Skip to content

recurse into dirs same as into tarball #42

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
misha-at-genestack wants to merge 1 commit into
base: master
Choose a base branch
from
Open

recurse into dirs same as into tarball #42

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: 10 additions & 7 deletions poretools/Fast5File.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,21 +67,23 @@ def _extract_fast5_files(self):
f = self.fileset[0]
# is it a directory?
if os.path.isdir(f):
pattern = f + '/' + '*.fast5'
files = glob.glob(pattern)
files = []
for (dirpath, dirnames, names) in os.walk(f):
files += [os.path.join(dirpath, n) for n in names if self._fast5_filename_filter(n)]

self.files = iter(files)
self.num_files_in_set = len(files)
self.set_type = FAST5SET_DIRECTORY
if not len(files):
logger.warning("Directory is empty!")

# is it a tarball?
elif tarfile.is_tarfile(f):
elif os.path.isfile(f) and tarfile.is_tarfile(f):
if os.path.isdir(PORETOOLS_TMPDIR):
shutil.rmtree(PORETOOLS_TMPDIR)
os.mkdir(PORETOOLS_TMPDIR)

self.files = TarballFileIterator(f)
self.files = TarballFileIterator(f, self._fast5_filename_filter)
# set to None to delay initialisation
self.num_files_in_set = None
self.set_type = FAST5SET_TARBALL
Expand All @@ -95,13 +97,14 @@ def _extract_fast5_files(self):
logger.error("Directory %s could not be opened. Exiting.\n" % dir)
sys.exit()

class TarballFileIterator:
def _fast5_filename_filter(self, filename):
return os.path.basename(filename).endswith('.fast5') and not os.path.basename(filename).startswith('.')

def __init__(self, tarball):
class TarballFileIterator:
def __init__(self, tarball, filename_filter = None):
self._tarball = tarball
self._tarfile = tarfile.open(tarball)
self._filename_filter = filename_filter

def __del__(self):
self._tarfile.close()
Expand All @@ -114,7 +117,7 @@ def next(self):
tarinfo = self._tarfile.next()
if tarinfo is None:
raise StopIteration
elif self._fast5_filename_filter(tarinfo.name):
elif self._filename_filter is None or self._filename_filter(tarinfo.name):
break
self._tarfile.extract(tarinfo, path=PORETOOLS_TMPDIR)
return os.path.join(PORETOOLS_TMPDIR, tarinfo.name)
Expand Down