Hide keyboard shortcuts

Hot-keys on this page

r m x p   toggle line displays

j k   next/prev highlighted chunk

0   (zero) top of page

1   (one) first highlighted chunk

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

82

83

84

85

86

87

88

89

90

91

92

93

94

95

96

97

98

99

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

396

397

398

399

400

401

402

403

404

405

406

407

408

409

410

411

412

413

414

415

416

417

418

419

420

421

422

423

424

425

426

427

428

429

430

431

432

433

434

435

436

437

438

439

440

441

442

443

444

445

446

447

448

449

450

451

452

453

454

455

456

457

458

459

460

461

462

463

464

465

466

467

468

469

470

471

472

473

474

475

476

477

478

479

480

481

482

483

484

485

486

487

488

489

490

491

492

493

494

495

496

497

498

499

500

501

502

503

504

505

506

507

508

509

510

511

512

513

514

515

516

517

518

519

520

521

522

523

524

525

526

527

528

529

530

531

532

533

534

535

536

537

538

539

540

541

542

543

544

545

546

547

548

549

550

551

552

553

554

555

556

557

558

559

560

561

562

563

564

565

566

567

568

569

570

571

572

573

574

575

576

577

578

579

580

581

582

583

584

585

586

587

588

589

590

591

592

593

594

595

596

597

598

599

600

601

602

603

604

605

606

607

608

609

610

611

612

613

614

615

616

617

618

619

620

621

622

623

624

625

626

627

628

629

630

631

632

633

634

635

636

637

638

639

640

641

642

643

644

645

646

647

648

649

650

651

652

653

654

655

656

657

658

659

660

661

662

663

664

665

666

667

668

669

670

671

672

673

674

675

676

677

678

679

680

681

682

683

684

685

686

687

688

689

690

691

692

693

694

695

696

697

698

699

700

701

702

703

704

705

706

707

708

709

710

711

712

713

714

715

716

717

718

719

720

721

722

723

724

725

726

727

728

729

730

731

732

733

734

735

736

737

738

739

740

741

742

743

744

745

746

747

748

749

750

751

752

753

754

755

756

757

758

759

760

761

762

763

764

765

766

767

768

769

770

771

772

773

774

775

776

777

778

779

780

781

782

783

784

785

786

787

788

789

790

791

792

793

794

795

796

797

798

799

800

801

802

803

804

805

806

807

808

809

810

811

812

813

814

815

816

817

818

819

820

821

822

823

824

825

826

827

828

829

830

831

832

833

834

835

836

837

838

839

840

841

842

843

844

845

846

847

848

849

850

851

852

853

854

855

856

857

858

859

860

861

862

863

864

865

866

867

868

869

870

871

872

873

874

875

876

877

878

879

880

881

882

883

884

885

886

887

888

889

890

891

892

893

894

895

896

897

898

899

900

901

902

903

904

905

906

907

908

909

910

911

912

913

914

915

916

917

918

919

920

921

922

923

924

925

926

927

928

929

930

931

932

933

934

935

936

937

938

939

940

941

942

943

944

945

946

947

948

949

950

951

952

953

954

955

956

957

958

959

960

961

962

963

964

965

966

967

968

969

970

# SECUREAUTH LABS. Copyright 2018 SecureAuth Corporation. All rights reserved. 

# 

# This software is provided under under a slightly modified version 

# of the Apache Software License. See the accompanying LICENSE file 

# for more information. 

# 

# Description: 

# Microsoft Extensive Storage Engine parser, just focused on trying  

# to parse NTDS.dit files (not meant as a full parser, although it might work) 

# 

# Author: 

# Alberto Solino (@agsolino) 

# 

# Reference for: 

# Structure. 

#  

# Excellent reference done by Joachim Metz 

# http://forensic-proof.com/wp-content/uploads/2011/07/Extensible-Storage-Engine-ESE-Database-File-EDB-format.pdf 

# 

# ToDo:  

# [ ] Parse multi-values properly 

# [ ] Support long values properly 

from __future__ import division 

from __future__ import print_function 

from impacket import LOG 

try: 

from collections import OrderedDict 

except: 

try: 

from ordereddict.ordereddict import OrderedDict 

except: 

from ordereddict import OrderedDict 

from impacket.structure import Structure, hexdump 

from struct import unpack 

from binascii import hexlify 

from six import b 

 

# Constants 

 

FILE_TYPE_DATABASE = 0 

FILE_TYPE_STREAMING_FILE = 1 

 

# Database state 

JET_dbstateJustCreated = 1 

JET_dbstateDirtyShutdown = 2 

JET_dbstateCleanShutdown = 3 

JET_dbstateBeingConverted = 4 

JET_dbstateForceDetach = 5 

 

# Page Flags 

FLAGS_ROOT = 1 

FLAGS_LEAF = 2 

FLAGS_PARENT = 4 

FLAGS_EMPTY = 8 

FLAGS_SPACE_TREE = 0x20 

FLAGS_INDEX = 0x40 

FLAGS_LONG_VALUE = 0x80 

FLAGS_NEW_FORMAT = 0x2000 

FLAGS_NEW_CHECKSUM = 0x2000 

 

# Tag Flags 

TAG_UNKNOWN = 0x1 

TAG_DEFUNCT = 0x2 

TAG_COMMON = 0x4 

 

# Fixed Page Numbers 

DATABASE_PAGE_NUMBER = 1 

CATALOG_PAGE_NUMBER = 4 

CATALOG_BACKUP_PAGE_NUMBER = 24 

 

# Fixed FatherDataPages 

DATABASE_FDP = 1 

CATALOG_FDP = 2 

CATALOG_BACKUP_FDP = 3 

 

