1
0
mirror of https://github.com/janeczku/calibre-web synced 2025-12-08 01:08:07 +00:00

Merge remote-tracking branch 'comic-reader/master'

This commit is contained in:
Ozzieisaacs
2019-05-31 08:43:51 +02:00
12 changed files with 2304 additions and 747 deletions

View File

@@ -0,0 +1,379 @@
/**
* archive.js
*
* Provides base functionality for unarchiving.
*
* Licensed under the MIT License
*
* Copyright(c) 2011 Google Inc.
*/
/* global bitjs */
var bitjs = bitjs || {};
bitjs.archive = bitjs.archive || {};
(function() {
// ===========================================================================
// Stolen from Closure because it's the best way to do Java-like inheritance.
bitjs.base = function(me, opt_methodName, var_args) {
var caller = arguments.callee.caller;
if (caller.superClass_) {
// This is a constructor. Call the superclass constructor.
return caller.superClass_.constructor.apply(
me, Array.prototype.slice.call(arguments, 1));
}
var args = Array.prototype.slice.call(arguments, 2);
var foundCaller = false;
for (var ctor = me.constructor; ctor; ctor = ctor.superClass_ && ctor.superClass_.constructor) {
if (ctor.prototype[opt_methodName] === caller) {
foundCaller = true;
} else if (foundCaller) {
return ctor.prototype[opt_methodName].apply(me, args);
}
}
// If we did not find the caller in the prototype chain,
// then one of two things happened:
// 1) The caller is an instance method.
// 2) This method was not called by the right caller.
if (me[opt_methodName] === caller) {
return me.constructor.prototype[opt_methodName].apply(me, args);
} else {
throw Error(
"goog.base called from a method of one name " +
"to a method of a different name");
}
};
bitjs.inherits = function(childCtor, parentCtor) {
/** @constructor */
function tempCtor() {};
tempCtor.prototype = parentCtor.prototype;
childCtor.superClass_ = parentCtor.prototype;
childCtor.prototype = new tempCtor();
childCtor.prototype.constructor = childCtor;
};
// ===========================================================================
/**
* An unarchive event.
*
* @param {string} type The event type.
* @constructor
*/
bitjs.archive.UnarchiveEvent = function(type) {
/**
* The event type.
*
* @type {string}
*/
this.type = type;
};
/**
* The UnarchiveEvent types.
*/
bitjs.archive.UnarchiveEvent.Type = {
START: "start",
PROGRESS: "progress",
EXTRACT: "extract",
FINISH: "finish",
INFO: "info",
ERROR: "error"
};
/**
* Useful for passing info up to the client (for debugging).
*
* @param {string} msg The info message.
*/
bitjs.archive.UnarchiveInfoEvent = function(msg) {
bitjs.base(this, bitjs.archive.UnarchiveEvent.Type.INFO);
/**
* The information message.
*
* @type {string}
*/
this.msg = msg;
};
bitjs.inherits(bitjs.archive.UnarchiveInfoEvent, bitjs.archive.UnarchiveEvent);
/**
* An unrecoverable error has occured.
*
* @param {string} msg The error message.
*/
bitjs.archive.UnarchiveErrorEvent = function(msg) {
bitjs.base(this, bitjs.archive.UnarchiveEvent.Type.ERROR);
/**
* The information message.
*
* @type {string}
*/
this.msg = msg;
};
bitjs.inherits(bitjs.archive.UnarchiveErrorEvent, bitjs.archive.UnarchiveEvent);
/**
* Start event.
*
* @param {string} msg The info message.
*/
bitjs.archive.UnarchiveStartEvent = function() {
bitjs.base(this, bitjs.archive.UnarchiveEvent.Type.START);
};
bitjs.inherits(bitjs.archive.UnarchiveStartEvent, bitjs.archive.UnarchiveEvent);
/**
* Finish event.
*
* @param {string} msg The info message.
*/
bitjs.archive.UnarchiveFinishEvent = function() {
bitjs.base(this, bitjs.archive.UnarchiveEvent.Type.FINISH);
};
bitjs.inherits(bitjs.archive.UnarchiveFinishEvent, bitjs.archive.UnarchiveEvent);
/**
* Progress event.
*/
bitjs.archive.UnarchiveProgressEvent = function(
currentFilename,
currentFileNumber,
currentBytesUnarchivedInFile,
currentBytesUnarchived,
totalUncompressedBytesInArchive,
totalFilesInArchive) {
bitjs.base(this, bitjs.archive.UnarchiveEvent.Type.PROGRESS);
this.currentFilename = currentFilename;
this.currentFileNumber = currentFileNumber;
this.currentBytesUnarchivedInFile = currentBytesUnarchivedInFile;
this.totalFilesInArchive = totalFilesInArchive;
this.currentBytesUnarchived = currentBytesUnarchived;
this.totalUncompressedBytesInArchive = totalUncompressedBytesInArchive;
};
bitjs.inherits(bitjs.archive.UnarchiveProgressEvent, bitjs.archive.UnarchiveEvent);
/**
* All extracted files returned by an Unarchiver will implement
* the following interface:
*
* interface UnarchivedFile {
* string filename
* TypedArray fileData
* }
*
*/
/**
* Extract event.
*/
bitjs.archive.UnarchiveExtractEvent = function(unarchivedFile) {
bitjs.base(this, bitjs.archive.UnarchiveEvent.Type.EXTRACT);
/**
* @type {UnarchivedFile}
*/
this.unarchivedFile = unarchivedFile;
};
bitjs.inherits(bitjs.archive.UnarchiveExtractEvent, bitjs.archive.UnarchiveEvent);
/**
* Base class for all Unarchivers.
*
* @param {ArrayBuffer} arrayBuffer The Array Buffer.
* @param {string} opt_pathToBitJS Optional string for where the BitJS files are located.
* @constructor
*/
bitjs.archive.Unarchiver = function(arrayBuffer, opt_pathToBitJS) {
/**
* The ArrayBuffer object.
* @type {ArrayBuffer}
* @protected
*/
this.ab = arrayBuffer;
/**
* The path to the BitJS files.
* @type {string}
* @private
*/
this.pathToBitJS_ = opt_pathToBitJS || "/";
/**
* A map from event type to an array of listeners.
* @type {Map.<string, Array>}
*/
this.listeners_ = {};
for (var type in bitjs.archive.UnarchiveEvent.Type) {
this.listeners_[bitjs.archive.UnarchiveEvent.Type[type]] = [];
}
};
/**
* Private web worker initialized during start().
* @type {Worker}
* @private
*/
bitjs.archive.Unarchiver.prototype.worker_ = null;
/**
* This method must be overridden by the subclass to return the script filename.
* @return {string} The script filename.
* @protected.
*/
bitjs.archive.Unarchiver.prototype.getScriptFileName = function() {
throw "Subclasses of AbstractUnarchiver must overload getScriptFileName()";
};
/**
* Adds an event listener for UnarchiveEvents.
*
* @param {string} Event type.
* @param {function} An event handler function.
*/
bitjs.archive.Unarchiver.prototype.addEventListener = function(type, listener) {
if (type in this.listeners_) {
if (this.listeners_[type].indexOf(listener) === -1) {
this.listeners_[type].push(listener);
}
}
};
/**
* Removes an event listener.
*
* @param {string} Event type.
* @param {EventListener|function} An event listener or handler function.
*/
bitjs.archive.Unarchiver.prototype.removeEventListener = function(type, listener) {
if (type in this.listeners_) {
var index = this.listeners_[type].indexOf(listener);
if (index !== -1) {
this.listeners_[type].splice(index, 1);
}
}
};
/**
* Receive an event and pass it to the listener functions.
*
* @param {bitjs.archive.UnarchiveEvent} e
* @private
*/
bitjs.archive.Unarchiver.prototype.handleWorkerEvent_ = function(e) {
if ((e instanceof bitjs.archive.UnarchiveEvent || e.type) &&
this.listeners_[e.type] instanceof Array) {
this.listeners_[e.type].forEach(function (listener) {
listener(e);
});
if (e.type === bitjs.archive.UnarchiveEvent.Type.FINISH) {
this.worker_.terminate();
}
}
};
/**
* Starts the unarchive in a separate Web Worker thread and returns immediately.
