Merge branch 'feature/bombe' into feature/typex

This commit is contained in:
s2224834 2019-03-12 18:21:34 +00:00
commit 1a707eab86
52 changed files with 4257 additions and 750 deletions

0
src/core/lib/BCD.mjs Executable file → Normal file
View file

0
src/core/lib/Base58.mjs Executable file → Normal file
View file

0
src/core/lib/Base64.mjs Executable file → Normal file
View file

0
src/core/lib/CanvasComponents.mjs Executable file → Normal file
View file

File diff suppressed because it is too large Load diff

263
src/core/lib/FileType.mjs Normal file
View file

@ -0,0 +1,263 @@
/**
* File type functions
*
* @author n1474335 [n1474335@gmail.com]
* @copyright Crown Copyright 2018
* @license Apache-2.0
*
*/
import {FILE_SIGNATURES} from "./FileSignatures";
import {sendStatusMessage} from "../Utils";
/**
* Checks whether a signature matches a buffer.
*
* @param {Object|Object[]} sig - A dictionary of offsets with values assigned to them.
* These values can be numbers for static checks, arrays of potential valid matches,
* or bespoke functions to check the validity of the buffer value at that offset.
* @param {Uint8Array} buf
* @param {number} [offset=0] Where in the buffer to start searching from
* @returns {boolean}
*/
function signatureMatches(sig, buf, offset=0) {
// Using a length check seems to be more performant than `sig instanceof Array`
if (sig.length) {
// sig is an Array - return true if any of them match
// The following `reduce` method is nice, but performance matters here, so we
// opt for a faster, if less elegant, for loop.
// return sig.reduce((acc, s) => acc || bytesMatch(s, buf, offset), false);
for (let i = 0; i < sig.length; i++) {
if (bytesMatch(sig[i], buf, offset)) return true;
}
return false;
} else {
return bytesMatch(sig, buf, offset);
}
}
/**
* Checks whether a set of bytes match the given buffer.
*
* @param {Object} sig - A dictionary of offsets with values assigned to them.
* These values can be numbers for static checks, arrays of potential valid matches,
* or bespoke functions to check the validity of the buffer value at that offset.
* @param {Uint8Array} buf
* @param {number} [offset=0] Where in the buffer to start searching from
* @returns {boolean}
*/
function bytesMatch(sig, buf, offset=0) {
for (const sigoffset in sig) {
const pos = parseInt(sigoffset, 10) + offset;
switch (typeof sig[sigoffset]) {
case "number": // Static check
if (buf[pos] !== sig[sigoffset])
return false;
break;
case "object": // Array of options
if (sig[sigoffset].indexOf(buf[pos]) < 0)
return false;
break;
case "function": // More complex calculation
if (!sig[sigoffset](buf[pos]))
return false;
break;
default:
throw new Error(`Unrecognised signature type at offset ${sigoffset}`);
}
}
return true;
}
/**
* Given a buffer, detects magic byte sequences at specific positions and returns the
* extension and mime type.
*
* @param {Uint8Array} buf
* @param {string[]} [categories=All] - Which categories of file to look for
* @returns {Object[]} types
* @returns {string} type.name - Name of file type
* @returns {string} type.ext - File extension
* @returns {string} type.mime - Mime type
* @returns {string} [type.desc] - Description
*/
export function detectFileType(buf, categories=Object.keys(FILE_SIGNATURES)) {
if (!(buf && buf.length > 1)) {
return [];
}
const matchingFiles = [];
const signatures = {};
for (const cat in FILE_SIGNATURES) {
if (categories.includes(cat)) {
signatures[cat] = FILE_SIGNATURES[cat];
}
}
for (const cat in signatures) {
const category = signatures[cat];
category.forEach(filetype => {
if (signatureMatches(filetype.signature, buf)) {
matchingFiles.push(filetype);
}
});
}
return matchingFiles;
}
/**
* Given a buffer, searches for magic byte sequences at all possible positions and returns
* the extensions and mime types.