# Catalog Types 

CATALOG_TYPE_TABLE = 1 

CATALOG_TYPE_COLUMN = 2 

CATALOG_TYPE_INDEX = 3 

CATALOG_TYPE_LONG_VALUE = 4 

CATALOG_TYPE_CALLBACK = 5 

 

# Column Types 

JET_coltypNil = 0 

JET_coltypBit = 1 

JET_coltypUnsignedByte = 2 

JET_coltypShort = 3 

JET_coltypLong = 4 

JET_coltypCurrency = 5 

JET_coltypIEEESingle = 6 

JET_coltypIEEEDouble = 7 

JET_coltypDateTime = 8 

JET_coltypBinary = 9 

JET_coltypText = 10 

JET_coltypLongBinary = 11 

JET_coltypLongText = 12 

JET_coltypSLV = 13 

JET_coltypUnsignedLong = 14 

JET_coltypLongLong = 15 

JET_coltypGUID = 16 

JET_coltypUnsignedShort= 17 

JET_coltypMax = 18 

 

ColumnTypeToName = { 

JET_coltypNil : 'NULL', 

JET_coltypBit : 'Boolean', 

JET_coltypUnsignedByte : 'Signed byte', 

JET_coltypShort : 'Signed short', 

JET_coltypLong : 'Signed long', 

JET_coltypCurrency : 'Currency', 

JET_coltypIEEESingle : 'Single precision FP', 

JET_coltypIEEEDouble : 'Double precision FP', 

JET_coltypDateTime : 'DateTime', 

JET_coltypBinary : 'Binary', 

JET_coltypText : 'Text', 

JET_coltypLongBinary : 'Long Binary', 

JET_coltypLongText : 'Long Text', 

JET_coltypSLV : 'Obsolete', 

JET_coltypUnsignedLong : 'Unsigned long', 

JET_coltypLongLong : 'Long long', 

JET_coltypGUID : 'GUID', 

JET_coltypUnsignedShort: 'Unsigned short', 

JET_coltypMax : 'Max', 

} 

 

ColumnTypeSize = { 

JET_coltypNil : None, 

JET_coltypBit : (1,'B'), 

JET_coltypUnsignedByte : (1,'B'), 

JET_coltypShort : (2,'<h'), 

JET_coltypLong : (4,'<l'), 

JET_coltypCurrency : (8,'<Q'), 

JET_coltypIEEESingle : (4,'<f'), 

JET_coltypIEEEDouble : (8,'<d'), 

JET_coltypDateTime : (8,'<Q'), 

JET_coltypBinary : None, 

JET_coltypText : None, 

JET_coltypLongBinary : None, 

JET_coltypLongText : None, 

JET_coltypSLV : None, 

JET_coltypUnsignedLong : (4,'<L'), 

JET_coltypLongLong : (8,'<Q'), 

JET_coltypGUID : (16,'16s'), 

JET_coltypUnsignedShort: (2,'<H'), 

JET_coltypMax : None, 

} 

 

# Tagged Data Type Flags 

TAGGED_DATA_TYPE_VARIABLE_SIZE = 1 

TAGGED_DATA_TYPE_COMPRESSED = 2 

TAGGED_DATA_TYPE_STORED = 4 

TAGGED_DATA_TYPE_MULTI_VALUE = 8 

TAGGED_DATA_TYPE_WHO_KNOWS = 10 

 

# Code pages 

CODEPAGE_UNICODE = 1200 

CODEPAGE_ASCII = 20127 

CODEPAGE_WESTERN = 1252 

 

StringCodePages = { 

CODEPAGE_UNICODE : 'utf-16le', 

CODEPAGE_ASCII : 'ascii', 

CODEPAGE_WESTERN : 'cp1252', 

} 

 

# Structures 

 

TABLE_CURSOR = { 

'TableData' : b'', 

'FatherDataPageNumber': 0, 

'CurrentPageData' : b'', 

'CurrentTag' : 0, 

} 

 

class ESENT_JET_SIGNATURE(Structure): 

structure = ( 

('Random','<L=0'), 

('CreationTime','<Q=0'), 

('NetBiosName','16s=b""'), 

) 

 

class ESENT_DB_HEADER(Structure): 