*/
bitjs.archive.Unarchiver.prototype.start = function() {
var me = this;
var scriptFileName = this.pathToBitJS_ + this.getScriptFileName();
if (scriptFileName) {
this.worker_ = new Worker(scriptFileName);
this.worker_.onerror = function(e) {
throw e;
};
this.worker_.onmessage = function(e) {
if (typeof e.data !== "string") {
// Assume that it is an UnarchiveEvent. Some browsers preserve the 'type'
// so that instanceof UnarchiveEvent returns true, but others do not.
me.handleWorkerEvent_(e.data);
}
};
this.worker_.postMessage({file: this.ab});
}
};
/**
* Terminates the Web Worker for this Unarchiver and returns immediately.
*/
bitjs.archive.Unarchiver.prototype.stop = function() {
if (this.worker_) {
this.worker_.terminate();
}
};
/**
* Unzipper
* @extends {bitjs.archive.Unarchiver}
* @constructor
*/
bitjs.archive.Unzipper = function(arrayBuffer, opt_pathToBitJS) {
bitjs.base(this, arrayBuffer, opt_pathToBitJS);
};
bitjs.inherits(bitjs.archive.Unzipper, bitjs.archive.Unarchiver);
bitjs.archive.Unzipper.prototype.getScriptFileName = function() {
return "unzip.js";
};
/**
* Unrarrer
* @extends {bitjs.archive.Unarchiver}
* @constructor
*/
bitjs.archive.Unrarrer = function(arrayBuffer, opt_pathToBitJS) {
bitjs.base(this, arrayBuffer, opt_pathToBitJS);
};
bitjs.inherits(bitjs.archive.Unrarrer, bitjs.archive.Unarchiver);
bitjs.archive.Unrarrer.prototype.getScriptFileName = function() {
return "unrar.js";
};
/**
* Untarrer
* @extends {bitjs.archive.Unarchiver}
* @constructor
*/
bitjs.archive.Untarrer = function(arrayBuffer, opt_pathToBitJS) {
bitjs.base(this, arrayBuffer, opt_pathToBitJS);
};
bitjs.inherits(bitjs.archive.Untarrer, bitjs.archive.Unarchiver);
bitjs.archive.Untarrer.prototype.getScriptFileName = function() {
return "untar.js";
};
/**
* Factory method that creates an unarchiver based on the byte signature found
* in the arrayBuffer.
* @param {ArrayBuffer} ab
* @param {string=} opt_pathToBitJS Path to the unarchiver script files.
* @return {bitjs.archive.Unarchiver}
*/
bitjs.archive.GetUnarchiver = function(ab, opt_pathToBitJS) {
var unarchiver = null;
var pathToBitJS = opt_pathToBitJS || '';
var h = new Uint8Array(ab, 0, 10);
if (h[0] == 0x52 && h[1] == 0x61 && h[2] == 0x72 && h[3] == 0x21) { // Rar!
unarchiver = new bitjs.archive.Unrarrer(ab, pathToBitJS);
} else if (h[0] == 80 && h[1] == 75) { // PK (Zip)
unarchiver = new bitjs.archive.Unzipper(ab, pathToBitJS);
} else { // Try with tar
console.log('geter');
unarchiver = new bitjs.archive.Untarrer(ab, pathToBitJS);
}
return unarchiver;
};
})();

View File

@@ -0,0 +1,858 @@
/**
* rarvm.js
*
* Licensed under the MIT License
*
* Copyright(c) 2017 Google Inc.
*/
/**
* CRC Implementation.
*/
var CRCTab = new Array(256).fill(0);
function InitCRC() {
for (var i = 0; i < 256; ++i) {
var c = i;
for (var j = 0; j < 8; ++j) {
// Read http://stackoverflow.com/questions/6798111/bitwise-operations-on-32-bit-unsigned-ints
// for the bitwise operator issue (JS interprets operands as 32-bit signed
// integers and we need to deal with unsigned ones here).
c = ((c & 1) ? ((c >>> 1) ^ 0xEDB88320) : (c >>> 1)) >>> 0;
}
CRCTab[i] = c;
}
}
/**
* @param {number} startCRC
* @param {Uint8Array} arr
* @return {number}
*/
function CRC(startCRC, arr) {
if (CRCTab[1] == 0) {
InitCRC();
}
/*
#if defined(LITTLE_ENDIAN) && defined(PRESENT_INT32) && defined(ALLOW_NOT_ALIGNED_INT)
while (Size>0 && ((long)Data & 7))
{
StartCRC=CRCTab[(byte)(StartCRC^Data[0])]^(StartCRC>>8);
Size--;
Data++;
}
while (Size>=8)
{
StartCRC^=*(uint32 *)Data;
StartCRC=CRCTab[(byte)StartCRC]^(StartCRC>>8);
StartCRC=CRCTab[(byte)StartCRC]^(StartCRC>>8);
StartCRC=CRCTab[(byte)StartCRC]^(StartCRC>>8);
StartCRC=CRCTab[(byte)StartCRC]^(StartCRC>>8);
StartCRC^=*(uint32 *)(Data+4);
StartCRC=CRCTab[(byte)StartCRC]^(StartCRC>>8);
StartCRC=CRCTab[(byte)StartCRC]^(StartCRC>>8);
StartCRC=CRCTab[(byte)StartCRC]^(StartCRC>>8);
StartCRC=CRCTab[(byte)StartCRC]^(StartCRC>>8);
Data+=8;
Size-=8;
}
#endif
*/
for (var i = 0; i < arr.length; ++i) {
var byte = ((startCRC ^ arr[i]) >>> 0) & 0xff;
startCRC = (CRCTab[byte] ^ (startCRC >>> 8)) >>> 0;
}
return startCRC;
}
// ============================================================================================== //
/**
* RarVM Implementation.
*/
var VM_MEMSIZE = 0x40000;
var VM_MEMMASK = (VM_MEMSIZE - 1);
var VM_GLOBALMEMADDR = 0x3C000;
var VM_GLOBALMEMSIZE = 0x2000;
var VM_FIXEDGLOBALSIZE = 64;
var MAXWINSIZE = 0x400000;
var MAXWINMASK = (MAXWINSIZE - 1);
/**
*/
var VM_Commands = {
VM_MOV: 0,
VM_CMP: 1,
VM_ADD: 2,
VM_SUB: 3,
VM_JZ: 4,
VM_JNZ: 5,
VM_INC: 6,
VM_DEC: 7,
VM_JMP: 8,
VM_XOR: 9,
VM_AND: 10,
VM_OR: 11,
VM_TEST: 12,
VM_JS: 13,
VM_JNS: 14,
VM_JB: 15,
VM_JBE: 16,
VM_JA: 17,
VM_JAE: 18,
VM_PUSH: 19,
VM_POP: 20,
VM_CALL: 21,
VM_RET: 22,
VM_NOT: 23,
VM_SHL: 24,
VM_SHR: 25,
VM_SAR: 26,
VM_NEG: 27,
VM_PUSHA: 28,
VM_POPA: 29,
VM_PUSHF: 30,
VM_POPF: 31,
VM_MOVZX: 32,
VM_MOVSX: 33,
VM_XCHG: 34,
VM_MUL: 35,
VM_DIV: 36,
VM_ADC: 37,
VM_SBB: 38,
VM_PRINT: 39,
/*
#ifdef VM_OPTIMIZE
VM_MOVB, VM_MOVD, VM_CMPB, VM_CMPD,
VM_ADDB, VM_ADDD, VM_SUBB, VM_SUBD, VM_INCB, VM_INCD, VM_DECB, VM_DECD,
VM_NEGB, VM_NEGD,
#endif
*/
// TODO: This enum value would be much larger if VM_OPTIMIZE.
VM_STANDARD: 40,
};
/**
*/
var VM_StandardFilters = {
VMSF_NONE: 0,
VMSF_E8: 1,
VMSF_E8E9: 2,
VMSF_ITANIUM: 3,
VMSF_RGB: 4,
VMSF_AUDIO: 5,
VMSF_DELTA: 6,
VMSF_UPCASE: 7,
};
/**
*/
var VM_Flags = {
VM_FC: 1,
VM_FZ: 2,
VM_FS: 0x80000000,
};
/**
*/
var VM_OpType = {
VM_OPREG: 0,
VM_OPINT: 1,
VM_OPREGMEM: 2,
VM_OPNONE: 3,
};
/**
* Finds the key that maps to a given value in an object. This function is useful in debugging
* variables that use the above enums.
* @param {Object} obj
* @param {number} val
* @return {string} The key/enum value as a string.