*
* @param {Uint8Array} buf
* @param {string[]} [categories=All] - Which categories of file to look for
* @returns {Object[]} foundFiles
* @returns {number} foundFiles.offset - The position in the buffer at which this file was found
* @returns {Object} foundFiles.fileDetails
* @returns {string} foundFiles.fileDetails.name - Name of file type
* @returns {string} foundFiles.fileDetails.ext - File extension
* @returns {string} foundFiles.fileDetails.mime - Mime type
* @returns {string} [foundFiles.fileDetails.desc] - Description
*/
export function scanForFileTypes(buf, categories=Object.keys(FILE_SIGNATURES)) {
if (!(buf && buf.length > 1)) {
return [];
}
const foundFiles = [];
const signatures = {};
for (const cat in FILE_SIGNATURES) {
if (categories.includes(cat)) {
signatures[cat] = FILE_SIGNATURES[cat];
}
}
for (const cat in signatures) {
const category = signatures[cat];
for (let i = 0; i < category.length; i++) {
const filetype = category[i];
const sigs = filetype.signature.length ? filetype.signature : [filetype.signature];
sigs.forEach(sig => {
let pos = 0;
while ((pos = locatePotentialSig(buf, sig, pos)) >= 0) {
if (bytesMatch(sig, buf, pos)) {
sendStatusMessage(`Found potential signature for ${filetype.name} at pos ${pos}`);
foundFiles.push({
offset: pos,
fileDetails: filetype
});
}
pos++;
}
});
}
}
// Return found files in order of increasing offset
return foundFiles.sort((a, b) => {
return a.offset - b.offset;
});
}
/**
* Fastcheck function to quickly scan the buffer for the first byte in a signature.
*
* @param {Uint8Array} buf - The buffer to search
* @param {Object} sig - A single signature object (Not an array of signatures)
* @param {number} offset - Where to start search from
* @returs {number} The position of the match or -1 if one cannot be found.
*/
function locatePotentialSig(buf, sig, offset) {
// Find values for first key and value in sig
const k = parseInt(Object.keys(sig)[0], 10);
const v = Object.values(sig)[0];
switch (typeof v) {
case "number":
return buf.indexOf(v, offset + k) - k;
case "object":
for (let i = offset + k; i < buf.length; i++) {
if (v.indexOf(buf[i]) >= 0) return i - k;
}
return -1;
case "function":
for (let i = offset + k; i < buf.length; i++) {
if (v(buf[i])) return i - k;
}
return -1;
default:
throw new Error("Unrecognised signature type");
}
}
/**
* Detects whether the given buffer is a file of the type specified.
*
* @param {string|RegExp} type
* @param {Uint8Array} buf
* @returns {string|false} The mime type or false if the type does not match
*/
export function isType(type, buf) {
const types = detectFileType(buf);
if (!(types && types.length)) return false;
if (typeof type === "string") {
return types.reduce((acc, t) => {
const mime = t.mime.startsWith(type) ? t.mime : false;
return acc || mime;
}, false);
} else if (type instanceof RegExp) {
return types.reduce((acc, t) => {
const mime = type.test(t.mime) ? t.mime : false;
return acc || mime;
}, false);
} else {
throw new Error("Invalid type input.");
}
}
/**
* Detects whether the given buffer contains an image file.
*
* @param {Uint8Array} buf
* @returns {string|false} The mime type or false if the type does not match
*/
export function isImage(buf) {
return isType("image", buf);
}
/**
* Attempts to extract a file from a data stream given its offset and extractor function.
