def id2path(id):
clean_id = id_encode(id)
path = []
while len(clean_id) > 0:
val, clean_id = clean_id[:2], clean_id[2:]
path.append(val)
return '/'.join(path)
def set_version_date(self, version, date):
if version in self.manifest['versions']:
self.manifest['version_dates'][version] = date
self.po.add_bytestream_by_path(os.path.join("__"+str(version), "3=%s" % id_encode(date)), date)
return True
else:
logger.error("Version %s does not exist" % version)
return False
def _setup_version_dir(self, version, date=None):
if not date:
if self.manifest['date']:
date = self.manifest['date']
else:
date = datetime.now().isoformat()
if version not in self.manifest['versions']:
self.manifest['versions'].append(version)
self.manifest['version_dates'][version] = date
self.manifest['subdir'][version] = []
self.manifest['metadata_files'][version] = []
self.manifest['files'][version] = []
self.manifest['versionlog'][version] = []
self.set_version_date(version, date)
self.po.add_bytestream_by_path(os.path.join("__"+str(version), "4=%s" % id_encode(self.item_id)), self.item_id)
def id_to_rsync(htid, **kwargs):
'''
Take an HTRC id and convert it to an Rsync location for syncing Extracted
Features
'''
if 'kind' in kwargs:
logging.warn("The basic/advanced split with extracted features files "
"was removed in schema version 3.0. This function only "
"supports the current format for Rsync URLs, if you "
"would like to see the legacy 2.0 format, see Github: "
"https://github.com/htrc/htrc-feature-reader/blob/3e100ae"
"9ea45317443ae05f43a188b12afe2e69a/htrc_features/utils.py"
)
libid, volid = htid.split('.', 1)
volid_clean = id_encode(volid)
filename = '.'.join([libid, volid_clean, 'json.bz2'])
path = '/'.join([libid, 'pairtree_root', id2path(volid).replace('\\', '/'),
volid_clean, filename])
return path
def encode(self, identifier):
"""Pairtree encode identifier."""
return id_encode(identifier)