*/
function findKeyForValue(obj, val) {
for (var key in obj) {
if (obj[key] === val) {
return key;
}
}
return null;
}
function getDebugString(obj, val) {
var s = 'Unknown.';
if (obj === VM_Commands) {
s = 'VM_Commands.';
} else if (obj === VM_StandardFilters) {
s = 'VM_StandardFilters.';
} else if (obj === VM_Flags) {
s = 'VM_OpType.';
} else if (obj === VM_OpType) {
s = 'VM_OpType.';
}
return s + findKeyForValue(obj, val);
}
/**
* @struct
* @constructor
*/
var VM_PreparedOperand = function() {
/** @type {VM_OpType} */
this.Type;
/** @type {number} */
this.Data = 0;
/** @type {number} */
this.Base = 0;
// TODO: In C++ this is a uint*
/** @type {Array<number>} */
this.Addr = null;
};
/** @return {string} */
VM_PreparedOperand.prototype.toString = function() {
if (this.Type === null) {
return 'Error: Type was null in VM_PreparedOperand';
}
return '{ ' +
'Type: ' + getDebugString(VM_OpType, this.Type) +
', Data: ' + this.Data +
', Base: ' + this.Base +
' }';
};
/**
* @struct
* @constructor
*/
var VM_PreparedCommand = function() {
/** @type {VM_Commands} */
this.OpCode;
/** @type {boolean} */
this.ByteMode = false;
/** @type {VM_PreparedOperand} */
this.Op1 = new VM_PreparedOperand();
/** @type {VM_PreparedOperand} */
this.Op2 = new VM_PreparedOperand();
};
/** @return {string} */
VM_PreparedCommand.prototype.toString = function(indent) {
if (this.OpCode === null) {
return 'Error: OpCode was null in VM_PreparedCommand';
}
indent = indent || '';
return indent + '{\n' +
indent + ' OpCode: ' + getDebugString(VM_Commands, this.OpCode) + ',\n' +
indent + ' ByteMode: ' + this.ByteMode + ',\n' +
indent + ' Op1: ' + this.Op1.toString() + ',\n' +
indent + ' Op2: ' + this.Op2.toString() + ',\n' +
indent + '}';
};
/**
* @struct
* @constructor
*/
var VM_PreparedProgram = function() {
/** @type {Array<VM_PreparedCommand>} */
this.Cmd = [];
/** @type {Array<VM_PreparedCommand>} */
this.AltCmd = null;
/** @type {Uint8Array} */
this.GlobalData = new Uint8Array();
/** @type {Uint8Array} */
this.StaticData = new Uint8Array(); // static data contained in DB operators
/** @type {Uint32Array} */
this.InitR = new Uint32Array(7);
/**
* A pointer to bytes that have been filtered by a program.
* @type {Uint8Array}
*/
this.FilteredData = null;
};
/** @return {string} */
VM_PreparedProgram.prototype.toString = function() {
var s = '{\n Cmd: [\n';
for (var i = 0; i < this.Cmd.length; ++i) {
s += this.Cmd[i].toString(' ') + ',\n';
}
s += '],\n';
// TODO: Dump GlobalData, StaticData, InitR?
s += ' }\n';
return s;
};
/**
* @struct
* @constructor
*/
var UnpackFilter = function() {
/** @type {number} */
this.BlockStart = 0;
/** @type {number} */
this.BlockLength = 0;
/** @type {number} */
this.ExecCount = 0;
/** @type {boolean} */
this.NextWindow = false;
// position of parent filter in Filters array used as prototype for filter
// in PrgStack array. Not defined for filters in Filters array.
/** @type {number} */
this.ParentFilter = null;
/** @type {VM_PreparedProgram} */
this.Prg = new VM_PreparedProgram();
};
var VMCF_OP0 = 0;
var VMCF_OP1 = 1;
var VMCF_OP2 = 2;
var VMCF_OPMASK = 3;
var VMCF_BYTEMODE = 4;
var VMCF_JUMP = 8;
var VMCF_PROC = 16;
var VMCF_USEFLAGS = 32;
var VMCF_CHFLAGS = 64;
var VM_CmdFlags = [
/* VM_MOV */
VMCF_OP2 | VMCF_BYTEMODE,
/* VM_CMP */
VMCF_OP2 | VMCF_BYTEMODE | VMCF_CHFLAGS,
/* VM_ADD */
VMCF_OP2 | VMCF_BYTEMODE | VMCF_CHFLAGS,
/* VM_SUB */
VMCF_OP2 | VMCF_BYTEMODE | VMCF_CHFLAGS,
/* VM_JZ */
VMCF_OP1 | VMCF_JUMP | VMCF_USEFLAGS,
/* VM_JNZ */
VMCF_OP1 | VMCF_JUMP | VMCF_USEFLAGS,
/* VM_INC */
VMCF_OP1 | VMCF_BYTEMODE | VMCF_CHFLAGS,
/* VM_DEC */
VMCF_OP1 | VMCF_BYTEMODE | VMCF_CHFLAGS,
/* VM_JMP */
VMCF_OP1 | VMCF_JUMP,
/* VM_XOR */
VMCF_OP2 | VMCF_BYTEMODE | VMCF_CHFLAGS,
/* VM_AND */
VMCF_OP2 | VMCF_BYTEMODE | VMCF_CHFLAGS,
/* VM_OR */
VMCF_OP2 | VMCF_BYTEMODE | VMCF_CHFLAGS,
/* VM_TEST */
VMCF_OP2 | VMCF_BYTEMODE | VMCF_CHFLAGS,
/* VM_JS */
VMCF_OP1 | VMCF_JUMP | VMCF_USEFLAGS,
/* VM_JNS */
VMCF_OP1 | VMCF_JUMP | VMCF_USEFLAGS,
/* VM_JB */
VMCF_OP1 | VMCF_JUMP | VMCF_USEFLAGS,
/* VM_JBE */
VMCF_OP1 | VMCF_JUMP | VMCF_USEFLAGS,
/* VM_JA */
VMCF_OP1 | VMCF_JUMP | VMCF_USEFLAGS,
/* VM_JAE */
VMCF_OP1 | VMCF_JUMP | VMCF_USEFLAGS,
/* VM_PUSH */
VMCF_OP1,
/* VM_POP */
VMCF_OP1,
/* VM_CALL */
VMCF_OP1 | VMCF_PROC,
/* VM_RET */
VMCF_OP0 | VMCF_PROC,
/* VM_NOT */
VMCF_OP1 | VMCF_BYTEMODE,
/* VM_SHL */
VMCF_OP2 | VMCF_BYTEMODE | VMCF_CHFLAGS,
/* VM_SHR */
VMCF_OP2 | VMCF_BYTEMODE | VMCF_CHFLAGS,
/* VM_SAR */
VMCF_OP2 | VMCF_BYTEMODE | VMCF_CHFLAGS,
/* VM_NEG */
VMCF_OP1 | VMCF_BYTEMODE | VMCF_CHFLAGS,
/* VM_PUSHA */
VMCF_OP0,
/* VM_POPA */
VMCF_OP0,
/* VM_PUSHF */
VMCF_OP0 | VMCF_USEFLAGS,
/* VM_POPF */
VMCF_OP0 | VMCF_CHFLAGS,
/* VM_MOVZX */
VMCF_OP2,
/* VM_MOVSX */
VMCF_OP2,
/* VM_XCHG */
VMCF_OP2 | VMCF_BYTEMODE,
/* VM_MUL */
VMCF_OP2 | VMCF_BYTEMODE,
/* VM_DIV */
VMCF_OP2 | VMCF_BYTEMODE,
/* VM_ADC */
VMCF_OP2 | VMCF_BYTEMODE | VMCF_USEFLAGS | VMCF_CHFLAGS,
/* VM_SBB */
VMCF_OP2 | VMCF_BYTEMODE | VMCF_USEFLAGS | VMCF_CHFLAGS,
/* VM_PRINT */
VMCF_OP0,
];
/**
* @param {number} length
* @param {number} crc
* @param {VM_StandardFilters} type
* @struct
* @constructor
*/
var StandardFilterSignature = function(length, crc, type) {
/** @type {number} */
this.Length = length;
/** @type {number} */
this.CRC = crc;
/** @type {VM_StandardFilters} */
this.Type = type;
};
/**
* @type {Array<StandardFilterSignature>}
*/
var StdList = [
new StandardFilterSignature(53, 0xad576887, VM_StandardFilters.VMSF_E8),
new StandardFilterSignature(57, 0x3cd7e57e, VM_StandardFilters.VMSF_E8E9),
new StandardFilterSignature(120, 0x3769893f, VM_StandardFilters.VMSF_ITANIUM),
new StandardFilterSignature(29, 0x0e06077d, VM_StandardFilters.VMSF_DELTA),
new StandardFilterSignature(149, 0x1c2c5dc8, VM_StandardFilters.VMSF_RGB),
new StandardFilterSignature(216, 0xbc85e701, VM_StandardFilters.VMSF_AUDIO),
new StandardFilterSignature(40, 0x46b9c560, VM_StandardFilters.VMSF_UPCASE),
];
/**
* @constructor
*/
var RarVM = function() {
/** @private {Uint8Array} */
this.mem_ = null;
/** @private {Uint32Array<number>} */
this.R_ = new Uint32Array(8);
/** @private {number} */
this.flags_ = 0;
};
/**
* Initializes the memory of the VM.