*
* @param {Uint8Array} bytes
* @param {Object} fileDetail
* @param {string} fileDetail.mime
* @param {string} fileDetail.extension
* @param {Function} fileDetail.extractor
* @param {number} offset
* @returns {File}
*/
export function extractFile(bytes, fileDetail, offset) {
if (fileDetail.extractor) {
sendStatusMessage(`Attempting to extract ${fileDetail.name} at pos ${offset}...`);
const fileData = fileDetail.extractor(bytes, offset);
const ext = fileDetail.extension.split(",")[0];
return new File([fileData], `extracted_at_0x${offset.toString(16)}.${ext}`, {
type: fileDetail.mime
});
}
throw new Error(`No extraction algorithm available for "${fileDetail.mime}" files`);
}

View file

@ -2,6 +2,7 @@ import OperationConfig from "../config/OperationConfig.json";
import Utils from "../Utils";
import Recipe from "../Recipe";
import Dish from "../Dish";
import {detectFileType} from "./FileType";
import chiSquared from "chi-squared";
/**
@ -92,7 +93,14 @@ class Magic {
* @returns {string} [type.desc] - Description
*/
detectFileType() {
return Magic.magicFileType(this.inputBuffer);
const fileType = detectFileType(this.inputBuffer);
if (!fileType.length) return null;
return {
ext: fileType[0].extension,
mime: fileType[0].mime,
desc: fileType[0].description
};
}
/**
@ -785,452 +793,9 @@ class Magic {
}[code];
}
/**
* Given a buffer, detects magic byte sequences at specific positions and returns the
* extension and mime type.
*
* @param {Uint8Array} buf
* @returns {Object} type
* @returns {string} type.ext - File extension
* @returns {string} type.mime - Mime type
* @returns {string} [type.desc] - Description
*/
static magicFileType(buf) {
if (!(buf && buf.length > 1)) {
return null;
}
if (buf[0] === 0xFF && buf[1] === 0xD8 && buf[2] === 0xFF) {
return {
ext: "jpg",
mime: "image/jpeg"
};
}
if (buf[0] === 0x89 && buf[1] === 0x50 && buf[2] === 0x4E && buf[3] === 0x47) {
return {
ext: "png",
mime: "image/png"
};
}
if (buf[0] === 0x47 && buf[1] === 0x49 && buf[2] === 0x46) {
return {
ext: "gif",
mime: "image/gif"
};
}
if (buf[8] === 0x57 && buf[9] === 0x45 && buf[10] === 0x42 && buf[11] === 0x50) {
return {
ext: "webp",
mime: "image/webp"
};
}
// needs to be before `tif` check
if (((buf[0] === 0x49 && buf[1] === 0x49 && buf[2] === 0x2A && buf[3] === 0x0) || (buf[0] === 0x4D && buf[1] === 0x4D && buf[2] === 0x0 && buf[3] === 0x2A)) && buf[8] === 0x43 && buf[9] === 0x52) {
return {
ext: "cr2",
mime: "image/x-canon-cr2"
};
}
if ((buf[0] === 0x49 && buf[1] === 0x49 && buf[2] === 0x2A && buf[3] === 0x0) || (buf[0] === 0x4D && buf[1] === 0x4D && buf[2] === 0x0 && buf[3] === 0x2A)) {
return {
ext: "tif",
mime: "image/tiff"
};
}
if (buf[0] === 0x42 && buf[1] === 0x4D) {
return {
ext: "bmp",
mime: "image/bmp"
};
}
if (buf[0] === 0x49 && buf[1] === 0x49 && buf[2] === 0xBC) {
return {
ext: "jxr",
mime: "image/vnd.ms-photo"
};
}
if (buf[0] === 0x38 && buf[1] === 0x42 && buf[2] === 0x50 && buf[3] === 0x53) {