structure = ( 

('CheckSum','<L=0'), 

('Signature','"\xef\xcd\xab\x89'), 

('Version','<L=0'), 

('FileType','<L=0'), 

('DBTime','<Q=0'), 

('DBSignature',':',ESENT_JET_SIGNATURE), 

('DBState','<L=0'), 

('ConsistentPosition','<Q=0'), 

('ConsistentTime','<Q=0'), 

('AttachTime','<Q=0'), 

('AttachPosition','<Q=0'), 

('DetachTime','<Q=0'), 

('DetachPosition','<Q=0'), 

('LogSignature',':',ESENT_JET_SIGNATURE), 

('Unknown','<L=0'), 

('PreviousBackup','24s=b""'), 

('PreviousIncBackup','24s=b""'), 

('CurrentFullBackup','24s=b""'), 

('ShadowingDisables','<L=0'), 

('LastObjectID','<L=0'), 

('WindowsMajorVersion','<L=0'), 

('WindowsMinorVersion','<L=0'), 

('WindowsBuildNumber','<L=0'), 

('WindowsServicePackNumber','<L=0'), 

('FileFormatRevision','<L=0'), 

('PageSize','<L=0'), 

('RepairCount','<L=0'), 

('RepairTime','<Q=0'), 

('Unknown2','28s=b""'), 

('ScrubTime','<Q=0'), 

('RequiredLog','<Q=0'), 

('UpgradeExchangeFormat','<L=0'), 

('UpgradeFreePages','<L=0'), 

('UpgradeSpaceMapPages','<L=0'), 

('CurrentShadowBackup','24s=b""'), 

('CreationFileFormatVersion','<L=0'), 

('CreationFileFormatRevision','<L=0'), 

('Unknown3','16s=b""'), 

('OldRepairCount','<L=0'), 

('ECCCount','<L=0'), 

('LastECCTime','<Q=0'), 

('OldECCFixSuccessCount','<L=0'), 

('ECCFixErrorCount','<L=0'), 

('LastECCFixErrorTime','<Q=0'), 

('OldECCFixErrorCount','<L=0'), 

('BadCheckSumErrorCount','<L=0'), 

('LastBadCheckSumTime','<Q=0'), 

('OldCheckSumErrorCount','<L=0'), 

('CommittedLog','<L=0'), 

('PreviousShadowCopy','24s=b""'), 

('PreviousDifferentialBackup','24s=b""'), 

('Unknown4','40s=b""'), 

('NLSMajorVersion','<L=0'), 

('NLSMinorVersion','<L=0'), 

('Unknown5','148s=b""'), 

('UnknownFlags','<L=0'), 

) 

 

class ESENT_PAGE_HEADER(Structure): 

structure_2003_SP0 = ( 

('CheckSum','<L=0'), 

('PageNumber','<L=0'), 

) 

structure_0x620_0x0b = ( 

('CheckSum','<L=0'), 

('ECCCheckSum','<L=0'), 

) 

structure_win7 = ( 

('CheckSum','<Q=0'), 

) 

common = ( 

('LastModificationTime','<Q=0'), 

('PreviousPageNumber','<L=0'), 

('NextPageNumber','<L=0'), 

('FatherDataPage','<L=0'), 

('AvailableDataSize','<H=0'), 

('AvailableUncommittedDataSize','<H=0'), 

('FirstAvailableDataOffset','<H=0'), 

('FirstAvailablePageTag','<H=0'), 

('PageFlags','<L=0'), 

) 

extended_win7 = ( 

('ExtendedCheckSum1','<Q=0'), 

('ExtendedCheckSum2','<Q=0'), 

('ExtendedCheckSum3','<Q=0'), 

('PageNumber','<Q=0'), 

('Unknown','<Q=0'), 

) 

def __init__(self, version, revision, pageSize=8192, data=None): 

273 ↛ 275line 273 didn't jump to line 275, because the condition on line 273 was never true if (version < 0x620) or (version == 0x620 and revision < 0x0b): 

# For sure the old format 

self.structure = self.structure_2003_SP0 + self.common 

276 ↛ 278line 276 didn't jump to line 278, because the condition on line 276 was never true elif version == 0x620 and revision < 0x11: 

# Exchange 2003 SP1 and Windows Vista and later 

self.structure = self.structure_0x620_0x0b + self.common 

else: 

# Windows 7 and later 

self.structure = self.structure_win7 + self.common 

282 ↛ 283line 282 didn't jump to line 283, because the condition on line 282 was never true if pageSize > 8192: 

self.structure += self.extended_win7 

 

Structure.__init__(self,data) 

 

class ESENT_ROOT_HEADER(Structure): 

structure = ( 

('InitialNumberOfPages','<L=0'), 

('ParentFatherDataPage','<L=0'), 

('ExtentSpace','<L=0'), 

('SpaceTreePageNumber','<L=0'), 

) 

 

class ESENT_BRANCH_HEADER(Structure): 

structure = ( 

('CommonPageKey',':'), 

) 

 

class ESENT_BRANCH_ENTRY(Structure): 

common = ( 

('CommonPageKeySize','<H=0'), 

) 

structure = ( 

('LocalPageKeySize','<H=0'), 

('_LocalPageKey','_-LocalPageKey','self["LocalPageKeySize"]'), 

('LocalPageKey',':'), 

('ChildPageNumber','<L=0'), 

) 

def __init__(self, flags, data=None): 

if flags & TAG_COMMON > 0: 

# Include the common header 

self.structure = self.common + self.structure 

Structure.__init__(self,data) 

 

class ESENT_LEAF_HEADER(Structure): 

structure = ( 

('CommonPageKey',':'), 

) 

 

class ESENT_LEAF_ENTRY(Structure): 

common = ( 

('CommonPageKeySize','<H=0'), 

) 

structure = ( 

('LocalPageKeySize','<H=0'), 

('_LocalPageKey','_-LocalPageKey','self["LocalPageKeySize"]'), 

('LocalPageKey',':'), 

('EntryData',':'), 

) 

def __init__(self, flags, data=None): 

if flags & TAG_COMMON > 0: 

# Include the common header 

self.structure = self.common + self.structure 

Structure.__init__(self,data) 

 

class ESENT_SPACE_TREE_HEADER(Structure): 

structure = ( 

('Unknown','<Q=0'), 

) 

 

class ESENT_SPACE_TREE_ENTRY(Structure): 

structure = ( 

('PageKeySize','<H=0'), 

('LastPageNumber','<L=0'), 

('NumberOfPages','<L=0'), 

) 

 

class ESENT_INDEX_ENTRY(Structure): 

structure = ( 

('RecordPageKey',':'), 

) 

 

class ESENT_DATA_DEFINITION_HEADER(Structure): 

structure = ( 

('LastFixedSize','<B=0'), 

('LastVariableDataType','<B=0'), 

('VariableSizeOffset','<H=0'), 

) 

 

class ESENT_CATALOG_DATA_DEFINITION_ENTRY(Structure): 

fixed = ( 

('FatherDataPageID','<L=0'), 

('Type','<H=0'), 

('Identifier','<L=0'), 

) 

