dfindexeddb 20240417__py3-none-any.whl → 20240519__py3-none-any.whl

dfindexeddb/indexeddb/chromium/blink.py

@@ -780,6 +780,9 @@ class V8ScriptValueDecoder:
 
     Returns:
       A parsed CryptoKey.
+
+    Raises:
+      ParserError: if there is an unexpected CryptoKeySubTag.
     """
     _, raw_key_byte = self.deserializer.decoder.DecodeUint8()
     key_byte = definitions.CryptoKeySubTag(raw_key_byte)
@@ -795,6 +798,8 @@ class V8ScriptValueDecoder:
       key_type, algorithm_parameters = self._ReadED25519Key()
     elif key_byte == definitions.CryptoKeySubTag.NO_PARAMS_KEY:
       key_type, algorithm_parameters = self.ReadNoParamsKey()
+    else:
+      raise errors.ParserError('Unexpected CryptoKeySubTag')
 
     _, raw_usages = self.deserializer.decoder.DecodeUint32Varint()
     usages = definitions.CryptoKeyUsage(raw_usages)

dfindexeddb/indexeddb/chromium/record.py

@@ -17,7 +17,11 @@ from __future__ import annotations
 from dataclasses import dataclass, field
 from datetime import datetime
 import io
-from typing import Any, BinaryIO, Optional, Tuple, Type, TypeVar, Union
+import pathlib
+import sys
+import traceback
+from typing import Any, BinaryIO, Generator, Optional, Tuple, Type, TypeVar, \
+    Union
 
 from dfindexeddb import errors
 from dfindexeddb.indexeddb.chromium import blink
@@ -456,7 +460,7 @@ class MaxDatabaseIdKey(BaseIndexedDBKey):
       cls, decoder: utils.LevelDBDecoder, key_prefix: KeyPrefix,
       base_offset: int = 0
   ) -> MaxDatabaseIdKey:
-    """Decodes the maximum databse key."""
+    """Decodes the maximum database key."""
     offset, key_type = decoder.DecodeUint8()
     if key_type != definitions.GlobalMetadataKeyType.MAX_DATABASE_ID:
       raise errors.ParserError('Not a MaxDatabaseIdKey')
@@ -1271,14 +1275,17 @@ class ExternalObjectEntry(utils.FromDecoderMixin):
         filename = None
         last_modified = None
       token = None
-    elif (object_type ==
-        definitions.ExternalObjectType.FILE_SYSTEM_ACCESS_HANDLE):
+    else:
+      if (object_type ==
+          definitions.ExternalObjectType.FILE_SYSTEM_ACCESS_HANDLE):
+        _, token = decoder.DecodeBlobWithLength()
+      else:
+        token = None
       blob_number = None
       mime_type = None
       size = None
       filename = None
       last_modified = None
-      _, token = decoder.DecodeBlobWithLength()
 
     return cls(offset=base_offset + offset, object_type=object_type,
         blob_number=blob_number, mime_type=mime_type, size=size,
@@ -1331,12 +1338,14 @@ class IndexedDBRecord:
   """An IndexedDB Record.
 
   Attributes:
+    path: the source file path
     offset: the offset of the record.
     key: the key of the record.
     value: the value of the record.
     sequence_number: if available, the sequence number of the record.
     type: the type of the record.
-    level: the leveldb level, None indicates the record came from a log file.
+    level: the leveldb level, if applicable, None can indicate the record
+        originated from a log file or the level could not be determined.
     recovered: True if the record is a recovered record.
   """
   path: str
@@ -1350,7 +1359,8 @@ class IndexedDBRecord:
 