*/
RarVM.prototype.init = function() {
if (!this.mem_) {
this.mem_ = new Uint8Array(VM_MEMSIZE);
}
};
/**
* @param {Uint8Array} code
* @return {VM_StandardFilters}
*/
RarVM.prototype.isStandardFilter = function(code) {
var codeCRC = (CRC(0xffffffff, code, code.length) ^ 0xffffffff) >>> 0;
for (var i = 0; i < StdList.length; ++i) {
if (StdList[i].CRC == codeCRC && StdList[i].Length == code.length)
return StdList[i].Type;
}
return VM_StandardFilters.VMSF_NONE;
};
/**
* @param {VM_PreparedOperand} op
* @param {boolean} byteMode
* @param {bitjs.io.BitStream} bstream A rtl bit stream.
*/
RarVM.prototype.decodeArg = function(op, byteMode, bstream) {
var data = bstream.peekBits(16);
if (data & 0x8000) {
op.Type = VM_OpType.VM_OPREG; // Operand is register (R[0]..R[7])
bstream.readBits(1); // 1 flag bit and...
op.Data = bstream.readBits(3); // ... 3 register number bits
op.Addr = [this.R_[op.Data]] // TODO &R[Op.Data] // Register address
} else {
if ((data & 0xc000) == 0) {
op.Type = VM_OpType.VM_OPINT; // Operand is integer
bstream.readBits(2); // 2 flag bits
if (byteMode) {
op.Data = bstream.readBits(8); // Byte integer.
} else {
op.Data = RarVM.readData(bstream); // 32 bit integer.
}
} else {
// Operand is data addressed by register data, base address or both.
op.Type = VM_OpType.VM_OPREGMEM;
if ((data & 0x2000) == 0) {
bstream.readBits(3); // 3 flag bits
// Base address is zero, just use the address from register.
op.Data = bstream.readBits(3); // (Data>>10)&7
op.Addr = [this.R_[op.Data]]; // TODO &R[op.Data]
op.Base = 0;
} else {
bstream.readBits(4); // 4 flag bits
if ((data & 0x1000) == 0) {
// Use both register and base address.
op.Data = bstream.readBits(3);
op.Addr = [this.R_[op.Data]]; // TODO &R[op.Data]
} else {
// Use base address only. Access memory by fixed address.
op.Data = 0;
}
op.Base = RarVM.readData(bstream); // Read base address.
}
}
}
};
/**
* @param {VM_PreparedProgram} prg
*/
RarVM.prototype.execute = function(prg) {
this.R_.set(prg.InitR);
var globalSize = Math.min(prg.GlobalData.length, VM_GLOBALMEMSIZE);
if (globalSize) {
this.mem_.set(prg.GlobalData.subarray(0, globalSize), VM_GLOBALMEMADDR);
}
var staticSize = Math.min(prg.StaticData.length, VM_GLOBALMEMSIZE - globalSize);
if (staticSize) {
this.mem_.set(prg.StaticData.subarray(0, staticSize), VM_GLOBALMEMADDR + globalSize);
}
this.R_[7] = VM_MEMSIZE;
this.flags_ = 0;
var preparedCodes = prg.AltCmd ? prg.AltCmd : prg.Cmd;
if (prg.Cmd.length > 0 && !this.executeCode(preparedCodes)) {
// Invalid VM program. Let's replace it with 'return' command.
preparedCode.OpCode = VM_Commands.VM_RET;
}
var dataView = new DataView(this.mem_.buffer, VM_GLOBALMEMADDR);
var newBlockPos = dataView.getUint32(0x20, true /* little endian */ ) & VM_MEMMASK;
var newBlockSize = dataView.getUint32(0x1c, true /* little endian */ ) & VM_MEMMASK;
if (newBlockPos + newBlockSize >= VM_MEMSIZE) {
newBlockPos = newBlockSize = 0;
}
prg.FilteredData = this.mem_.subarray(newBlockPos, newBlockPos + newBlockSize);
prg.GlobalData = new Uint8Array(0);
var dataSize = Math.min(dataView.getUint32(0x30),
(VM_GLOBALMEMSIZE - VM_FIXEDGLOBALSIZE));
if (dataSize != 0) {
var len = dataSize + VM_FIXEDGLOBALSIZE;
prg.GlobalData = new Uint8Array(len);
prg.GlobalData.set(mem.subarray(VM_GLOBALMEMADDR, VM_GLOBALMEMADDR + len));
}
};
/**
* @param {Array<VM_PreparedCommand>} preparedCodes
* @return {boolean}
*/
RarVM.prototype.executeCode = function(preparedCodes) {
var codeIndex = 0;
var cmd = preparedCodes[codeIndex];
// TODO: Why is this an infinite loop instead of just returning
// when a VM_RET is hit?
while (1) {
switch (cmd.OpCode) {
case VM_Commands.VM_RET:
if (this.R_[7] >= VM_MEMSIZE) {
return true;
}
//SET_IP(GET_VALUE(false,(uint *)&Mem[R[7] & VM_MEMMASK]));
this.R_[7] += 4;
continue;
case VM_Commands.VM_STANDARD:
this.executeStandardFilter(cmd.Op1.Data);
break;
default:
console.error('RarVM OpCode not supported: ' + getDebugString(VM_Commands, cmd.OpCode));
break;
} // switch (cmd.OpCode)
codeIndex++;
cmd = preparedCodes[codeIndex];
}
};
/**
* @param {number} filterType
*/
RarVM.prototype.executeStandardFilter = function(filterType) {
switch (filterType) {
case VM_StandardFilters.VMSF_DELTA:
var dataSize = this.R_[4];
var channels = this.R_[0];
var srcPos = 0;
var border = dataSize * 2;
//SET_VALUE(false,&Mem[VM_GLOBALMEMADDR+0x20],DataSize);
var dataView = new DataView(this.mem_.buffer, VM_GLOBALMEMADDR);
dataView.setUint32(0x20, dataSize, true /* little endian */ );
if (dataSize >= VM_GLOBALMEMADDR / 2) {
break;
}
// Bytes from same channels are grouped to continual data blocks,
// so we need to place them back to their interleaving positions.
for (var curChannel = 0; curChannel < channels; ++curChannel) {
var prevByte = 0;
for (var destPos = dataSize + curChannel; destPos < border; destPos += channels) {
prevByte = (prevByte - this.mem_[srcPos++]) & 0xff;
this.mem_[destPos] = prevByte;
}
}
break;
default:
console.error('RarVM Standard Filter not supported: ' + getDebugString(VM_StandardFilters, filterType));
break;
}
};
/**
* @param {Uint8Array} code
* @param {VM_PreparedProgram} prg
*/
RarVM.prototype.prepare = function(code, prg) {
var codeSize = code.length;
//InitBitInput();
//memcpy(InBuf,Code,Min(CodeSize,BitInput::MAX_SIZE));
var bstream = new bitjs.io.BitStream(code.buffer, true /* rtl */ );
// Calculate the single byte XOR checksum to check validity of VM code.
var xorSum = 0;
for (var i = 1; i < codeSize; ++i) {
xorSum ^= code[i];
}
bstream.readBits(8);
prg.Cmd = []; // TODO: Is this right? I don't see it being done in rarvm.cpp.
