Updates to support additional parsing of blink serialized objects (go…

…ogle#37)

* Initial  commit

* Pytype fix

* Updates

* Updates

* Updates

* Add more tests

* pylint/pytype fixes

* Add more tests

* Update docstring

* Updates

* Updates

* Updates

* Reformat test file

* Whitespace fix

dfindexeddb/indexeddb/chromium/definitions.py

@@ -141,10 +141,12 @@ class BlinkSerializationTag(IntEnum):
   ENCODED_AUDIO_CHUNK = ord('y')
   ENCODED_VIDEO_CHUNK = ord('z')
   CROP_TARGET = ord('c')
+  RESTRICTION_TARGET = ord('D')
   MEDIA_SOURCE_HANDLE = ord('S')
   DEPRECATED_DETECTED_BARCODE = ord('B')
   DEPRECATED_DETECTED_FACE = ord('F')
   DEPRECATED_DETECTED_TEXT = ord('t')
+  FENCED_FRAME_CONFIG = ord('C')
   DOM_EXCEPTION = ord('x')
   TRAILER_OFFSET = 0xFE
   VERSION = 0xFF
@@ -304,3 +306,67 @@ class V8ErrorTag(IntEnum):
   CAUSE = ord('c')
   STACK = ord('s')
   END = ord('.')
+
+
+class ImageSerializationTag(IntEnum):
+  """Image Serialization tags."""
+  END = 0
+  PREDEFINED_COLOR_SPACE = 1
+  CANVAS_PIXEL_FORMAT = 2
+  IMAGE_DATA_STORAGE_FORMAT = 3
+  ORIGIN_CLEAN = 4
+  IS_PREMULTIPLIED = 5
+  CANVAS_OPACITY_MODE = 6
+  PARAMETRIC_COLOR_SPACE = 7
+  IMAGE_ORIENTATION = 8
+  LAST = IMAGE_ORIENTATION
+
+
+class SerializedPredefinedColorSpace(IntEnum):
+  """Serialized Predefined Color Space enumeration."""
+  LEGACY_OBSOLETE = 0
+  SRGB = 1
+  REC2020 = 2
+  P3 = 3
+  REC2100HLG = 4
+  REC2100PQ = 5
+  SRGB_LINEAR = 6
+  LAST = SRGB_LINEAR
+
+
+class SerializedPixelFormat(IntEnum):
+  """Serialized Pixel Format enumeration."""
+  NATIVE8_LEGACY_OBSOLETE = 0
+  F16 = 1
+  RGBA8 = 2
+  BGRA8 = 3
+  RGBX8 = 4
+  LAST = RGBX8
+
+
+class SerializedImageDataStorageFormat(IntEnum):
+  """The Serialized Image Data Storage Format."""
+  UINT8CLAMPED = 0
+  UINT16 = 1
+  FLOAT32 = 2
+  LAST = FLOAT32
+
+
+class SerializedOpacityMode(IntEnum):
+  """The Serialized Opacity Mode."""
+  KNONOPAQUE = 0
+  KOPAQUE = 1
+  KLAST = KOPAQUE
+
+
+class SerializedImageOrientation(IntEnum):
+  """The Serialized Image Orientation."""
+  TOP_LEFT = 0
+  TOP_RIGHT = 1
+  BOTTOM_RIGHT = 2
+  BOTTOM_LEFT = 3
+  LEFT_TOP = 4
+  RIGHT_TOP = 5
+  RIGHT_BOTTOM = 6
+  LEFT_BOTTOM = 7
+  LAST = LEFT_BOTTOM

dfindexeddb/indexeddb/chromium/record.py

@@ -546,7 +546,7 @@ def FromDecoder(
 
 
 @dataclass
-class EarlistCompactionTimeKey(BaseIndexedDBKey):
+class EarliestCompactionTimeKey(BaseIndexedDBKey):
   """An earliest compaction time IndexedDB key."""
 
   def DecodeValue(self, decoder: utils.LevelDBDecoder) -> int:
@@ -558,11 +558,11 @@ def DecodeValue(self, decoder: utils.LevelDBDecoder) -> int:
   def FromDecoder(
       cls, decoder: utils.LevelDBDecoder, key_prefix: KeyPrefix,
       base_offset: int = 0
-  ) -> EarlistCompactionTimeKey:
+  ) -> EarliestCompactionTimeKey:
     """Decodes the earliest compaction time key."""
     offset, key_type = decoder.DecodeUint8()
     if key_type != definitions.GlobalMetadataKeyType.EARLIEST_COMPACTION_TIME:
-      raise errors.ParserError('Not a EarlistCompactionTimeKey')
+      raise errors.ParserError('Not a EarliestCompactionTimeKey')
     return cls(offset=base_offset + offset, key_prefix=key_prefix)
 