return {
ext: "psd",
mime: "image/vnd.adobe.photoshop"
};
}
// needs to be before `zip` check
if (buf[0] === 0x50 && buf[1] === 0x4B && buf[2] === 0x3 && buf[3] === 0x4 && buf[30] === 0x6D && buf[31] === 0x69 && buf[32] === 0x6D && buf[33] === 0x65 && buf[34] === 0x74 && buf[35] === 0x79 && buf[36] === 0x70 && buf[37] === 0x65 && buf[38] === 0x61 && buf[39] === 0x70 && buf[40] === 0x70 && buf[41] === 0x6C && buf[42] === 0x69 && buf[43] === 0x63 && buf[44] === 0x61 && buf[45] === 0x74 && buf[46] === 0x69 && buf[47] === 0x6F && buf[48] === 0x6E && buf[49] === 0x2F && buf[50] === 0x65 && buf[51] === 0x70 && buf[52] === 0x75 && buf[53] === 0x62 && buf[54] === 0x2B && buf[55] === 0x7A && buf[56] === 0x69 && buf[57] === 0x70) {
return {
ext: "epub",
mime: "application/epub+zip"
};
}
if (buf[0] === 0x50 && buf[1] === 0x4B && (buf[2] === 0x3 || buf[2] === 0x5 || buf[2] === 0x7) && (buf[3] === 0x4 || buf[3] === 0x6 || buf[3] === 0x8)) {
return {
ext: "zip",
mime: "application/zip"
};
}
if (buf[257] === 0x75 && buf[258] === 0x73 && buf[259] === 0x74 && buf[260] === 0x61 && buf[261] === 0x72) {
return {
ext: "tar",
mime: "application/x-tar"
};
}
if (buf[0] === 0x52 && buf[1] === 0x61 && buf[2] === 0x72 && buf[3] === 0x21 && buf[4] === 0x1A && buf[5] === 0x7 && (buf[6] === 0x0 || buf[6] === 0x1)) {
return {
ext: "rar",
mime: "application/x-rar-compressed"
};
}
if (buf[0] === 0x1F && buf[1] === 0x8B && buf[2] === 0x8) {
return {
ext: "gz",
mime: "application/gzip"
};
}
if (buf[0] === 0x42 && buf[1] === 0x5A && buf[2] === 0x68) {
return {
ext: "bz2",
mime: "application/x-bzip2"
};
}
if (buf[0] === 0x37 && buf[1] === 0x7A && buf[2] === 0xBC && buf[3] === 0xAF && buf[4] === 0x27 && buf[5] === 0x1C) {
return {
ext: "7z",
mime: "application/x-7z-compressed"
};
}
if (buf[0] === 0x78 && buf[1] === 0x01) {
return {
ext: "dmg, zlib",
mime: "application/x-apple-diskimage, application/x-deflate"
};
}
if ((buf[0] === 0x0 && buf[1] === 0x0 && buf[2] === 0x0 && (buf[3] === 0x18 || buf[3] === 0x20) && buf[4] === 0x66 && buf[5] === 0x74 && buf[6] === 0x79 && buf[7] === 0x70) || (buf[0] === 0x33 && buf[1] === 0x67 && buf[2] === 0x70 && buf[3] === 0x35) || (buf[0] === 0x0 && buf[1] === 0x0 && buf[2] === 0x0 && buf[3] === 0x1C && buf[4] === 0x66 && buf[5] === 0x74 && buf[6] === 0x79 && buf[7] === 0x70 && buf[8] === 0x6D && buf[9] === 0x70 && buf[10] === 0x34 && buf[11] === 0x32 && buf[16] === 0x6D && buf[17] === 0x70 && buf[18] === 0x34 && buf[19] === 0x31 && buf[20] === 0x6D && buf[21] === 0x70 && buf[22] === 0x34 && buf[23] === 0x32 && buf[24] === 0x69 && buf[25] === 0x73 && buf[26] === 0x6F && buf[27] === 0x6D)) {
return {
ext: "mp4",
mime: "video/mp4"
};
}
if ((buf[0] === 0x0 && buf[1] === 0x0 && buf[2] === 0x0 && buf[3] === 0x1C && buf[4] === 0x66 && buf[5] === 0x74 && buf[6] === 0x79 && buf[7] === 0x70 && buf[8] === 0x4D && buf[9] === 0x34 && buf[10] === 0x56)) {