 

column_stuff = ( 

('ColumnType','<L=0'), 

('SpaceUsage','<L=0'), 

('ColumnFlags','<L=0'), 

('CodePage','<L=0'), 

) 

 

other = ( 

('FatherDataPageNumber','<L=0'), 

) 

 

table_stuff = ( 

('SpaceUsage','<L=0'), 

# ('TableFlags','<L=0'), 

# ('InitialNumberOfPages','<L=0'), 

) 

 

index_stuff = ( 

('SpaceUsage','<L=0'), 

('IndexFlags','<L=0'), 

('Locale','<L=0'), 

) 

 

lv_stuff = ( 

('SpaceUsage','<L=0'), 

# ('LVFlags','<L=0'), 

# ('InitialNumberOfPages','<L=0'), 

) 

common = ( 

# ('RootFlag','<B=0'), 

# ('RecordOffset','<H=0'), 

# ('LCMapFlags','<L=0'), 

# ('KeyMost','<H=0'), 

('Trailing',':'), 

) 

 

def __init__(self,data): 

# Depending on the type of data we'll end up building a different struct 

dataType = unpack('<H', data[4:][:2])[0] 

self.structure = self.fixed 

 

if dataType == CATALOG_TYPE_TABLE: 

self.structure += self.other + self.table_stuff 

elif dataType == CATALOG_TYPE_COLUMN: 

self.structure += self.column_stuff 

elif dataType == CATALOG_TYPE_INDEX: 

self.structure += self.other + self.index_stuff 

415 ↛ 417line 415 didn't jump to line 417, because the condition on line 415 was never false elif dataType == CATALOG_TYPE_LONG_VALUE: 

self.structure += self.other + self.lv_stuff 

elif dataType == CATALOG_TYPE_CALLBACK: 

raise Exception('CallBack types not supported!') 

else: 

LOG.error('Unknown catalog type 0x%x' % dataType) 

self.structure = () 

Structure.__init__(self,data) 

 

self.structure += self.common 

 

Structure.__init__(self,data) 

 

 

#def pretty_print(x): 

# if x in '0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&\'()*+,-./:;<=>?@[\\]^_`{|}~ ': 

# return x 

# else: 

# return '.' 

# 

#def hexdump(data): 

# x=str(data) 

# strLen = len(x) 

# i = 0 

# while i < strLen: 

# print "%04x " % i, 

# for j in range(16): 

# if i+j < strLen: 

# print "%02X" % ord(x[i+j]), 

# 

# else: 

# print " ", 

# if j%16 == 7: 

# print "", 

# print " ", 

# print ''.join(pretty_print(x) for x in x[i:i+16] ) 

# i += 16 

 

def getUnixTime(t): 

t -= 116444736000000000 

t //= 10000000 

return t 

 

class ESENT_PAGE: 

def __init__(self, db, data=None): 

self.__DBHeader = db 

self.data = data 

self.record = None 

463 ↛ exitline 463 didn't return from function '__init__', because the condition on line 463 was never false if data is not None: 

self.record = ESENT_PAGE_HEADER(self.__DBHeader['Version'], self.__DBHeader['FileFormatRevision'], self.__DBHeader['PageSize'], data) 

 

def printFlags(self): 

flags = self.record['PageFlags'] 

if flags & FLAGS_EMPTY: 

print("\tEmpty") 

if flags & FLAGS_INDEX: 

print("\tIndex") 

if flags & FLAGS_LEAF: 

print("\tLeaf") 

else: 

print("\tBranch") 

if flags & FLAGS_LONG_VALUE: 

print("\tLong Value") 

if flags & FLAGS_NEW_CHECKSUM: 

print("\tNew Checksum") 

if flags & FLAGS_NEW_FORMAT: 

print("\tNew Format") 

if flags & FLAGS_PARENT: 

print("\tParent") 

if flags & FLAGS_ROOT: 

print("\tRoot") 

if flags & FLAGS_SPACE_TREE: 

print("\tSpace Tree") 

 

def dump(self): 

baseOffset = len(self.record) 

self.record.dump() 

tags = self.data[-4*self.record['FirstAvailablePageTag']:] 

 

print("FLAGS: ") 

self.printFlags() 

 

print() 

 

for i in range(self.record['FirstAvailablePageTag']): 

tag = tags[-4:] 

if self.__DBHeader['Version'] == 0x620 and self.__DBHeader['FileFormatRevision'] > 11 and self.__DBHeader['PageSize'] > 8192: 

valueSize = unpack('<H', tag[:2])[0] & 0x7fff 

valueOffset = unpack('<H',tag[2:])[0] & 0x7fff 

hexdump((self.data[baseOffset+valueOffset:][:6])) 

pageFlags = ord(self.data[baseOffset+valueOffset:][1]) >> 5 

#print "TAG FLAG: 0x%x " % (unpack('<L', self.data[baseOffset+valueOffset:][:4]) ) >> 5 

#print "TAG FLAG: 0x " , ord(self.data[baseOffset+valueOffset:][0]) 

else: 

valueSize = unpack('<H', tag[:2])[0] & 0x1fff 

pageFlags = (unpack('<H', tag[2:])[0] & 0xe000) >> 13 

valueOffset = unpack('<H',tag[2:])[0] & 0x1fff 

 

print("TAG %-8d offset:0x%-6x flags:0x%-4x valueSize:0x%x" % (i,valueOffset,pageFlags,valueSize)) 

#hexdump(self.getTag(i)[1]) 

tags = tags[:-4] 

 

if self.record['PageFlags'] & FLAGS_ROOT > 0: 

rootHeader = ESENT_ROOT_HEADER(self.getTag(0)[1]) 

rootHeader.dump() 

elif self.record['PageFlags'] & FLAGS_LEAF == 0: 