// VM code is valid if equal.
if (xorSum == code[0]) {
var filterType = this.isStandardFilter(code);
if (filterType != VM_StandardFilters.VMSF_NONE) {
// VM code is found among standard filters.
var curCmd = new VM_PreparedCommand();
prg.Cmd.push(curCmd);
curCmd.OpCode = VM_Commands.VM_STANDARD;
curCmd.Op1.Data = filterType;
// TODO: Addr=&CurCmd->Op1.Data
curCmd.Op1.Addr = [curCmd.Op1.Data];
curCmd.Op2.Addr = [null]; // &CurCmd->Op2.Data;
curCmd.Op1.Type = VM_OpType.VM_OPNONE;
curCmd.Op2.Type = VM_OpType.VM_OPNONE;
codeSize = 0;
}
var dataFlag = bstream.readBits(1);
// Read static data contained in DB operators. This data cannot be
// changed, it is a part of VM code, not a filter parameter.
if (dataFlag & 0x8000) {
var dataSize = RarVM.readData(bstream) + 1;
// TODO: This accesses the byte pointer of the bstream directly. Is that ok?
for (var i = 0; i < bstream.bytePtr < codeSize && i < dataSize; ++i) {
// Append a byte to the program's static data.
var newStaticData = new Uint8Array(prg.StaticData.length + 1);
newStaticData.set(prg.StaticData);
newStaticData[newStaticData.length - 1] = bstream.readBits(8);
prg.StaticData = newStaticData;
}
}
while (bstream.bytePtr < codeSize) {
var curCmd = new VM_PreparedCommand();
prg.Cmd.push(curCmd); // Prg->Cmd.Add(1)
var flag = bstream.peekBits(1);
if (!flag) { // (Data&0x8000)==0
curCmd.OpCode = bstream.readBits(4);
} else {
curCmd.OpCode = (bstream.readBits(6) - 24);
}
if (VM_CmdFlags[curCmd.OpCode] & VMCF_BYTEMODE) {
curCmd.ByteMode = (bstream.readBits(1) != 0);
} else {
curCmd.ByteMode = 0;
}
curCmd.Op1.Type = VM_OpType.VM_OPNONE;
curCmd.Op2.Type = VM_OpType.VM_OPNONE;
var opNum = (VM_CmdFlags[curCmd.OpCode] & VMCF_OPMASK);
curCmd.Op1.Addr = null;
curCmd.Op2.Addr = null;
if (opNum > 0) {
this.decodeArg(curCmd.Op1, curCmd.ByteMode, bstream); // reading the first operand
if (opNum == 2) {
this.decodeArg(curCmd.Op2, curCmd.ByteMode, bstream); // reading the second operand
} else {
if (curCmd.Op1.Type == VM_OpType.VM_OPINT && (VM_CmdFlags[curCmd.OpCode] & (VMCF_JUMP | VMCF_PROC))) {
// Calculating jump distance.
var distance = curCmd.Op1.Data;
if (distance >= 256) {
distance -= 256;
} else {
if (distance >= 136) {
distance -= 264;
} else {
if (distance >= 16) {
distance -= 8;
} else {
if (distance >= 8) {
distance -= 16;
}
}
}
distance += prg.Cmd.length;
}
curCmd.Op1.Data = distance;
}
}
} // if (OpNum>0)
} // while ((uint)InAddr<CodeSize)
} // if (XorSum==Code[0])
var curCmd = new VM_PreparedCommand();
prg.Cmd.push(curCmd);
curCmd.OpCode = VM_Commands.VM_RET;
// TODO: Addr=&CurCmd->Op1.Data
curCmd.Op1.Addr = [curCmd.Op1.Data];
curCmd.Op2.Addr = [curCmd.Op2.Data];
curCmd.Op1.Type = VM_OpType.VM_OPNONE;
curCmd.Op2.Type = VM_OpType.VM_OPNONE;
// If operand 'Addr' field has not been set by DecodeArg calls above,
// let's set it to point to operand 'Data' field. It is necessary for
// VM_OPINT type operands (usual integers) or maybe if something was
// not set properly for other operands. 'Addr' field is required
// for quicker addressing of operand data.
for (var i = 0; i < prg.Cmd.length; ++i) {
var cmd = prg.Cmd[i];
if (cmd.Op1.Addr == null) {
cmd.Op1.Addr = [cmd.Op1.Data];
}
if (cmd.Op2.Addr == null) {
cmd.Op2.Addr = [cmd.Op2.Data];
}
}
/*
#ifdef VM_OPTIMIZE
if (CodeSize!=0)
Optimize(Prg);
#endif
*/
};
/**
* @param {Uint8Array} arr The byte array to set a value in.
* @param {number} value The unsigned 32-bit value to set.
* @param {number} offset Offset into arr to start setting the value, defaults to 0.
*/
RarVM.prototype.setLowEndianValue = function(arr, value, offset) {
var i = offset || 0;
arr[i] = value & 0xff;
arr[i + 1] = (value >>> 8) & 0xff;
arr[i + 2] = (value >>> 16) & 0xff;
arr[i + 3] = (value >>> 24) & 0xff;
};
/**
* Sets a number of bytes of the VM memory at the given position from a
* source buffer of bytes.
* @param {number} pos The position in the VM memory to start writing to.
* @param {Uint8Array} buffer The source buffer of bytes.
* @param {number} dataSize The number of bytes to set.
*/
RarVM.prototype.setMemory = function(pos, buffer, dataSize) {
if (pos < VM_MEMSIZE) {
var numBytes = Math.min(dataSize, VM_MEMSIZE - pos);
for (var i = 0; i < numBytes; ++i) {
this.mem_[pos + i] = buffer[i];
}
}
};
/**
* Static function that reads in the next set of bits for the VM
* (might return 4, 8, 16 or 32 bits).
* @param {bitjs.io.BitStream} bstream A RTL bit stream.
* @return {number} The value of the bits read.
*/
RarVM.readData = function(bstream) {
// Read in the first 2 bits.
var flags = bstream.readBits(2);
switch (flags) { // Data&0xc000
// Return the next 4 bits.
case 0:
return bstream.readBits(4); // (Data>>10)&0xf
case 1: // 0x4000
// 0x3c00 => 0011 1100 0000 0000
if (bstream.peekBits(4) == 0) { // (Data&0x3c00)==0
// Skip the 4 zero bits.
bstream.readBits(4);
// Read in the next 8 and pad with 1s to 32 bits.
return (0xffffff00 | bstream.readBits(8)) >>> 0; // ((Data>>2)&0xff)
}
// Else, read in the next 8.
return bstream.readBits(8);
// Read in the next 16.
case 2: // 0x8000
var val = bstream.getBits();
bstream.readBits(16);
return val; //bstream.readBits(16);
// case 3
default:
return (bstream.readBits(16) << 16) | bstream.readBits(16);
}
};
// ============================================================================================== //

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,167 @@
/**
* untar.js
*
* Licensed under the MIT License
*
* Copyright(c) 2011 Google Inc.
*
* Reference Documentation:
*
* TAR format: http://www.gnu.org/software/automake/manual/tar/Standard.html
*/
// This file expects to be invoked as a Worker (see onmessage below).
importScripts('../io/bytestream.js');
importScripts('archive.js');
// Progress variables.
var currentFilename = "";
var currentFileNumber = 0;
var currentBytesUnarchivedInFile = 0;
var currentBytesUnarchived = 0;
var totalUncompressedBytesInArchive = 0;
var totalFilesInArchive = 0;
// Helper functions.
var info = function(str) {
postMessage(new bitjs.archive.UnarchiveInfoEvent(str));
};
var err = function(str) {
postMessage(new bitjs.archive.UnarchiveErrorEvent(str));
};
// Removes all characters from the first zero-byte in the string onwards.
var readCleanString = function(bstr, numBytes) {
var str = bstr.readString(numBytes);
var zIndex = str.indexOf(String.fromCharCode(0));
return zIndex != -1 ? str.substr(0, zIndex) : str;
};
var postProgress = function() {
postMessage(new bitjs.archive.UnarchiveProgressEvent(
currentFilename,
currentFileNumber,
currentBytesUnarchivedInFile,
currentBytesUnarchived,
totalUncompressedBytesInArchive,
totalFilesInArchive,
));
};
// takes a ByteStream and parses out the local file information
var TarLocalFile = function(bstream) {
this.isValid = false;
var bytesRead = 0;
// Read in the header block
this.name = readCleanString(bstream, 100);
this.mode = readCleanString(bstream, 8);
this.uid = readCleanString(bstream, 8);
this.gid = readCleanString(bstream, 8);
this.size = parseInt(readCleanString(bstream, 12), 8);
this.mtime = readCleanString(bstream, 12);
this.chksum = readCleanString(bstream, 8);
this.typeflag = readCleanString(bstream, 1);
this.linkname = readCleanString(bstream, 100);
this.maybeMagic = readCleanString(bstream, 6);
if (this.maybeMagic == "ustar") {
this.version = readCleanString(bstream, 2);
this.uname = readCleanString(bstream, 32);
this.gname = readCleanString(bstream, 32);
this.devmajor = readCleanString(bstream, 8);
this.devminor = readCleanString(bstream, 8);
this.prefix = readCleanString(bstream, 155);
if (this.prefix.length) {
this.name = this.prefix + this.name;
}
bstream.readBytes(12); // 512 - 500
} else {
bstream.readBytes(255); // 512 - 257
}
bytesRead += 512;
// Done header, now rest of blocks are the file contents.