   @classmethod
   def FromLevelDBRecord(
-      cls, db_record: record.LevelDBRecord
+      cls,
+      db_record: record.LevelDBRecord
   ) -> IndexedDBRecord:
     """Returns an IndexedDBRecord from a ParsedInternalKey."""
     idb_key = IndexedDbKey.FromBytes(
@@ -1366,3 +1376,76 @@ class IndexedDBRecord:
         type=db_record.record.record_type,
         level=db_record.level,
         recovered=db_record.recovered)
+
+  @classmethod
+  def FromFile(
+      cls,
+      file_path: pathlib.Path
+  ) -> Generator[IndexedDBRecord, None, None]:
+    """Yields IndexedDBRecords from a file."""
+    for db_record in record.LevelDBRecord.FromFile(file_path):
+      try:
+        yield cls.FromLevelDBRecord(db_record)
+      except(
+          errors.ParserError,
+          errors.DecoderError,
+          NotImplementedError) as err:
+        print((
+            'Error parsing Indexeddb record: '
+            f'{err} at offset {db_record.record.offset} in '
+            f'{db_record.path}'),
+            file=sys.stderr)
+        print(f'Traceback: {traceback.format_exc()}', file=sys.stderr)
+
+
+class FolderReader:
+  """A IndexedDB folder reader for Chrome/Chromium.
+
+  Attributes:
+    foldername (str): the source LevelDB folder.
+  """
+
+  def __init__(self, foldername: pathlib.Path):
+    """Initializes the FileReader.
+
+    Args:
+      foldername: the source IndexedDB folder.
+
+    Raises:
+      ValueError: if foldername is None or not a directory.
+    """
+    if not foldername or not foldername.is_dir():
+      raise ValueError(f'{foldername} is None or not a directory')
+    self.foldername = foldername
+
+  def GetRecords(
+      self,
+      use_manifest: bool = False,
+      use_sequence_number: bool = False
+  ) -> Generator[IndexedDBRecord, None, None]:
+    """Yield LevelDBRecords.
+
+    Args:
+      use_manifest: True to use the current manifest in the folder as a means to
+          find the active file set.
+      use_sequence_number: True to use the sequence number to determine the
+    Yields:
+      IndexedDBRecord.
+    """
+    leveldb_folder_reader = record.FolderReader(self.foldername)
+    for leveldb_record in leveldb_folder_reader.GetRecords(
+        use_manifest=use_manifest,
+        use_sequence_number=use_sequence_number):
+      try:
+        yield IndexedDBRecord.FromLevelDBRecord(
+            leveldb_record)
+      except(
+          errors.ParserError,
+          errors.DecoderError,
+          NotImplementedError) as err:
+        print((
+            'Error parsing Indexeddb record: '
+            f'{err} at offset {leveldb_record.record.offset} in '
+            f'{leveldb_record.path}'),
+            file=sys.stderr)
+        print(f'Traceback: {traceback.format_exc()}', file=sys.stderr)

dfindexeddb/indexeddb/cli.py

@@ -19,14 +19,13 @@ import enum
 from datetime import datetime
 import json
 import pathlib
-import sys
-import traceback
 
-from dfindexeddb import errors
+from dfindexeddb import utils
 from dfindexeddb import version
-from dfindexeddb.leveldb import record as leveldb_record
+from dfindexeddb.indexeddb.chromium import blink
 from dfindexeddb.indexeddb.chromium import record as chromium_record
 from dfindexeddb.indexeddb.chromium import v8
+from dfindexeddb.indexeddb.safari import record as safari_record
 
 
 _VALID_PRINTABLE_CHARACTERS = (
@@ -38,7 +37,7 @@ class Encoder(json.JSONEncoder):
   """A JSON encoder class for dfindexeddb fields."""
   def default(self, o):
     if dataclasses.is_dataclass(o):
-      o_dict = dataclasses.asdict(o)
+      o_dict = utils.asdict(o)
       return o_dict
     if isinstance(o, bytes):
       out = []
@@ -73,98 +72,92 @@ def _Output(structure, output):
     print(structure)
 
