type : "boolean" ,
value : cat === "Miscellaneous" ? false : true
} ;
2019-03-02 17:12:21 +01:00
} ) . concat ( [
{
name : "Ignore failed extractions" ,
type : "boolean" ,
2020-04-16 09:59:43 +02:00
value : true
2019-03-02 17:12:21 +01:00
}
] ) ;
2018-12-14 17:43:03 +01:00
}
/ * *
* @ param { ArrayBuffer } input
* @ param { Object [ ] } args
* @ returns { List < File > }
* /
run ( input , args ) {
2019-01-14 19:55:10 +01:00
const bytes = new Uint8Array ( input ) ,
2019-03-02 17:12:21 +01:00
categories = [ ] ,
ignoreFailedExtractions = args . pop ( 1 ) ;
2019-01-14 19:55:10 +01:00
args . forEach ( ( cat , i ) => {
if ( cat ) categories . push ( Object . keys ( FILE _SIGNATURES ) [ i ] ) ;
} ) ;
2018-12-14 17:43:03 +01:00
// Scan for embedded files
2019-01-14 19:55:10 +01:00
const detectedFiles = scanForFileTypes ( bytes , categories ) ;
2018-12-14 17:43:03 +01:00
// Extract each file that we support
const files = [ ] ;
2019-03-09 07:25:27 +01:00
const errors = [ ] ;
2018-12-18 18:44:42 +01:00
detectedFiles . forEach ( detectedFile => {
2018-12-14 17:43:03 +01:00
try {
2018-12-18 18:44:42 +01:00
files . push ( extractFile ( bytes , detectedFile . fileDetails , detectedFile . offset ) ) ;
2019-01-11 18:44:13 +01:00
} catch ( err ) {
2019-03-02 17:12:21 +01:00
if ( ! ignoreFailedExtractions && err . message . indexOf ( "No extraction algorithm available" ) < 0 ) {
2019-03-09 07:25:27 +01:00
errors . push (
2019-03-02 17:12:21 +01:00
` Error while attempting to extract ${ detectedFile . fileDetails . name } ` +
` at offset ${ detectedFile . offset } : \n ` +
` ${ err . message } `
) ;
}
2019-01-11 18:44:13 +01:00
}
2018-12-14 17:43:03 +01:00
} ) ;
2019-03-09 07:25:27 +01:00
if ( errors . length ) {
throw new OperationError ( errors . join ( "\n\n" ) ) ;
}
2018-12-14 17:43:03 +01:00
return files ;
}
2019-03-09 07:25:27 +01:00
2018-12-14 17:43:03 +01:00
/ * *
* Displays the files in HTML for web apps .
*
* @ param { File [ ] } files
* @ returns { html }
* /
async present ( files ) {
return await Utils . displayFilesAsHTML ( files ) ;
}
}
export default ExtractFiles ;