def test_SHA1_file():
filepath = path.join("tests", "testarchive.zip")
version = to_bytes(slackviewer.__version__)
def SHA1_file(filepath, extra=b''):
"""The original unoptimized method (reads whole file instead of chunks)"""
with io.open(filepath, 'rb') as f:
return hashlib.sha1(f.read() + extra).hexdigest()
expected = SHA1_file(filepath, version)
actual = archive.SHA1_file(filepath, version)
assert actual == expected
def extract_archive(filepath):
"""
Returns the path of the archive
:param str filepath: Path to file to extract or read
:return: path of the archive
:rtype: str
"""
# Checks if file path is a directory
if os.path.isdir(filepath):
path = os.path.abspath(filepath)
print("Archive already extracted. Viewing from {}...".format(path))
return path
# Checks if the filepath is a zipfile and continues to extract if it is
# if not it raises an error
elif not zipfile.is_zipfile(filepath):
# Misuse of TypeError? :P
raise TypeError("{} is not a zipfile".format(filepath))
archive_sha = SHA1_file(
filepath=filepath,
# Add version of slackviewer to hash as well so we can invalidate the cached copy
# if there are new features added
extra=to_bytes(slackviewer.__version__))
try:
extracted_path = os.path.join(os.getenv('SLACKVIEWER_TEMP_PATH'),
archive_sha)
except:
extracted_path = os.path.join(SLACKVIEWER_TEMP_PATH, archive_sha)
if os.path.exists(extracted_path):
print("{} already exists".format(extracted_path))
else:
# Extract zip
with zipfile.ZipFile(filepath) as zip:
print("{} extracting to {}...".format(filepath, extracted_path))
zip.extractall(path=extracted_path)
print("{} extracted to {}".format(filepath, extracted_path))
# Add additional file with archive info
create_archive_info(filepath, extracted_path, archive_sha)
return extracted_path
def extract_archive(filepath):
if os.path.isdir(filepath):
print("Archive already extracted. Viewing from {}...".format(filepath))
return filepath
if not zipfile.is_zipfile(filepath):
# Misuse of TypeError? :P
raise TypeError("{} is not a zipfile".format(filepath))
archive_sha = SHA1_file(
filepath=filepath,
# Add version of slackviewer to hash as well so we can invalidate the cached copy
# if there are new features added
extra=to_bytes(slackviewer.__version__))
extracted_path = os.path.join(SLACKVIEWER_TEMP_PATH, archive_sha)
if os.path.exists(extracted_path):
print("{} already exists".format(extracted_path))
else:
# Extract zip
with zipfile.ZipFile(filepath) as zip:
print("{} extracting to {}...".format(filepath, extracted_path))
zip.extractall(path=extracted_path)
print("{} extracted to {}.".format(filepath, extracted_path))
# Add additional file with archive info
archive_info = {
"sha1": archive_sha,
"filename": os.path.split(filepath)[1],
"empty_dms": remove_empty_dirs(extracted_path)
}
with io.open(os.path.join(
extracted_path,
".slackviewer_archive_info.json",
),
'w+',
encoding="utf-8") as f:
s = json.dumps(archive_info, ensure_ascii=False)
s = to_unicode(s)
f.write(s)
return extracted_path