return {
ext: "m4v",
mime: "video/x-m4v"
};
}
if (buf[0] === 0x4D && buf[1] === 0x54 && buf[2] === 0x68 && buf[3] === 0x64) {
return {
ext: "mid",
mime: "audio/midi"
};
}
// needs to be before the `webm` check
if (buf[31] === 0x6D && buf[32] === 0x61 && buf[33] === 0x74 && buf[34] === 0x72 && buf[35] === 0x6f && buf[36] === 0x73 && buf[37] === 0x6B && buf[38] === 0x61) {
return {
ext: "mkv",
mime: "video/x-matroska"
};
}
if (buf[0] === 0x1A && buf[1] === 0x45 && buf[2] === 0xDF && buf[3] === 0xA3) {
return {
ext: "webm",
mime: "video/webm"
};
}
if (buf[0] === 0x0 && buf[1] === 0x0 && buf[2] === 0x0 && buf[3] === 0x14 && buf[4] === 0x66 && buf[5] === 0x74 && buf[6] === 0x79 && buf[7] === 0x70) {
return {
ext: "mov",
mime: "video/quicktime"
};
}
if (buf[0] === 0x52 && buf[1] === 0x49 && buf[2] === 0x46 && buf[3] === 0x46 && buf[8] === 0x41 && buf[9] === 0x56 && buf[10] === 0x49) {
return {
ext: "avi",
mime: "video/x-msvideo"
};
}
if (buf[0] === 0x30 && buf[1] === 0x26 && buf[2] === 0xB2 && buf[3] === 0x75 && buf[4] === 0x8E && buf[5] === 0x66 && buf[6] === 0xCF && buf[7] === 0x11 && buf[8] === 0xA6 && buf[9] === 0xD9) {
return {
ext: "wmv",
mime: "video/x-ms-wmv"
};
}
if (buf[0] === 0x0 && buf[1] === 0x0 && buf[2] === 0x1 && buf[3].toString(16)[0] === "b") {
return {
ext: "mpg",
mime: "video/mpeg"
};
}
if ((buf[0] === 0x49 && buf[1] === 0x44 && buf[2] === 0x33) || (buf[0] === 0xFF && buf[1] === 0xfb)) {
return {
ext: "mp3",
mime: "audio/mpeg"
};
}
if ((buf[4] === 0x66 && buf[5] === 0x74 && buf[6] === 0x79 && buf[7] === 0x70 && buf[8] === 0x4D && buf[9] === 0x34 && buf[10] === 0x41) || (buf[0] === 0x4D && buf[1] === 0x34 && buf[2] === 0x41 && buf[3] === 0x20)) {
return {
ext: "m4a",
mime: "audio/m4a"
};
}
if (buf[0] === 0x4F && buf[1] === 0x67 && buf[2] === 0x67 && buf[3] === 0x53) {
return {
ext: "ogg",
mime: "audio/ogg"
};
}
if (buf[0] === 0x66 && buf[1] === 0x4C && buf[2] === 0x61 && buf[3] === 0x43) {
return {
ext: "flac",
mime: "audio/x-flac"
};
}
if (buf[0] === 0x52 && buf[1] === 0x49 && buf[2] === 0x46 && buf[3] === 0x46 && buf[8] === 0x57 && buf[9] === 0x41 && buf[10] === 0x56 && buf[11] === 0x45) {
return {
ext: "wav",
mime: "audio/x-wav"
};
}
if (buf[0] === 0x23 && buf[1] === 0x21 && buf[2] === 0x41 && buf[3] === 0x4D && buf[4] === 0x52 && buf[5] === 0x0A) {
return {
ext: "amr",
mime: "audio/amr"
};
}
if (buf[0] === 0x25 && buf[1] === 0x50 && buf[2] === 0x44 && buf[3] === 0x46) {
return {
ext: "pdf",
mime: "application/pdf"
};
}
if (buf[0] === 0x4D && buf[1] === 0x5A) {
return {
ext: "exe",
mime: "application/x-msdownload"
};
}
if ((buf[0] === 0x43 || buf[0] === 0x46) && buf[1] === 0x57 && buf[2] === 0x53) {
return {
ext: "swf",
mime: "application/x-shockwave-flash"
};
}
if (buf[0] === 0x7B && buf[1] === 0x5C && buf[2] === 0x72 && buf[3] === 0x74 && buf[4] === 0x66) {
return {
ext: "rtf",
mime: "application/rtf"
