Skip to content

Fix three bugs that silently drop or crash on page text extraction #29

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
jrzmurray wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix three bugs that silently drop or crash on page text extraction #29

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
41 changes: 37 additions & 4 deletions pyOneNote/FileNode.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,10 +143,27 @@ def __init__(self, file, document):
file.seek(self.data.ref.stp)
self.propertySet = ObjectSpaceObjectPropSet(file, document)
file.seek(current_offset)
elif self.file_node_header.file_node_type == "ObjectDeclaration2LargeRefCountFND":
self.data = ObjectDeclaration2LargeRefCountFND(file, self.document, self.file_node_header)
current_offset = file.tell()
if self.data.body.jcid.IsPropertySet:
file.seek(self.data.ref.stp)
self.propertySet = ObjectSpaceObjectPropSet(file, document)
file.seek(current_offset)
elif self.file_node_header.file_node_type == "ReadOnlyObjectDeclaration2LargeRefCountFND":
self.data = ReadOnlyObjectDeclaration2LargeRefCountFND(file, self.document, self.file_node_header)
current_offset = file.tell()
if self.data.base.body.jcid.IsPropertySet:
file.seek(self.data.base.ref.stp)
self.propertySet = ObjectSpaceObjectPropSet(file, document)
file.seek(current_offset)
elif self.file_node_header.file_node_type == "ReadOnlyObjectDeclaration2RefCountFND":
self.data = ReadOnlyObjectDeclaration2RefCountFND(file, self.document, self.file_node_header)
current_offset = file.tell()
if self.data.base.body.jcid.IsPropertySet:
file.seek(self.data.base.ref.stp)
self.propertySet = ObjectSpaceObjectPropSet(file, document)
file.seek(current_offset)
elif self.file_node_header.file_node_type == "FileDataStoreListReferenceFND":
self.data = FileDataStoreListReferenceFND(file, self.file_node_header)
elif self.file_node_header.file_node_type == "FileDataStoreObjectReferenceFND":
Expand Down Expand Up @@ -174,10 +191,10 @@ def __init__(self, file, document):
# no data part
self.data = None
else:
p = 1
self.data = None

current_offset = file.tell()
if self.file_node_header.baseType == 2:
if self.file_node_header.baseType == 2 and self.data is not None:
self.children.append(FileNodeList(file, self.document, self.data.ref))
file.seek(current_offset)

Expand Down Expand Up @@ -638,9 +655,19 @@ def __init__(self, file, OIDs, OSIDs, ContextIDs, document):
count, = struct.unpack('<I', file.read(4))
self.rgData.append(self.get_compact_ids(ContextIDs, count))
elif type == 0x10:
raise NotImplementedError('ArrayOfPropertyValues is not implement')
# prtArrayOfPropertyValues ([MS-ONESTORE] 2.6.9): cProperties
# (4 bytes), then if cProperties > 0 a prid PropertyID
# (4 bytes, always type 0x11/PropertySet) followed by that
# many nested PropertySet structures.
count, = struct.unpack('<I', file.read(4))
array_data = []
if count > 0:
PropertyID(file) # prid header, type is always 0x11 here
for _ in range(count):
array_data.append(PropertySet(file, OIDs, OSIDs, ContextIDs, document))
self.rgData.append(array_data)
elif type == 0x11:
self.rgData.append(PropertySet(file))
self.rgData.append(PropertySet(file, OIDs, OSIDs, ContextIDs, document))
else:
raise ValueError('rgPrids[i].type is not valid')

Expand All @@ -664,6 +691,12 @@ def get_properties(self):
if isinstance(self.rgData[i], PrtFourBytesOfLengthFollowedByData):
if 'guid' in propertyName.lower():
propertyVal = uuid.UUID(bytes_le=self.rgData[i].Data).hex
elif propertyName == 'TextExtendedAscii':
# OneNote for Mac stores plain-text runs as single-byte
# (latin-1) text under this property, instead of the
# UTF-16 RichEditTextUnicode Windows OneNote uses.
# Decoding it as utf-16 either garbles it or throws.
propertyVal = self.rgData[i].Data.decode('latin-1')
else:
try:
propertyVal = self.rgData[i].Data.decode('utf-16')
Expand Down
17 changes: 15 additions & 2 deletions pyOneNote/OneDocument.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,15 +24,28 @@ def get_properties(self):
if self._properties:
return self._properties
nodes = []
filters = ['ObjectDeclaration2RefCountFND']
# ObjectDeclaration2LargeRefCountFND is used for objects whose
# reference count doesn't fit in one byte (e.g. more heavily-shared
# or larger page content), and the ReadOnly* variants wrap either
# declaration with an extra md5Hash. All four carry the same
# propertySet-bearing body and were previously excluded here, which
# silently dropped any text stored under them.
filters = [
'ObjectDeclaration2RefCountFND',
'ObjectDeclaration2LargeRefCountFND',
'ReadOnlyObjectDeclaration2RefCountFND',
'ReadOnlyObjectDeclaration2LargeRefCountFND',
]

self._properties = []

OneDocment.traverse_nodes(self.root_file_node_list, nodes, filters)
for node in nodes:
if hasattr(node, 'propertySet'):
node.propertySet.body.indent= '\t\t'
self._properties.append({'type': str(node.data.body.jcid), 'identity':str(node.data.body.oid), 'val':node.propertySet.body.get_properties()})
# ReadOnly* variants wrap the declaration in `.base`.
decl_body = node.data.base.body if hasattr(node.data, 'base') else node.data.body
self._properties.append({'type': str(decl_body.jcid), 'identity':str(decl_body.oid), 'val':node.propertySet.body.get_properties()})

return self._properties

Expand Down