 
+def BlinkCommand(args):
+  """The CLI for processing a file as a blink value."""
+  with open(args.source, 'rb') as fd:
+    buffer = fd.read()
+    blink_value = blink.V8ScriptValueDecoder.FromBytes(buffer)
+    _Output(blink_value, output=args.output)
+
+
 def DbCommand(args):
-  """The CLI for processing a directory as indexeddb."""
-  if args.use_manifest:
-    for db_record in leveldb_record.LevelDBRecord.FromManifest(args.source):
-      record = db_record.record
-      try:
-        idb_record = chromium_record.IndexedDBRecord.FromLevelDBRecord(
-            db_record)
-      except(
-          errors.ParserError,
-          errors.DecoderError,
-          NotImplementedError) as err:
-        print((
-            f'Error parsing Indexeddb record {record.__class__.__name__}: {err}'
-            f' at offset {record.offset} in {db_record.path}'), file=sys.stderr)
-        print(f'Traceback: {traceback.format_exc()}', file=sys.stderr)
-        continue
-      _Output(idb_record, output=args.output)
-  else:
-    for db_record in leveldb_record.LevelDBRecord.FromDir(args.source):
-      record = db_record.record
-      try:
-        idb_record = chromium_record.IndexedDBRecord.FromLevelDBRecord(
-            db_record)
-      except(
-          errors.ParserError,
-          errors.DecoderError,
-          NotImplementedError) as err:
-        print((
-            f'Error parsing Indexeddb record {record.__class__.__name__}: {err}'
-            f' at offset {record.offset} in {db_record.path}'), file=sys.stderr)
-        print(f'Traceback: {traceback.format_exc()}', file=sys.stderr)
-        continue
-      _Output(idb_record, output=args.output)
+  """The CLI for processing a directory as IndexedDB."""
+  if args.format in ('chrome', 'chromium'):
+    for db_record in chromium_record.FolderReader(
+        args.source).GetRecords(
+            use_manifest=args.use_manifest,
+            use_sequence_number=args.use_sequence_number):
+      _Output(db_record, output=args.output)
+  elif args.format == 'safari':
+    for db_record in safari_record.FileReader(args.source).Records():
+      _Output(db_record, output=args.output)
 
 
 def LdbCommand(args):
-  """The CLI for processing a leveldb table (.ldb) file as indexeddb."""
-  for db_record in leveldb_record.LevelDBRecord.FromFile(args.source):
-    record = db_record.record
-    try:
-      idb_record = chromium_record.IndexedDBRecord.FromLevelDBRecord(
-          db_record)
-    except(
-        errors.ParserError,
-        errors.DecoderError,
-        NotImplementedError) as err:
-      print(
-          (f'Error parsing Indexeddb record {record.__class__.__name__}: {err} '
-           f'at offset {record.offset} in {db_record.path}'), file=sys.stderr)
-      print(f'Traceback: {traceback.format_exc()}', file=sys.stderr)
-      continue
-    _Output(idb_record, output=args.output)
+  """The CLI for processing a LevelDB table (.ldb) file as IndexedDB."""
+  for db_record in chromium_record.IndexedDBRecord.FromFile(args.source):
+    _Output(db_record, output=args.output)
 
 
 def LogCommand(args):
-  """The CLI for processing a leveldb log file as indexeddb."""
-  for db_record in leveldb_record.LevelDBRecord.FromFile(args.source):
-    record = db_record.record
-    try:
-      idb_record = chromium_record.IndexedDBRecord.FromLevelDBRecord(
-          db_record)
-    except(
-        errors.ParserError,
-        errors.DecoderError,
-        NotImplementedError) as err:
-      print(
-          (f'Error parsing Indexeddb record {record.__class__.__name__}: {err} '
-           f'at offset {record.offset} in {db_record.path}'), file=sys.stderr)
-      print(f'Traceback: {traceback.format_exc()}', file=sys.stderr)
-      continue
-    _Output(idb_record, output=args.output)
+  """The CLI for processing a LevelDB log file as IndexedDB."""
+  for db_record in chromium_record.IndexedDBRecord.FromFile(args.source):
+    _Output(db_record, output=args.output)
 
 
 def App():
   """The CLI app entrypoint for dfindexeddb."""
   parser = argparse.ArgumentParser(
       prog='dfindexeddb',
-      description='A cli tool for parsing indexeddb files',
+      description='A cli tool for parsing IndexedDB files',
       epilog=f'Version {version.GetVersion()}')
 
   subparsers = parser.add_subparsers()
 