};
}
if (buf[0] === 0x77 && buf[1] === 0x4F && buf[2] === 0x46 && buf[3] === 0x46 && buf[4] === 0x00 && buf[5] === 0x01 && buf[6] === 0x00 && buf[7] === 0x00) {
return {
ext: "woff",
mime: "application/font-woff"
};
}
if (buf[0] === 0x77 && buf[1] === 0x4F && buf[2] === 0x46 && buf[3] === 0x32 && buf[4] === 0x00 && buf[5] === 0x01 && buf[6] === 0x00 && buf[7] === 0x00) {
return {
ext: "woff2",
mime: "application/font-woff"
};
}
if (buf[34] === 0x4C && buf[35] === 0x50 && ((buf[8] === 0x02 && buf[9] === 0x00 && buf[10] === 0x01) || (buf[8] === 0x01 && buf[9] === 0x00 && buf[10] === 0x00) || (buf[8] === 0x02 && buf[9] === 0x00 && buf[10] === 0x02))) {
return {
ext: "eot",
mime: "application/octet-stream"
};
}
if (buf[0] === 0x00 && buf[1] === 0x01 && buf[2] === 0x00 && buf[3] === 0x00 && buf[4] === 0x00) {
return {
ext: "ttf",
mime: "application/font-sfnt"
};
}
if (buf[0] === 0x4F && buf[1] === 0x54 && buf[2] === 0x54 && buf[3] === 0x4F && buf[4] === 0x00) {
return {
ext: "otf",
mime: "application/font-sfnt"
};
}
if (buf[0] === 0x00 && buf[1] === 0x00 && buf[2] === 0x01 && buf[3] === 0x00) {
return {
ext: "ico",
mime: "image/x-icon"
};
}
if (buf[0] === 0x46 && buf[1] === 0x4C && buf[2] === 0x56 && buf[3] === 0x01) {
return {
ext: "flv",
mime: "video/x-flv"
};
}
if (buf[0] === 0x25 && buf[1] === 0x21) {
return {
ext: "ps",
mime: "application/postscript"
};
}
if (buf[0] === 0xFD && buf[1] === 0x37 && buf[2] === 0x7A && buf[3] === 0x58 && buf[4] === 0x5A && buf[5] === 0x00) {
return {
ext: "xz",
mime: "application/x-xz"
};
}
if (buf[0] === 0x53 && buf[1] === 0x51 && buf[2] === 0x4C && buf[3] === 0x69) {
return {
ext: "sqlite",
mime: "application/x-sqlite3"
};
}
/**
*
* Added by n1474335 [n1474335@gmail.com] from here on
*
*/
if ((buf[0] === 0x1F && buf[1] === 0x9D) || (buf[0] === 0x1F && buf[1] === 0xA0)) {
return {
ext: "z, tar.z",
mime: "application/x-gtar"
};
}
if (buf[0] === 0x7F && buf[1] === 0x45 && buf[2] === 0x4C && buf[3] === 0x46) {
return {
ext: "none, axf, bin, elf, o, prx, puff, so",
mime: "application/x-executable",
desc: "Executable and Linkable Format file. No standard file extension."
};
}
if (buf[0] === 0xCA && buf[1] === 0xFE && buf[2] === 0xBA && buf[3] === 0xBE) {
return {
ext: "class",
mime: "application/java-vm"
};
}
if (buf[0] === 0xEF && buf[1] === 0xBB && buf[2] === 0xBF) {
return {
ext: "txt",
mime: "text/plain",
desc: "UTF-8 encoded Unicode byte order mark detected, commonly but not exclusively seen in text files."
};
}
// Must be before Little-endian UTF-16 BOM
if (buf[0] === 0xFF && buf[1] === 0xFE && buf[2] === 0x00 && buf[3] === 0x00) {
return {
ext: "UTF32LE",
mime: "charset/utf32le",
desc: "Little-endian UTF-32 encoded Unicode byte order mark detected."
};
}
if (buf[0] === 0xFF && buf[1] === 0xFE) {
return {
ext: "UTF16LE",
mime: "charset/utf16le",
desc: "Little-endian UTF-16 encoded Unicode byte order mark detected."