this.filename = this.name;
this.fileData = null;
info("Untarring file '" + this.filename + "'");
info(" size = " + this.size);
info(" typeflag = " + this.typeflag);
// A regular file.
if (this.typeflag == 0) {
info(" This is a regular file.");
var sizeInBytes = parseInt(this.size);
this.fileData = new Uint8Array(bstream.readBytes(sizeInBytes));
bytesRead += sizeInBytes;
if (this.name.length > 0 && this.size > 0 && this.fileData && this.fileData.buffer) {
this.isValid = true;
}
// Round up to 512-byte blocks.
var remaining = 512 - bytesRead % 512;
if (remaining > 0 && remaining < 512) {
bstream.readBytes(remaining);
}
} else if (this.typeflag == 5) {
info(" This is a directory.");
}
}
var untar = function(arrayBuffer) {
postMessage(new bitjs.archive.UnarchiveStartEvent());
currentFilename = "";
currentFileNumber = 0;
currentBytesUnarchivedInFile = 0;
currentBytesUnarchived = 0;
totalUncompressedBytesInArchive = 0;
totalFilesInArchive = 0;
allLocalFiles = [];
var bstream = new bitjs.io.ByteStream(arrayBuffer);
postProgress();
// While we don't encounter an empty block, keep making TarLocalFiles.
while (bstream.peekNumber(4) != 0) {
var oneLocalFile = new TarLocalFile(bstream);
if (oneLocalFile && oneLocalFile.isValid) {
// If we make it to this point and haven't thrown an error, we have successfully
// read in the data for a local file, so we can update the actual bytestream.
allLocalFiles.push(oneLocalFile);
totalUncompressedBytesInArchive += oneLocalFile.size;
// update progress
currentFilename = oneLocalFile.filename;
currentFileNumber = totalFilesInArchive++;
currentBytesUnarchivedInFile = oneLocalFile.size;
currentBytesUnarchived += oneLocalFile.size;
postMessage(new bitjs.archive.UnarchiveExtractEvent(oneLocalFile));
postProgress();
}
}
totalFilesInArchive = allLocalFiles.length;
postProgress();
postMessage(new bitjs.archive.UnarchiveFinishEvent());
};
// event.data.file has the first ArrayBuffer.
// event.data.bytes has all subsequent ArrayBuffers.
onmessage = function(event) {
try {
untar(event.data.file, true);
} catch (e) {
if (typeof e === "string" && e.startsWith("Error! Overflowed")) {
// Overrun the buffer.
// unarchiveState = UnarchiveState.WAITING;
} else {
console.error("Found an error while untarring");
console.log(e);
throw e;
}
}
};

View File

@@ -0,0 +1,667 @@
/**
* unzip.js
*
* Licensed under the MIT License
*
* Copyright(c) 2011 Google Inc.
* Copyright(c) 2011 antimatter15
*
* Reference Documentation:
*
* ZIP format: http://www.pkware.com/documents/casestudies/APPNOTE.TXT
* DEFLATE format: http://tools.ietf.org/html/rfc1951
*/
/* global bitjs, importScripts, Uint8Array*/
// This file expects to be invoked as a Worker (see onmessage below).
importScripts('../io/bitstream.js');
importScripts('../io/bytebuffer.js');
importScripts('../io/bytestream.js');
importScripts('archive.js');
// Progress variables.
var currentFilename = "";
var currentFileNumber = 0;
var currentBytesUnarchivedInFile = 0;
var currentBytesUnarchived = 0;
var totalUncompressedBytesInArchive = 0;
var totalFilesInArchive = 0;
// Helper functions.
var info = function(str) {
postMessage(new bitjs.archive.UnarchiveInfoEvent(str));
};
var err = function(str) {
postMessage(new bitjs.archive.UnarchiveErrorEvent(str));
};
var postProgress = function() {
postMessage(new bitjs.archive.UnarchiveProgressEvent(
currentFilename,
currentFileNumber,
currentBytesUnarchivedInFile,
currentBytesUnarchived,
totalUncompressedBytesInArchive,
totalFilesInArchive));
};
var zLocalFileHeaderSignature = 0x04034b50;
var zArchiveExtraDataSignature = 0x08064b50;
var zCentralFileHeaderSignature = 0x02014b50;
var zDigitalSignatureSignature = 0x05054b50;
// takes a ByteStream and parses out the local file information
var ZipLocalFile = function(bstream) {
if (typeof bstream !== typeof {} || !bstream.readNumber || typeof bstream.readNumber !== typeof function() {}) {
return null;
}
bstream.readNumber(4); // swallow signature
this.version = bstream.readNumber(2);
this.generalPurpose = bstream.readNumber(2);
this.compressionMethod = bstream.readNumber(2);
this.lastModFileTime = bstream.readNumber(2);
this.lastModFileDate = bstream.readNumber(2);
this.crc32 = bstream.readNumber(4);
this.compressedSize = bstream.readNumber(4);
this.uncompressedSize = bstream.readNumber(4);
this.fileNameLength = bstream.readNumber(2);
this.extraFieldLength = bstream.readNumber(2);
this.filename = null;
if (this.fileNameLength > 0) {
this.filename = bstream.readString(this.fileNameLength);
}
info("Zip Local File Header:");
info(" version=" + this.version);
info(" general purpose=" + this.generalPurpose);
info(" compression method=" + this.compressionMethod);
info(" last mod file time=" + this.lastModFileTime);
info(" last mod file date=" + this.lastModFileDate);
info(" crc32=" + this.crc32);
info(" compressed size=" + this.compressedSize);
info(" uncompressed size=" + this.uncompressedSize);
info(" file name length=" + this.fileNameLength);
info(" extra field length=" + this.extraFieldLength);
info(" filename = '" + this.filename + "'");
this.extraField = null;
if (this.extraFieldLength > 0) {
this.extraField = bstream.readString(this.extraFieldLength);
info(" extra field=" + this.extraField);
}
// read in the compressed data
this.fileData = null;
if (this.compressedSize > 0) {
this.fileData = new Uint8Array(bstream.bytes.buffer, bstream.ptr, this.compressedSize);
bstream.ptr += this.compressedSize;
}
// TODO: deal with data descriptor if present (we currently assume no data descriptor!)
// "This descriptor exists only if bit 3 of the general purpose bit flag is set"
// But how do you figure out how big the file data is if you don't know the compressedSize
// from the header?!?