# Branch Header 

flags, data = self.getTag(0) 

branchHeader = ESENT_BRANCH_HEADER(data) 

branchHeader.dump() 

else: 

# Leaf Header 

flags, data = self.getTag(0) 

if self.record['PageFlags'] & FLAGS_SPACE_TREE > 0: 

# Space Tree 

spaceTreeHeader = ESENT_SPACE_TREE_HEADER(data) 

spaceTreeHeader.dump() 

else: 

leafHeader = ESENT_LEAF_HEADER(data) 

leafHeader.dump() 

 

# Print the leaf/branch tags 

for tagNum in range(1,self.record['FirstAvailablePageTag']): 

flags, data = self.getTag(tagNum) 

if self.record['PageFlags'] & FLAGS_LEAF == 0: 

# Branch page 

branchEntry = ESENT_BRANCH_ENTRY(flags, data) 

branchEntry.dump() 

elif self.record['PageFlags'] & FLAGS_LEAF > 0: 

# Leaf page 

if self.record['PageFlags'] & FLAGS_SPACE_TREE > 0: 

# Space Tree 

spaceTreeEntry = ESENT_SPACE_TREE_ENTRY(data) 

#spaceTreeEntry.dump() 

 

elif self.record['PageFlags'] & FLAGS_INDEX > 0: 

# Index Entry 

indexEntry = ESENT_INDEX_ENTRY(data) 

#indexEntry.dump() 

elif self.record['PageFlags'] & FLAGS_LONG_VALUE > 0: 

# Long Page Value 

raise Exception('Long value still not supported') 

else: 

# Table Value 

leafEntry = ESENT_LEAF_ENTRY(flags, data) 

dataDefinitionHeader = ESENT_DATA_DEFINITION_HEADER(leafEntry['EntryData']) 

dataDefinitionHeader.dump() 

catalogEntry = ESENT_CATALOG_DATA_DEFINITION_ENTRY(leafEntry['EntryData'][len(dataDefinitionHeader):]) 

catalogEntry.dump() 

hexdump(leafEntry['EntryData']) 

 

def getTag(self, tagNum): 

567 ↛ 568line 567 didn't jump to line 568, because the condition on line 567 was never true if self.record['FirstAvailablePageTag'] < tagNum: 

raise Exception('Trying to grab an unknown tag 0x%x' % tagNum) 

 

tags = self.data[-4*self.record['FirstAvailablePageTag']:] 

baseOffset = len(self.record) 

for i in range(tagNum): 

tags = tags[:-4] 

 

tag = tags[-4:] 

 

577 ↛ 578line 577 didn't jump to line 578, because the condition on line 577 was never true if self.__DBHeader['Version'] == 0x620 and self.__DBHeader['FileFormatRevision'] >= 17 and self.__DBHeader['PageSize'] > 8192: 

valueSize = unpack('<H', tag[:2])[0] & 0x7fff 

valueOffset = unpack('<H',tag[2:])[0] & 0x7fff 

tmpData = list(self.data[baseOffset+valueOffset:][:valueSize]) 

pageFlags = ord(tmpData[1]) >> 5 

tmpData[1] = chr(ord(tmpData[1:2]) & 0x1f) 

tagData = "".join(tmpData) 

else: 

valueSize = unpack('<H', tag[:2])[0] & 0x1fff 

pageFlags = (unpack('<H', tag[2:])[0] & 0xe000) >> 13 

valueOffset = unpack('<H',tag[2:])[0] & 0x1fff 

tagData = self.data[baseOffset+valueOffset:][:valueSize] 

 

#return pageFlags, self.data[baseOffset+valueOffset:][:valueSize] 

return pageFlags, tagData 

 

class ESENT_DB: 

def __init__(self, fileName, pageSize = 8192, isRemote = False): 

self.__fileName = fileName 

self.__pageSize = pageSize 

self.__DB = None 

self.__DBHeader = None 

self.__totalPages = None 

self.__tables = OrderedDict() 

self.__currentTable = None 

self.__isRemote = isRemote 

self.mountDB() 

 

def mountDB(self): 

LOG.debug("Mounting DB...") 

607 ↛ 611line 607 didn't jump to line 611, because the condition on line 607 was never false if self.__isRemote is True: 

self.__DB = self.__fileName 

self.__DB.open() 

else: 

self.__DB = open(self.__fileName,"rb") 

mainHeader = self.getPage(-1) 

self.__DBHeader = ESENT_DB_HEADER(mainHeader) 

self.__pageSize = self.__DBHeader['PageSize'] 

self.__DB.seek(0,2) 

self.__totalPages = (self.__DB.tell() // self.__pageSize) -2 

LOG.debug("Database Version:0x%x, Revision:0x%x"% (self.__DBHeader['Version'], self.__DBHeader['FileFormatRevision'])) 

LOG.debug("Page Size: %d" % self.__pageSize) 

LOG.debug("Total Pages in file: %d" % self.__totalPages) 

self.parseCatalog(CATALOG_PAGE_NUMBER) 

 

def printCatalog(self): 

indent = ' ' 

 

print("Database version: 0x%x, 0x%x" % (self.__DBHeader['Version'], self.__DBHeader['FileFormatRevision'] )) 

print("Page size: %d " % self.__pageSize) 

print("Number of pages: %d" % self.__totalPages) 

print() 

print("Catalog for %s" % self.__fileName) 

for table in list(self.__tables.keys()): 

print("[%s]" % table.decode('utf8')) 

print("%sColumns " % indent) 

for column in list(self.__tables[table]['Columns'].keys()): 

record = self.__tables[table]['Columns'][column]['Record'] 

print("%s%-5d%-30s%s" % (indent*2, record['Identifier'], column.decode('utf-8'),ColumnTypeToName[record['ColumnType']])) 

print("%sIndexes"% indent) 

for index in list(self.__tables[table]['Indexes'].keys()): 

print("%s%s" % (indent*2, index.decode('utf-8'))) 

print("") 