 
@@ -668,7 +668,7 @@ class GlobalMetaDataKey(BaseIndexedDBKey):
       definitions.GlobalMetadataKeyType
           .EARLIEST_SWEEP: EarliestSweepKey,
       definitions.GlobalMetadataKeyType
-          .EARLIEST_COMPACTION_TIME: EarlistCompactionTimeKey,
+          .EARLIEST_COMPACTION_TIME: EarliestCompactionTimeKey,
       definitions.GlobalMetadataKeyType
           .SCOPES_PREFIX: ScopesPrefixKey,
       definitions.GlobalMetadataKeyType
@@ -692,7 +692,7 @@ def FromDecoder(
              Type[DatabaseFreeListKey],
              Type[DatabaseNameKey],
              Type[EarliestSweepKey],
-             Type[EarlistCompactionTimeKey],
+             Type[EarliestCompactionTimeKey],
              Type[MaxDatabaseIdKey],
              Type[RecoveryBlobJournalKey],
              Type[SchemaVersionKey],
@@ -972,7 +972,7 @@ class ObjectStoreDataValue:
     blob_offset: the blob offset, only valid if wrapped.
     value: the blink serialized value, only valid if not wrapped.
   """
-  unkown: int
+  unknown: int
   is_wrapped: bool
   blob_size: Optional[int]
   blob_offset: Optional[int]
@@ -1003,15 +1003,15 @@ def DecodeValue(
       _, blob_size = decoder.DecodeVarint()
       _, blob_offset = decoder.DecodeVarint()
       return ObjectStoreDataValue(
-          unkown=unknown_integer,
+          unknown=unknown_integer,
           is_wrapped=True,
           blob_size=blob_size,
           blob_offset=blob_offset,
           value=None)
     _, blink_bytes = decoder.ReadBytes()
     blink_value = blink.V8ScriptValueDecoder.FromBytes(blink_bytes)
     return ObjectStoreDataValue(
-        unkown=unknown_integer,
+        unknown=unknown_integer,
         is_wrapped=False,
         blob_size=None,
         blob_offset=None,

dfindexeddb/indexeddb/chromium/v8.py

@@ -152,7 +152,12 @@ def _PeekTag(self) -> Optional[definitions.V8SerializationTag]:
       _, tag_value = self.decoder.PeekBytes(1)
     except errors.DecoderError:
       return None
-    return definitions.V8SerializationTag(tag_value[0])
+    try:
+      return definitions.V8SerializationTag(tag_value[0])
+    except ValueError as error:
+      raise errors.ParserError(
+          f'Invalid v8 tag value {tag_value} at offset'
+          f' {self.decoder.stream.tell()}') from error
 
   def _ReadTag(self) -> definitions.V8SerializationTag:
     """Returns the next non-padding serialization tag.
@@ -269,7 +274,7 @@ def _ReadObjectInternal(self) -> Tuple[definitions.V8SerializationTag, Any]:
             self.version >= 15):
       parsed_object = self.ReadSharedObject()
     elif self.version < 13:
-      self.decoder.stream.seek(-1)
+      self.decoder.stream.seek(-1, os.SEEK_CUR)
       parsed_object = self.ReadHostObject()
     else:
       parsed_object = None
@@ -492,7 +497,7 @@ def _ReadJSPrimitiveWrapper(
     return value
 
   def _ReadJSRegExp(self) -> RegExp:
-    """Reads a Javscript regular expression from the current position."""
+    """Reads a Javascript regular expression from the current position."""
     next_id = self._GetNextId()
     pattern = self.ReadString()
     _, flags = self.decoder.DecodeUint32Varint()  # TODO: verify flags

dfindexeddb/indexeddb/cli.py

@@ -15,6 +15,7 @@
 """A CLI tool for dfindexeddb."""
 import argparse
 import dataclasses
+import enum
 from datetime import datetime
 import json
 import pathlib
@@ -57,6 +58,8 @@ def default(self, o):
       return list(o)
     if isinstance(o, v8.RegExp):
       return str(o)
+    if isinstance(o, enum.Enum):
+      return o.name
     return json.JSONEncoder.default(self, o)
 
 
@@ -85,6 +88,7 @@ def IndexeddbCommand(args):
           (f'Error parsing blink value: {err} for {record.__class__.__name__} '
            f'at offset {record.offset} in {db_record.path}'), file=sys.stderr)
       print(f'Traceback: {traceback.format_exc()}', file=sys.stderr)
+      print(f'Record: {record}', file=sys.stderr)
     _Output(db_record, output=args.output)
 
 

tests/dfindexeddb/indexeddb/chromium/__init__.py

@@ -0,0 +1,14 @@
+# -*- 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.