if ((this.generalPurpose & bitjs.BIT[3]) !== 0) {
this.crc32 = bstream.readNumber(4);
this.compressedSize = bstream.readNumber(4);
this.uncompressedSize = bstream.readNumber(4);
}
};
// determine what kind of compressed data we have and decompress
ZipLocalFile.prototype.unzip = function() {
// Zip Version 1.0, no compression (store only)
if (this.compressionMethod === 0 ) {
info("ZIP v" + this.version + ", store only: " + this.filename + " (" + this.compressedSize + " bytes)");
currentBytesUnarchivedInFile = this.compressedSize;
currentBytesUnarchived += this.compressedSize;
this.fileData = zeroCompression(this.fileData, this.uncompressedSize);
}
// version == 20, compression method == 8 (DEFLATE)
else if (this.compressionMethod === 8) {
info("ZIP v2.0, DEFLATE: " + this.filename + " (" + this.compressedSize + " bytes)");
this.fileData = inflate(this.fileData, this.uncompressedSize);
}
else {
err("UNSUPPORTED VERSION/FORMAT: ZIP v" + this.version + ", compression method=" + this.compressionMethod + ": " + this.filename + " (" + this.compressedSize + " bytes)");
this.fileData = null;
}
};
// Takes an ArrayBuffer of a zip file in
// returns null on error
// returns an array of DecompressedFile objects on success
var unzip = function(arrayBuffer) {
postMessage(new bitjs.archive.UnarchiveStartEvent());
currentFilename = "";
currentFileNumber = 0;
currentBytesUnarchivedInFile = 0;
currentBytesUnarchived = 0;
totalUncompressedBytesInArchive = 0;
totalFilesInArchive = 0;
currentBytesUnarchived = 0;
var bstream = new bitjs.io.ByteStream(arrayBuffer);
// detect local file header signature or return null
if (bstream.peekNumber(4) === zLocalFileHeaderSignature) {
var localFiles = [];
// loop until we don't see any more local files
while (bstream.peekNumber(4) === zLocalFileHeaderSignature) {
var oneLocalFile = new ZipLocalFile(bstream);
// this should strip out directories/folders
if (oneLocalFile && oneLocalFile.uncompressedSize > 0 && oneLocalFile.fileData) {
localFiles.push(oneLocalFile);
totalUncompressedBytesInArchive += oneLocalFile.uncompressedSize;
}
}
totalFilesInArchive = localFiles.length;
// got all local files, now sort them
localFiles.sort(function(a, b) {
var aname = a.filename.toLowerCase();
var bname = b.filename.toLowerCase();
return aname > bname ? 1 : -1;
});
// archive extra data record
if (bstream.peekNumber(4) === zArchiveExtraDataSignature) {
info(" Found an Archive Extra Data Signature");
// skipping this record for now
bstream.readNumber(4);
var archiveExtraFieldLength = bstream.readNumber(4);
bstream.readString(archiveExtraFieldLength);
}
// central directory structure
// TODO: handle the rest of the structures (Zip64 stuff)
if (bstream.peekNumber(4) === zCentralFileHeaderSignature) {
info(" Found a Central File Header");
// read all file headers
while (bstream.peekNumber(4) === zCentralFileHeaderSignature) {
bstream.readNumber(4); // signature
bstream.readNumber(2); // version made by
bstream.readNumber(2); // version needed to extract
bstream.readNumber(2); // general purpose bit flag
bstream.readNumber(2); // compression method
bstream.readNumber(2); // last mod file time
bstream.readNumber(2); // last mod file date
bstream.readNumber(4); // crc32
bstream.readNumber(4); // compressed size
bstream.readNumber(4); // uncompressed size
var fileNameLength = bstream.readNumber(2); // file name length
var extraFieldLength = bstream.readNumber(2); // extra field length
var fileCommentLength = bstream.readNumber(2); // file comment length
bstream.readNumber(2); // disk number start
bstream.readNumber(2); // internal file attributes
bstream.readNumber(4); // external file attributes
bstream.readNumber(4); // relative offset of local header
bstream.readString(fileNameLength); // file name
bstream.readString(extraFieldLength); // extra field
bstream.readString(fileCommentLength); // file comment
}
}
// digital signature
if (bstream.peekNumber(4) === zDigitalSignatureSignature) {
info(" Found a Digital Signature");
bstream.readNumber(4);
var sizeOfSignature = bstream.readNumber(2);
bstream.readString(sizeOfSignature); // digital signature data
}
// report # files and total length
if (localFiles.length > 0) {
postProgress();
}
// now do the unzipping of each file
for (var i = 0; i < localFiles.length; ++i) {
var localfile = localFiles[i];
// update progress
currentFilename = localfile.filename;
currentFileNumber = i;
currentBytesUnarchivedInFile = 0;
// actually do the unzipping
localfile.unzip();
if (localfile.fileData !== null) {
postMessage(new bitjs.archive.UnarchiveExtractEvent(localfile));
postProgress();
}
}
postProgress();
postMessage(new bitjs.archive.UnarchiveFinishEvent());
}
};
// returns a table of Huffman codes
// each entry's index is its code and its value is a JavaScript object
// containing {length: 6, symbol: X}
function getHuffmanCodes(bitLengths) {
// ensure bitLengths is an array containing at least one element
if (typeof bitLengths !== typeof [] || bitLengths.length < 1) {
err("Error! getHuffmanCodes() called with an invalid array");
return null;
}
// Reference: http://tools.ietf.org/html/rfc1951#page-8
var numLengths = bitLengths.length,
blCount = [],
MAX_BITS = 1;
// Step 1: count up how many codes of each length we have
for (var i = 0; i < numLengths; ++i) {
var length = bitLengths[i];
// test to ensure each bit length is a positive, non-zero number
if (typeof length !== typeof 1 || length < 0) {
err("bitLengths contained an invalid number in getHuffmanCodes(): " + length + " of type " + (typeof length));
return null;
}
// increment the appropriate bitlength count
if (typeof blCount[length] === "undefined") blCount[length] = 0;
// a length of zero means this symbol is not participating in the huffman coding
if (length > 0) blCount[length]++;
if (length > MAX_BITS) MAX_BITS = length;
}
// Step 2: Find the numerical value of the smallest code for each code length
var nextCode = [],
code = 0;
for (var bits = 1; bits <= MAX_BITS; ++bits) {
var length2 = bits - 1;
// ensure undefined lengths are zero
if (typeof blCount[length2] === "undefined") blCount[length2] = 0;
code = (code + blCount[bits - 1]) << 1;
nextCode [bits] = code;
}
// Step 3: Assign numerical values to all codes
var table = {},
tableLength = 0;
for (var n = 0; n < numLengths; ++n) {
var len = bitLengths[n];
if (len !== 0) {
table[nextCode [len]] = { length: len, symbol: n }; //, bitstring: binaryValueToString(nextCode [len],len) };
tableLength++;
nextCode [len]++;
}
}
table.maxLength = tableLength;
return table;
}
/*
The Huffman codes for the two alphabets are fixed, and are not
represented explicitly in the data. The Huffman code lengths
for the literal/length alphabet are:
Lit Value Bits Codes
--------- ---- -----
0 - 143 8 00110000 through
10111111
144 - 255 9 110010000 through
111111111
256 - 279 7 0000000 through
0010111
280 - 287 8 11000000 through
11000111
*/
// fixed Huffman codes go from 7-9 bits, so we need an array whose index can hold up to 9 bits
var fixedHCtoLiteral = null;
var fixedHCtoDistance = null;
function getFixedLiteralTable() {
// create once
if (!fixedHCtoLiteral) {
var bitlengths = new Array(288);
var i;
for (i = 0; i <= 143; ++i) bitlengths[i] = 8;
for (i = 144; i <= 255; ++i) bitlengths[i] = 9;
for (i = 256; i <= 279; ++i) bitlengths[i] = 7;
for (i = 280; i <= 287; ++i) bitlengths[i] = 8;
// get huffman code table
fixedHCtoLiteral = getHuffmanCodes(bitlengths);
}
return fixedHCtoLiteral;
}
function getFixedDistanceTable() {
// create once
if (!fixedHCtoDistance) {
var bitlengths = new Array(32);
for (var i = 0; i < 32; ++i) {
bitlengths[i] = 5;
}
// get huffman code table
fixedHCtoDistance = getHuffmanCodes(bitlengths);
}
return fixedHCtoDistance;
}
// extract one bit at a time until we find a matching Huffman Code
// then return that symbol
function decodeSymbol(bstream, hcTable) {
var code = 0, len = 0;
// loop until we match
for (;;) {
// read in next bit
var bit = bstream.readBits(1);
code = (code << 1) | bit;
++len;
// check against Huffman Code table and break if found
if (hcTable.hasOwnProperty(code) && hcTable[code].length === len) {
break;
}
if (len > hcTable.maxLength) {
err("Bit stream out of sync, didn't find a Huffman Code, length was " + len +
" and table only max code length of " + hcTable.maxLength);
break;
}
}
return hcTable[code].symbol;
}
var CodeLengthCodeOrder = [16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15];
/*
Extra Extra Extra
Code Bits Length(s) Code Bits Lengths Code Bits Length(s)
---- ---- ------ ---- ---- ------- ---- ---- -------
257 0 3 267 1 15,16 277 4 67-82
258 0 4 268 1 17,18 278 4 83-98
259 0 5 269 2 19-22 279 4 99-114
260 0 6 270 2 23-26 280 4 115-130
261 0 7 271 2 27-30 281 5 131-162
262 0 8 272 2 31-34 282 5 163-194
263 0 9 273 3 35-42 283 5 195-226
264 0 10 274 3 43-50 284 5 227-257
265 1 11,12 275 3 51-58 285 0 258
266 1 13,14 276 3 59-66
*/
var LengthLookupTable = [
[0, 3],
[0, 4],
[0, 5],
[0, 6],
[0, 7],
[0, 8],
[0, 9],
[0, 10],
[1, 11],
[1, 13],
[1, 15],
[1, 17],
[2, 19],
[2, 23],
[2, 27],
[2, 31],
[3, 35],
[3, 43],
[3, 51],
[3, 59],
[4, 67],
[4, 83],
[4, 99],
[4, 115],
[5, 131],
[5, 163],
[5, 195],
[5, 227],
[0, 258]
];
/*
Extra Extra Extra
Code Bits Dist Code Bits Dist Code Bits Distance
---- ---- ---- ---- ---- ------ ---- ---- --------
0 0 1 10 4 33-48 20 9 1025-1536
1 0 2 11 4 49-64 21 9 1537-2048
2 0 3 12 5 65-96 22 10 2049-3072
3 0 4 13 5 97-128 23 10 3073-4096
4 1 5,6 14 6 129-192 24 11 4097-6144
5 1 7,8 15 6 193-256 25 11 6145-8192
6 2 9-12 16 7 257-384 26 12 8193-12288
7 2 13-16 17 7 385-512 27 12 12289-16384
8 3 17-24 18 8 513-768 28 13 16385-24576
9 3 25-32 19 8 769-1024 29 13 24577-32768
*/
var DistLookupTable = [
[0, 1],
[0, 2],
[0, 3],
[0, 4],
[1, 5],
[1, 7],
[2, 9],
[2, 13],
[3, 17],
[3, 25],
[4, 33],
[4, 49],
[5, 65],
[5, 97],
[6, 129],
[6, 193],
[7, 257],
[7, 385],
[8, 513],
[8, 769],
[9, 1025],
[9, 1537],
[10, 2049],
[10, 3073],
[11, 4097],
[11, 6145],
[12, 8193],
[12, 12289],
[13, 16385],
[13, 24577]
];
function inflateBlockData(bstream, hcLiteralTable, hcDistanceTable, buffer) {
/*
loop (until end of block code recognized)
decode literal/length value from input stream
if value < 256
copy value (literal byte) to output stream
otherwise
if value = end of block (256)
break from loop
otherwise (value = 257..285)
decode distance from input stream
move backwards distance bytes in the output
stream, and copy length bytes from this
position to the output stream.