+  parser_blink = subparsers.add_parser(
+      'blink', help='Parse a file as a blink value.')
+  parser_blink.add_argument(
+      '-s', '--source',
+      required=True,
+      type=pathlib.Path,
+      help=(
+        'The source file.'))
+  parser_blink.add_argument(
+      '-o',
+      '--output',
+      choices=[
+          'json',
+          'jsonl',
+          'repr'],
+      default='json',
+      help='Output format.  Default is json')
+  parser_blink.set_defaults(func=BlinkCommand)
+
   parser_db = subparsers.add_parser(
-      'db', help='Parse a directory as indexeddb.')
-  parser_db.add_argument(
-      '-s', '--source', required=True, type=pathlib.Path,
-      help='The source leveldb folder')
+      'db', help='Parse a directory as IndexedDB.')
   parser_db.add_argument(
+      '-s', '--source',
+      required=True,
+      type=pathlib.Path,
+      help=(
+        'The source IndexedDB folder (for chrome/chromium) '
+        'or file (for safari).'))
+  recover_group = parser_db.add_mutually_exclusive_group()
+  recover_group.add_argument(
       '--use_manifest',
       action='store_true',
       help='Use manifest file to determine active/deleted records.')
+  recover_group.add_argument(
+      '--use_sequence_number',
+      action='store_true',
+      help=(
+          'Use sequence number and file offset to determine active/deleted '
+          'records.'))
+  parser_db.add_argument(
+      '--format',
+      required=True,
+      choices=['chromium', 'chrome', 'safari'],
+      help='The type of IndexedDB to parse.')
   parser_db.add_argument(
       '-o',
       '--output',
@@ -177,9 +170,12 @@ def App():
   parser_db.set_defaults(func=DbCommand)
 
   parser_ldb = subparsers.add_parser(
-      'ldb', help='Parse a ldb file as indexeddb.')
+      'ldb',
+      help='Parse a ldb file as IndexedDB.')
   parser_ldb.add_argument(
-      '-s', '--source', required=True, type=pathlib.Path,
+      '-s', '--source',
+      required=True,
+      type=pathlib.Path,
       help='The source .ldb file.')
   parser_ldb.add_argument(
       '-o',
@@ -193,9 +189,12 @@ def App():
   parser_ldb.set_defaults(func=LdbCommand)
 
   parser_log = subparsers.add_parser(
-      'log', help='Parse a log file as indexeddb.')
+      'log',
+      help='Parse a log file as IndexedDB.')
   parser_log.add_argument(
-      '-s', '--source', required=True, type=pathlib.Path,
+      '-s', '--source',
+      required=True,
+      type=pathlib.Path,
       help='The source .log file.')
   parser_log.add_argument(
       '-o',
@@ -209,4 +208,7 @@ def App():
   parser_log.set_defaults(func=LogCommand)
 
   args = parser.parse_args()
-  args.func(args)
+  if hasattr(args, 'func'):
+    args.func(args)
+  else:
+    parser.print_help()

