Skip to content

fix: allow UTF-16 surrogates to be passed through #93

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
dbushong wants to merge 2 commits into
base: master
Choose a base branch
from
Open

fix: allow UTF-16 surrogates to be passed through #93

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bc12fb8
fix: allow UTF-16 surrogates to be passed through
dbushong Sep 12, 2025
1d99746
fix: make error_handler configurable
dbushong Sep 15, 2025
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
14 changes: 10 additions & 4 deletions src/dnfile/stream.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -192,7 +192,13 @@ class UserString(HeapItemBinary, HeapItemString):

flag: Optional[int] = None

def __init__(self, data: Union[bytes, HeapItemBinary], rva: Optional[int] = None, encoding="utf-16"):
def __init__(
self,
data: Union[bytes, HeapItemBinary],
rva: Optional[int] = None,
encoding: str = "utf-16",
error_handler: str = "strict",
):
self.encoding = encoding
if isinstance(data, bytes):
HeapItemBinary.__init__(self, data, rva=rva)
Expand Down Expand Up @@ -234,7 +240,7 @@ def __init__(self, data: Union[bytes, HeapItemBinary], rva: Optional[int] = None
str_buf = buf

try:
self.value = str_buf.decode(encoding)
self.value = str_buf.decode(encoding, errors=error_handler)
except UnicodeDecodeError as e:
logger.warning(f"UserString decode error (rva:0x{self.rva:08x}): {e}")
self.value = None
Expand All @@ -257,12 +263,12 @@ def get_bytes(self, index) -> Optional[bytes]:

return item.value_bytes()

def get(self, index, encoding="utf-16") -> Optional[UserString]:
def get(self, index: int, encoding: str = "utf-16", error_handler: str = "strict") -> Optional[UserString]:
bin_item = super().get(index)
if bin_item is None:
return None

us_item = UserString(bin_item, encoding=encoding)
us_item = UserString(bin_item, encoding=encoding, error_handler=error_handler)

return us_item

Expand Down