*/
var blockSize = 0;
for (;;) {
var symbol = decodeSymbol(bstream, hcLiteralTable);
if (symbol < 256) {
// copy literal byte to output
buffer.insertByte(symbol);
blockSize++;
}
else {
// end of block reached
if (symbol === 256) {
break;
}
else {
var lengthLookup = LengthLookupTable[symbol - 257],
length = lengthLookup[1] + bstream.readBits(lengthLookup[0]),
distLookup = DistLookupTable[decodeSymbol(bstream, hcDistanceTable)],
distance = distLookup[1] + bstream.readBits(distLookup[0]);
// now apply length and distance appropriately and copy to output
// TODO: check that backward distance < data.length?
// http://tools.ietf.org/html/rfc1951#page-11
// "Note also that the referenced string may overlap the current
// position; for example, if the last 2 bytes decoded have values
// X and Y, a string reference with <length = 5, distance = 2>
// adds X,Y,X,Y,X to the output stream."
//
// loop for each character
var ch = buffer.ptr - distance;
blockSize += length;
if (length > distance) {
var data = buffer.data;
while (length--) {
buffer.insertByte(data[ch++]);
}
} else {
buffer.insertBytes(buffer.data.subarray(ch, ch + length));
}
} // length-distance pair
} // length-distance pair or end-of-block
} // loop until we reach end of block
return blockSize;
}
function zeroCompression(compressedData, numDecompressedBytes) {
var bstream = new bitjs.io.BitStream(compressedData.buffer,
false /* rtl */,
compressedData.byteOffset,
compressedData.byteLength);
var buffer = new bitjs.io.ByteBuffer(numDecompressedBytes);
buffer.insertBytes(bstream.readBytes(numDecompressedBytes));
return buffer.data;
}
// {Uint8Array} compressedData A Uint8Array of the compressed file data.
// compression method 8
// deflate: http://tools.ietf.org/html/rfc1951
function inflate(compressedData, numDecompressedBytes) {
// Bit stream representing the compressed data.
var bstream = new bitjs.io.BitStream(compressedData.buffer,
false /* rtl */,
compressedData.byteOffset,
compressedData.byteLength);
var buffer = new bitjs.io.ByteBuffer(numDecompressedBytes);
var blockSize = 0;
// block format: http://tools.ietf.org/html/rfc1951#page-9
var bFinal = 0;
do {
bFinal = bstream.readBits(1);
var bType = bstream.readBits(2);
blockSize = 0;
// ++numBlocks;
// no compression
if (bType == 0) {
// skip remaining bits in this byte
while (bstream.bitPtr !== 0) bstream.readBits(1);
var len = bstream.readBits(16);
bstream.readBits(16);
// TODO: check if nlen is the ones-complement of len?
if (len > 0) buffer.insertBytes(bstream.readBytes(len));
blockSize = len;
}
// fixed Huffman codes
else if (bType === 1) {
blockSize = inflateBlockData(bstream, getFixedLiteralTable(), getFixedDistanceTable(), buffer);
}
// dynamic Huffman codes
else if (bType === 2) {
var numLiteralLengthCodes = bstream.readBits(5) + 257;
var numDistanceCodes = bstream.readBits(5) + 1,
numCodeLengthCodes = bstream.readBits(4) + 4;
// populate the array of code length codes (first de-compaction)
var codeLengthsCodeLengths = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0];
for (var i = 0; i < numCodeLengthCodes; ++i) {
codeLengthsCodeLengths[ CodeLengthCodeOrder[i] ] = bstream.readBits(3);
}
// get the Huffman Codes for the code lengths
var codeLengthsCodes = getHuffmanCodes(codeLengthsCodeLengths);
// now follow this mapping
/*
0 - 15: Represent code lengths of 0 - 15
16: Copy the previous code length 3 - 6 times.
The next 2 bits indicate repeat length
(0 = 3, ... , 3 = 6)
Example: Codes 8, 16 (+2 bits 11),
16 (+2 bits 10) will expand to
12 code lengths of 8 (1 + 6 + 5)
17: Repeat a code length of 0 for 3 - 10 times.
(3 bits of length)
18: Repeat a code length of 0 for 11 - 138 times
(7 bits of length)
*/
// to generate the true code lengths of the Huffman Codes for the literal
// and distance tables together
var literalCodeLengths = [];
var prevCodeLength = 0;
while (literalCodeLengths.length < numLiteralLengthCodes + numDistanceCodes) {
var symbol = decodeSymbol(bstream, codeLengthsCodes);
if (symbol <= 15) {
literalCodeLengths.push(symbol);
prevCodeLength = symbol;
} else if (symbol === 16) {
var repeat = bstream.readBits(2) + 3;
while (repeat--) {
literalCodeLengths.push(prevCodeLength);
}
} else if (symbol === 17) {
var repeat1 = bstream.readBits(3) + 3;
while (repeat1--) {
literalCodeLengths.push(0);
}
} else if (symbol === 18) {
var repeat2 = bstream.readBits(7) + 11;
while (repeat2--) {
literalCodeLengths.push(0);
}
}
}
// now split the distance code lengths out of the literal code array
var distanceCodeLengths = literalCodeLengths.splice(numLiteralLengthCodes, numDistanceCodes);
// now generate the true Huffman Code tables using these code lengths
var hcLiteralTable = getHuffmanCodes(literalCodeLengths),
hcDistanceTable = getHuffmanCodes(distanceCodeLengths);
blockSize = inflateBlockData(bstream, hcLiteralTable, hcDistanceTable, buffer);
} else {
// error
err("Error! Encountered deflate block of type 3");
return null;
}
// update progress
currentBytesUnarchivedInFile += blockSize;
currentBytesUnarchived += blockSize;
postProgress();
} while (bFinal !== 1);
// we are done reading blocks if the bFinal bit was set for this block
// return the buffer data bytes
return buffer.data;
}
// event.data.file has the ArrayBuffer.
onmessage = function(event) {
unzip(event.data.file, true);
};