dfindexeddb/indexeddb/safari/definitions.py

@@ -0,0 +1,123 @@
+# -*- coding: utf-8 -*-
+# Copyright 2024 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Definitions for Webkit/Safari."""
+from enum import IntEnum
+
+
+CurrentVersion = 0x0000000F  # 15
+TerminatorTag = 0xFFFFFFFF
+StringPoolTag = 0xFFFFFFFE
+NonIndexPropertiesTag = 0xFFFFFFFD
+ImageDataPoolTag = 0xFFFFFFFE
+StringDataIs8BitFlag = 0x80000000
+
+
+SIDBKeyVersion = 0x00
+
+
+class SIDBKeyType(IntEnum):
+  """SIDBKeyType."""
+  MIN = 0x00
+  NUMBER = 0x20
+  DATE = 0x40
+  STRING = 0x60
+  BINARY = 0x80
+  ARRAY = 0xA0
+  MAX = 0xFF
+
+
+class SerializationTag(IntEnum):
+  """Database Metadata key types.  
+  
+  All tags are recorded as a single uint8_t.
+  """
+  ARRAY = 1
+  OBJECT = 2
+  UNDEFINED = 3
+  NULL = 4
+  INT = 5
+  ZERO = 6
+  ONE = 7
+  FALSE = 8
+  TRUE = 9
+  DOUBLE = 10
+  DATE = 11
+  FILE = 12
+  FILE_LIST = 13
+  IMAGE_DATA = 14
+  BLOB = 15
+  STRING = 16
+  EMPTY_STRING = 17
+  REG_EXP = 18
+  OBJECT_REFERENCE = 19
+  MESSAGE_PORT_REFERENCE = 20
+  ARRAY_BUFFER = 21
+  ARRAY_BUFFER_VIEW = 22
+  ARRAY_BUFFER_TRANSFER = 23
+  TRUE_OBJECT = 24
+  FALSE_OBJECT = 25
+  STRING_OBJECT = 26
+  EMPTY_STRING_OBJECT = 27
+  NUMBER_OBJECT = 28
+  SET_OBJECT = 29
+  MAP_OBJECT = 30
+  NON_MAP_PROPERTIES = 31
+  NON_SET_PROPERTIES = 32
+  CRYPTO_KEY = 33
+  SHARED_ARRAY_BUFFER = 34
+  WASM_MODULE = 35
+  DOM_POINT_READONLY = 36
+  DOM_POINT = 37
+  DOM_RECT_READONLY = 38
+  DOM_RECT = 39
+  DOM_MATRIX_READONLY = 40
+  DOM_MATRIX = 41
+  DOM_QUAD = 42
+  IMAGE_BITMAP_TRANSFER = 43
+  RTC_CERTIFICATE = 44
+  IMAGE_BITMAP = 45
+  OFF_SCREEN_CANVAS_TRANSFER = 46
+  BIGINT = 47
+  BIGINT_OBJECT = 48
+  WASM_MEMORY = 49
+  RTC_DATA_CHANNEL_TRANSFER = 50
+  DOM_EXCEPTION = 51
+  WEB_CODECS_ENCODED_VIDEO_CHUNK = 52
+  WEB_CODECS_VIDEO_FRAME = 53
+  RESIZABLE_ARRAY_BUFFER = 54
+  ERROR_INSTANCE = 55
+  IN_MEMORY_OFFSCREEN_CANVAS = 56
+  IN_MEMORY_MESSAGE_PORT = 57
+  WEB_CODECS_ENCODED_AUDIO_CHUNK = 58
+  WEB_CODECS_AUDIO_DATA = 59
+  MEDIA_STREAM_TRACK = 60
+  MEDIA_SOURCE_HANDLE_TRANSFER = 61
+  ERROR = 255
+
+
+class ArrayBufferViewSubtag(IntEnum):
+  """ArrayBufferView sub tags."""
+  DATA_VIEW = 0
+  INT8_ARRAY = 1
+  UINT8_ARRAY = 2
+  UINT8_CLAMPED_ARRAY = 3
+  INT16_ARRAY = 4
+  UINT16_ARRAY = 5
+  INT32_ARRAY = 6
+  UINT32_ARRAY = 7
+  FLOAT32_ARRAY = 8
+  FLOAT64_ARRAY = 9
+  BIG_INT64_ARRAY = 10
+  BIG_UINT64_ARRAY = 11