 

def __addItem(self, entry): 

dataDefinitionHeader = ESENT_DATA_DEFINITION_HEADER(entry['EntryData']) 

catalogEntry = ESENT_CATALOG_DATA_DEFINITION_ENTRY(entry['EntryData'][len(dataDefinitionHeader):]) 

itemName = self.__parseItemName(entry) 

 

if catalogEntry['Type'] == CATALOG_TYPE_TABLE: 

self.__tables[itemName] = OrderedDict() 

self.__tables[itemName]['TableEntry'] = entry 

self.__tables[itemName]['Columns'] = OrderedDict() 

self.__tables[itemName]['Indexes'] = OrderedDict() 

self.__tables[itemName]['LongValues'] = OrderedDict() 

self.__currentTable = itemName 

elif catalogEntry['Type'] == CATALOG_TYPE_COLUMN: 

self.__tables[self.__currentTable]['Columns'][itemName] = entry 

self.__tables[self.__currentTable]['Columns'][itemName]['Header'] = dataDefinitionHeader 

self.__tables[self.__currentTable]['Columns'][itemName]['Record'] = catalogEntry 

elif catalogEntry['Type'] == CATALOG_TYPE_INDEX: 

self.__tables[self.__currentTable]['Indexes'][itemName] = entry 

659 ↛ 662line 659 didn't jump to line 662, because the condition on line 659 was never false elif catalogEntry['Type'] == CATALOG_TYPE_LONG_VALUE: 

self.__addLongValue(entry) 

else: 

raise Exception('Unknown type 0x%x' % catalogEntry['Type']) 

 

def __parseItemName(self,entry): 

dataDefinitionHeader = ESENT_DATA_DEFINITION_HEADER(entry['EntryData']) 

 

667 ↛ 670line 667 didn't jump to line 670, because the condition on line 667 was never false if dataDefinitionHeader['LastVariableDataType'] > 127: 

numEntries = dataDefinitionHeader['LastVariableDataType'] - 127 

else: 

numEntries = dataDefinitionHeader['LastVariableDataType'] 

 

itemLen = unpack('<H',entry['EntryData'][dataDefinitionHeader['VariableSizeOffset']:][:2])[0] 

itemName = entry['EntryData'][dataDefinitionHeader['VariableSizeOffset']:][2*numEntries:][:itemLen] 

return itemName 

 

def __addLongValue(self, entry): 

dataDefinitionHeader = ESENT_DATA_DEFINITION_HEADER(entry['EntryData']) 

lvLen = unpack('<H',entry['EntryData'][dataDefinitionHeader['VariableSizeOffset']:][:2])[0] 

lvName = entry['EntryData'][dataDefinitionHeader['VariableSizeOffset']:][7:][:lvLen] 

self.__tables[self.__currentTable]['LongValues'][lvName] = entry 

 

def parsePage(self, page): 

# Print the leaf/branch tags 

for tagNum in range(1,page.record['FirstAvailablePageTag']): 

flags, data = page.getTag(tagNum) 

if page.record['PageFlags'] & FLAGS_LEAF > 0: 

# Leaf page 

688 ↛ 689line 688 didn't jump to line 689, because the condition on line 688 was never true if page.record['PageFlags'] & FLAGS_SPACE_TREE > 0: 

pass 

690 ↛ 691line 690 didn't jump to line 691, because the condition on line 690 was never true elif page.record['PageFlags'] & FLAGS_INDEX > 0: 

pass 

692 ↛ 693line 692 didn't jump to line 693, because the condition on line 692 was never true elif page.record['PageFlags'] & FLAGS_LONG_VALUE > 0: 

pass 

else: 

# Table Value 

leafEntry = ESENT_LEAF_ENTRY(flags, data) 

self.__addItem(leafEntry) 

 

def parseCatalog(self, pageNum): 

# Parse all the pages starting at pageNum and commit table data 

page = self.getPage(pageNum) 

self.parsePage(page) 

 

for i in range(1, page.record['FirstAvailablePageTag']): 

flags, data = page.getTag(i) 

if page.record['PageFlags'] & FLAGS_LEAF == 0: 

# Branch page 

branchEntry = ESENT_BRANCH_ENTRY(flags, data) 

self.parseCatalog(branchEntry['ChildPageNumber']) 

 

 

def readHeader(self): 

LOG.debug("Reading Boot Sector for %s" % self.__volumeName) 

 

def getPage(self, pageNum): 

LOG.debug("Trying to fetch page %d (0x%x)" % (pageNum, (pageNum+1)*self.__pageSize)) 

self.__DB.seek((pageNum+1)*self.__pageSize, 0) 

data = self.__DB.read(self.__pageSize) 

719 ↛ 720line 719 didn't jump to line 720, because the condition on line 719 was never true while len(data) < self.__pageSize: 

remaining = self.__pageSize - len(data) 

data += self.__DB.read(remaining) 

# Special case for the first page 

if pageNum <= 0: 

return data 

else: 

return ESENT_PAGE(self.__DBHeader, data) 

 

def close(self): 

self.__DB.close() 

 

def openTable(self, tableName): 

# Returns a cursos for later use 

 

734 ↛ 737line 734 didn't jump to line 737, because the condition on line 734 was never false if isinstance(tableName, bytes) is not True: 

tableName = b(tableName) 

