Skip to content

Avoid failing to scan very large files #371

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

Merged
merged 1 commit into from
Jan 9, 2025
Merged

Avoid failing to scan very large files #371

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
17 changes: 12 additions & 5 deletions mhkit/dolfyn/io/nortek2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,9 @@
from ..time import epoch2dt64, _fill_time_gaps


int32_max = np.iinfo(np.int32).max


def read_signature(
filename,
userdata=True,
Expand Down Expand Up @@ -163,7 +166,7 @@ def __init__(
debug=debug,
dp=dual_profile,
)
self._reopen(bufsize)
self._open(bufsize)
self.filehead_config = self._read_filehead_config_string()
self._ens_pos = self._index["pos"][
lib._boolarray_firstensemble_ping(self._index)
Expand All @@ -183,7 +186,7 @@ def _calc_lastblock_iswhole(
return (self._eof - self._ens_pos[-1]) == standard_blocksize

def _check_nortek(self, endian):
self._reopen(10)
self._open(10)
byts = self.f.read(2)
if endian is None:
if unpack("<" + "BB", byts) == (165, 10):
Expand All @@ -205,8 +208,12 @@ def find_all(s, c):
yield idx
idx = s.find(c, idx + 1)

# Open the entire file
self._reopen(self._eof)
# Open the entire file to find start header
if self._eof >= int32_max:
init_buffer = int32_max
else:
init_buffer = self._eof
self._open(init_buffer)
pk = self.f.peek(1)
# Search for multiple saved headers
found = [i for i in find_all(pk, b"GETCLOCKSTR")]
Expand All @@ -216,7 +223,7 @@ def find_all(s, c):
start_idx = found[-1] - 11
return start_idx

def _reopen(self, bufsize=None):
def _open(self, bufsize=None):
if bufsize is None:
bufsize = 1000000
try:
Expand Down
Loading