};
}
if ((buf[0x8001] === 0x43 && buf[0x8002] === 0x44 && buf[0x8003] === 0x30 && buf[0x8004] === 0x30 && buf[0x8005] === 0x31) ||
(buf[0x8801] === 0x43 && buf[0x8802] === 0x44 && buf[0x8803] === 0x30 && buf[0x8804] === 0x30 && buf[0x8805] === 0x31) ||
(buf[0x9001] === 0x43 && buf[0x9002] === 0x44 && buf[0x9003] === 0x30 && buf[0x9004] === 0x30 && buf[0x9005] === 0x31)) {
return {
ext: "iso",
mime: "application/octet-stream",
desc: "ISO 9660 CD/DVD image file"
};
}
if (buf[0] === 0xD0 && buf[1] === 0xCF && buf[2] === 0x11 && buf[3] === 0xE0 && buf[4] === 0xA1 && buf[5] === 0xB1 && buf[6] === 0x1A && buf[7] === 0xE1) {
return {
ext: "doc, xls, ppt",
mime: "application/msword, application/vnd.ms-excel, application/vnd.ms-powerpoint",
desc: "Microsoft Office documents"
};
}
if (buf[0] === 0x64 && buf[1] === 0x65 && buf[2] === 0x78 && buf[3] === 0x0A && buf[4] === 0x30 && buf[5] === 0x33 && buf[6] === 0x35 && buf[7] === 0x00) {
return {
ext: "dex",
mime: "application/octet-stream",
desc: "Dalvik Executable (Android)"
};
}
if (buf[0] === 0x4B && buf[1] === 0x44 && buf[2] === 0x4D) {
return {
ext: "vmdk",
mime: "application/vmdk, application/x-virtualbox-vmdk"
};
}
if (buf[0] === 0x43 && buf[1] === 0x72 && buf[2] === 0x32 && buf[3] === 0x34) {
return {
ext: "crx",
mime: "application/crx",
desc: "Google Chrome extension or packaged app"
};
}
if (buf[0] === 0x78 && (buf[1] === 0x01 || buf[1] === 0x9C || buf[1] === 0xDA || buf[1] === 0x5e)) {
return {
ext: "zlib",
mime: "application/x-deflate"
};
}
return null;
}
}
/**
* Byte frequencies of various languages generated from Wikipedia dumps taken in late 2017 and early 2018.
* The Chi-Squared test cannot accept expected values of 0, so 0.0001 has been used to account for bytes

263
src/core/lib/Stream.mjs Normal file
View file

@ -0,0 +1,263 @@
/**
* Stream class for parsing binary protocols.
*
* @author n1474335 [n1474335@gmail.com]
* @author tlwr [toby@toby.codes]
* @copyright Crown Copyright 2018
* @license Apache-2.0
*
*/
/**
* A Stream can be used to traverse a binary blob, interpreting sections of it
* as various data types.
*/
export default class Stream {
/**
* Stream constructor.
*
* @param {Uint8Array} input
*/
constructor(input) {
this.bytes = input;
this.length = this.bytes.length;
this.position = 0;
this.bitPos = 0;
}
/**
* Get a number of bytes from the current position.
*
* @param {number} numBytes
* @returns {Uint8Array}
*/
getBytes(numBytes) {
if (this.position > this.length) return undefined;
const newPosition = this.position + numBytes;
const bytes = this.bytes.slice(this.position, newPosition);
this.position = newPosition;
this.bitPos = 0;
return bytes;
}
/**
* Interpret the following bytes as a string, stopping at the next null byte or
* the supplied limit.
*
* @param {number} numBytes
* @returns {string}
*/
readString(numBytes) {
if (this.position > this.length) return undefined;
let result = "";
for (let i = this.position; i < this.position + numBytes; i++) {
const currentByte = this.bytes[i];
if (currentByte === 0) break;
result += String.fromCharCode(currentByte);
}
this.position += numBytes;
this.bitPos = 0;
return result;
}
/**
* Interpret the following bytes as an integer in big or little endian.