 

737 ↛ 768line 737 didn't jump to line 768, because the condition on line 737 was never false if tableName in self.__tables: 

entry = self.__tables[tableName]['TableEntry'] 

dataDefinitionHeader = ESENT_DATA_DEFINITION_HEADER(entry['EntryData']) 

catalogEntry = ESENT_CATALOG_DATA_DEFINITION_ENTRY(entry['EntryData'][len(dataDefinitionHeader):]) 

 

# Let's position the cursor at the leaf levels for fast reading 

pageNum = catalogEntry['FatherDataPageNumber'] 

done = False 

while done is False: 

page = self.getPage(pageNum) 

747 ↛ 749line 747 didn't jump to line 749, because the condition on line 747 was never true if page.record['FirstAvailablePageTag'] <= 1: 

# There are no records 

done = True 

750 ↛ 745line 750 didn't jump to line 745, because the loop on line 750 didn't complete for i in range(1, page.record['FirstAvailablePageTag']): 

flags, data = page.getTag(i) 

if page.record['PageFlags'] & FLAGS_LEAF == 0: 

# Branch page, move on to the next page 

branchEntry = ESENT_BRANCH_ENTRY(flags, data) 

pageNum = branchEntry['ChildPageNumber'] 

break 

else: 

done = True 

break 

 

cursor = TABLE_CURSOR 

cursor['TableData'] = self.__tables[tableName] 

cursor['FatherDataPageNumber'] = catalogEntry['FatherDataPageNumber'] 

cursor['CurrentPageData'] = page 

cursor['CurrentTag'] = 0 

return cursor 

else: 

return None 

 

def __getNextTag(self, cursor): 

page = cursor['CurrentPageData'] 

 

if cursor['CurrentTag'] >= page.record['FirstAvailablePageTag']: 

# No more data in this page, chau 

return None 

 

flags, data = page.getTag(cursor['CurrentTag']) 

778 ↛ 791line 778 didn't jump to line 791, because the condition on line 778 was never false if page.record['PageFlags'] & FLAGS_LEAF > 0: 

# Leaf page 

780 ↛ 781line 780 didn't jump to line 781, because the condition on line 780 was never true if page.record['PageFlags'] & FLAGS_SPACE_TREE > 0: 

raise Exception('FLAGS_SPACE_TREE > 0') 

782 ↛ 783line 782 didn't jump to line 783, because the condition on line 782 was never true elif page.record['PageFlags'] & FLAGS_INDEX > 0: 

raise Exception('FLAGS_INDEX > 0') 

784 ↛ 785line 784 didn't jump to line 785, because the condition on line 784 was never true elif page.record['PageFlags'] & FLAGS_LONG_VALUE > 0: 

raise Exception('FLAGS_LONG_VALUE > 0') 

else: 

# Table Value 

leafEntry = ESENT_LEAF_ENTRY(flags, data) 

return leafEntry 

 

return None 

 

def getNextRow(self, cursor): 

cursor['CurrentTag'] += 1 

 

tag = self.__getNextTag(cursor) 

#hexdump(tag) 

 

if tag is None: 

# No more tags in this page, search for the next one on the right 

page = cursor['CurrentPageData'] 

if page.record['NextPageNumber'] == 0: 

# No more pages, chau 

return None 

else: 

cursor['CurrentPageData'] = self.getPage(page.record['NextPageNumber']) 

cursor['CurrentTag'] = 0 

return self.getNextRow(cursor) 

else: 

return self.__tagToRecord(cursor, tag['EntryData']) 

 

def __tagToRecord(self, cursor, tag): 

# So my brain doesn't forget, the data record is composed of: 

# Header 

# Fixed Size Data (ID < 127) 

# The easiest to parse. Their size is fixed in the record. You can get its size 

# from the Column Record, field SpaceUsage 

# Variable Size Data (127 < ID < 255) 

# At VariableSizeOffset you get an array of two bytes per variable entry, pointing 

# to the length of the value. Values start at: 

# numEntries = LastVariableDataType - 127 

# VariableSizeOffset + numEntries * 2 (bytes) 

# Tagged Data ( > 255 ) 

# After the Variable Size Value, there's more data for the tagged values. 

# Right at the beginning there's another array (taggedItems), pointing to the 

# values, size. 

# 

# The interesting thing about this DB records is there's no need for all the columns to be there, hence 

# saving space. That's why I got over all the columns, and if I find data (of any type), i assign it. If  

# not, the column's empty. 

# 

# There are a lot of caveats in the code, so take your time to explore it.  

# 

# ToDo: Better complete this description 

# 

 

record = OrderedDict() 

taggedItems = OrderedDict() 

taggedItemsParsed = False 

 

dataDefinitionHeader = ESENT_DATA_DEFINITION_HEADER(tag) 

#dataDefinitionHeader.dump() 

variableDataBytesProcessed = (dataDefinitionHeader['LastVariableDataType'] - 127) * 2 

prevItemLen = 0 

tagLen = len(tag) 

fixedSizeOffset = len(dataDefinitionHeader) 

variableSizeOffset = dataDefinitionHeader['VariableSizeOffset'] 

 

columns = cursor['TableData']['Columns'] 

 

for column in list(columns.keys()): 

columnRecord = columns[column]['Record'] 

#columnRecord.dump() 

if columnRecord['Identifier'] <= dataDefinitionHeader['LastFixedSize']: 

# Fixed Size column data type, still available data 

record[column] = tag[fixedSizeOffset:][:columnRecord['SpaceUsage']] 

fixedSizeOffset += columnRecord['SpaceUsage'] 

 