*
* @param {number} numBytes
* @param {string} [endianness="be"]
* @returns {number}
*/
readInt(numBytes, endianness="be") {
if (this.position > this.length) return undefined;
let val = 0;
if (endianness === "be") {
for (let i = this.position; i < this.position + numBytes; i++) {
val = val << 8;
val |= this.bytes[i];
}
} else {
for (let i = this.position + numBytes - 1; i >= this.position; i--) {
val = val << 8;
val |= this.bytes[i];
}
}
this.position += numBytes;
this.bitPos = 0;
return val;
}
/**
* Reads a number of bits from the buffer.
*
* @TODO Add endianness
*
* @param {number} numBits
* @returns {number}
*/
readBits(numBits) {
if (this.position > this.length) return undefined;
let bitBuf = 0,
bitBufLen = 0;
// Add remaining bits from current byte
bitBuf = (this.bytes[this.position++] & bitMask(this.bitPos)) >>> this.bitPos;
bitBufLen = 8 - this.bitPos;
this.bitPos = 0;
// Not enough bits yet
while (bitBufLen < numBits) {
bitBuf |= this.bytes[this.position++] << bitBufLen;
bitBufLen += 8;
}
// Reverse back to numBits
if (bitBufLen > numBits) {
const excess = bitBufLen - numBits;
bitBuf &= (1 << numBits) - 1;
bitBufLen -= excess;
this.position--;
this.bitPos = 8 - excess;
}
return bitBuf;
/**
* Calculates the bit mask based on the current bit position.
*
* @param {number} bitPos
* @returns {number} The bit mask
*/
function bitMask(bitPos) {
return 256 - (1 << bitPos);
}
}
/**
* Consume the stream until we reach the specified byte or sequence of bytes.
*
* @param {number|List<number>} val
*/
continueUntil(val) {
if (this.position > this.length) return;
this.bitPos = 0;
if (typeof val === "number") {
while (++this.position < this.length && this.bytes[this.position] !== val) {
continue;
}
return;
}
// val is an array
let found = false;
while (!found && this.position < this.length) {
while (++this.position < this.length && this.bytes[this.position] !== val[0]) {
continue;
}
found = true;
for (let i = 1; i < val.length; i++) {
if (this.position + i > this.length || this.bytes[this.position + i] !== val[i])
found = false;
}
}
}
/**
* Consume the next byte if it matches the supplied value.
*
* @param {number} val
*/
consumeIf(val) {
if (this.bytes[this.position] === val) {
this.position++;
this.bitPos = 0;
}
}
/**
* Move forwards through the stream by the specified number of bytes.
*
* @param {number} numBytes
*/
moveForwardsBy(numBytes) {
const pos = this.position + numBytes;
if (pos < 0 || pos > this.length)
throw new Error("Cannot move to position " + pos + " in stream. Out of bounds.");
this.position = pos;
this.bitPos = 0;
}
/**
* Move backwards through the stream by the specified number of bytes.
*
* @param {number} numBytes
*/
moveBackwardsBy(numBytes) {
const pos = this.position - numBytes;
if (pos < 0 || pos > this.length)
throw new Error("Cannot move to position " + pos + " in stream. Out of bounds.");
this.position = pos;
this.bitPos = 0;
}
/**
* Move backwards through the strem by the specified number of bits.
*
* @param {number} numBits
*/
moveBackwardsByBits(numBits) {
if (numBits <= this.bitPos) {
this.bitPos -= numBits;
} else {
if (this.bitPos > 0) {
numBits -= this.bitPos;
this.bitPos = 0;
}
while (numBits > 0) {
this.moveBackwardsBy(1);
this.bitPos = 8;
this.moveBackwardsByBits(numBits);
numBits -= 8;
}
}
}
/**
* Move to a specified position in the stream.
*
* @param {number} pos
*/
moveTo(pos) {
if (pos < 0 || pos > this.length)
throw new Error("Cannot move to position " + pos + " in stream. Out of bounds.");
this.position = pos;
this.bitPos = 0;
}
/**
* Returns true if there are more bytes left in the stream.
*
* @returns {boolean}
*/
hasMore() {
return this.position < this.length;
}
/**
* Returns a slice of the stream up to the current position.
*
* @returns {Uint8Array}
*/
carve() {
if (this.bitPos > 0) this.position++;
return this.bytes.slice(0, this.position);
}
}