859 ↛ 861line 859 didn't jump to line 861, because the condition on line 859 was never true elif 127 < columnRecord['Identifier'] <= dataDefinitionHeader['LastVariableDataType']: 

# Variable data type 

index = columnRecord['Identifier'] - 127 - 1 

itemLen = unpack('<H',tag[variableSizeOffset+index*2:][:2])[0] 

 

if itemLen & 0x8000: 

# Empty item 

itemLen = prevItemLen 

record[column] = None 

else: 

itemValue = tag[variableSizeOffset+variableDataBytesProcessed:][:itemLen-prevItemLen] 

record[column] = itemValue 

 

#if columnRecord['Identifier'] <= dataDefinitionHeader['LastVariableDataType']: 

variableDataBytesProcessed +=itemLen-prevItemLen 

 

prevItemLen = itemLen 

 

elif columnRecord['Identifier'] > 255: 

# Have we parsed the tagged items already? 

if taggedItemsParsed is False and (variableDataBytesProcessed+variableSizeOffset) < tagLen: 

index = variableDataBytesProcessed+variableSizeOffset 

#hexdump(tag[index:]) 

endOfVS = self.__pageSize 

firstOffsetTag = (unpack('<H', tag[index+2:][:2])[0] & 0x3fff) + variableDataBytesProcessed+variableSizeOffset 

while True: 

taggedIdentifier = unpack('<H', tag[index:][:2])[0] 

index += 2 

taggedOffset = (unpack('<H', tag[index:][:2])[0] & 0x3fff) 

# As of Windows 7 and later ( version 0x620 revision 0x11) the  

# tagged data type flags are always present 

890 ↛ 891line 890 didn't jump to line 891, because the condition on line 890 was never true if self.__DBHeader['Version'] == 0x620 and self.__DBHeader['FileFormatRevision'] >= 17 and self.__DBHeader['PageSize'] > 8192: 

flagsPresent = 1 

else: 

flagsPresent = (unpack('<H', tag[index:][:2])[0] & 0x4000) 

index += 2 

if taggedOffset < endOfVS: 

endOfVS = taggedOffset 

taggedItems[taggedIdentifier] = (taggedOffset, tagLen, flagsPresent) 

#print "ID: %d, Offset:%d, firstOffset:%d, index:%d, flag: 0x%x" % (taggedIdentifier, taggedOffset,firstOffsetTag,index, flagsPresent) 

if index >= firstOffsetTag: 

# We reached the end of the variable size array 

break 

 

# Calculate length of variable items 

# Ugly.. should be redone 

prevKey = list(taggedItems.keys())[0] 

for i in range(1,len(taggedItems)): 

offset0, length, flags = taggedItems[prevKey] 

offset, _, _ = list(taggedItems.items())[i][1] 

taggedItems[prevKey] = (offset0, offset-offset0, flags) 

#print "ID: %d, Offset: %d, Len: %d, flags: %d" % (prevKey, offset0, offset-offset0, flags) 

prevKey = list(taggedItems.keys())[i] 

taggedItemsParsed = True 

 

# Tagged data type 

if columnRecord['Identifier'] in taggedItems: 

offsetItem = variableDataBytesProcessed + variableSizeOffset + taggedItems[columnRecord['Identifier']][0] 

itemSize = taggedItems[columnRecord['Identifier']][1] 

# If item have flags, we should skip them 

if taggedItems[columnRecord['Identifier']][2] > 0: 

itemFlag = ord(tag[offsetItem:offsetItem+1]) 

offsetItem += 1 

itemSize -= 1 

else: 

itemFlag = 0 

 

#print "ID: %d, itemFlag: 0x%x" %( columnRecord['Identifier'], itemFlag) 

927 ↛ 928line 927 didn't jump to line 928, because the condition on line 927 was never true if itemFlag & (TAGGED_DATA_TYPE_COMPRESSED ): 

LOG.error('Unsupported tag column: %s, flag:0x%x' % (column, itemFlag)) 

record[column] = None 

elif itemFlag & TAGGED_DATA_TYPE_MULTI_VALUE: 

# ToDo: Parse multi-values properly 

LOG.debug('Multivalue detected in column %s, returning raw results' % (column)) 

record[column] = (hexlify(tag[offsetItem:][:itemSize]),) 

else: 

record[column] = tag[offsetItem:][:itemSize] 

 

else: 

record[column] = None 

else: 

record[column] = None 

 

# If we understand the data type, we unpack it and cast it accordingly 

# otherwise, we just encode it in hex 

if type(record[column]) is tuple: 

# A multi value data, we won't decode it, just leave it this way 

record[column] = record[column][0] 

elif columnRecord['ColumnType'] == JET_coltypText or columnRecord['ColumnType'] == JET_coltypLongText: 

# Let's handle strings 

if record[column] is not None: 

950 ↛ 951line 950 didn't jump to line 951, because the condition on line 950 was never true if columnRecord['CodePage'] not in StringCodePages: 

raise Exception('Unknown codepage 0x%x'% columnRecord['CodePage']) 

stringDecoder = StringCodePages[columnRecord['CodePage']] 

 

try: 

record[column] = record[column].decode(stringDecoder) 

except Exception: 

LOG.debug("Exception:", exc_info=True) 

LOG.debug('Fixing Record[%r][%d]: %r' % (column, columnRecord['ColumnType'], record[column])) 

record[column] = record[column].decode(stringDecoder, "replace") 

pass 

else: 

unpackData = ColumnTypeSize[columnRecord['ColumnType']] 

if record[column] is not None: 

if unpackData is None: 

record[column] = hexlify(record[column]) 

else: 

unpackStr = unpackData[1] 

record[column] = unpack(unpackStr, record[column])[0] 

 

return record