def mbox_lister(search_date, quarters_path, fail_object=None):
"""mbox_lister(datetime.date, quarters_path, fail_object) --> Set([string_1, ..., string_n])
Searches for mailboxes of a determined date received as argument.
Returns a set with the path of such mailboxes."""
# Verifies whether the type of the argument received is "date"
if not isinstance(search_date, date):
raise TypeError, "The argument \"search_date\" must be date typed;"
# Gets the quarter which the date received belongs to
quarter = datequarter(search_date) + 1
# Compiling a regular expression to match the quarter in the path
quarter_ex = compile(str(search_date.year)+"-Q"+str(quarter))
# Search for a path that holds the calculated quarter
for quarter_path in recursive_walk(quarters_path, maxdepth=0, dirs_only=True):
if search(quarter_ex, quarter_path):
break
else:
quarter_path = ""
# Once there's no path within the determined quarter, returns the fail_object
if quarter_path == "":
return fail_object
# Creates a list to store logfile paths
logfile_list = list()
# Search for logfiles produced in the received date
for logfile_path in recursive_walk(quarter_path, files_only=True):
if basename(logfile_path) == "logfile." + str(search_date):
logfile_list.append(logfile_path)
# Once there's no logfile path in the list, returns the fail_object
if len(logfile_list) == 0:
return fail_object
# Creates a set to store mailbox paths
mailbox_set = set()
# Reads the logfiles formerly found in search of mailboxes
for logfile_path in logfile_list:
mailbox_set |= logfile_mboxset(logfile_path)
return mailbox_set
def __init__(self, directory):
subject_mapping = {}
with open(configs.MAPPING_FILE) as mappping_file:
mappping_file = mappping_file.read().strip().split('\n')
for line in mappping_file:
id = re.findall(r'^(\d+)\s', line)[0]
name = line[len(id) + 1:]
subject_mapping[name] = id
def getSubject(name):
return int(subject_mapping[name])
#
self.dataset = SingleDataset()
subject_dirs = fileutils.listdir(directory)
ann = Annotation()
prev_subject_id = None
sjList = None
for dir in subject_dirs:
subject_name = fileutils.dirname(dir)
subject_id = getSubject(subject_name)
duplicate = None
for sj in self.dataset.subjects:
if sj.id == subject_id and sj.name == subject_name:
duplicate = sj
##
if duplicate == None:
subject = Subject(subject_id, subject_name)
else:
subject = duplicate
if prev_subject_id != subject_id:
sjList = ann.getSubjectList(subject_id)
prev_subject_id = subject_id
for file in fileutils.recursive_walk(dir):
if fileutils.fileextension(file) == configs.LAYER:
###
filename = fileutils.filename(file)
rc = Record()
rc.data = blob.load_np_array(file)
rc.label = int(Annotation.getClass(sjList, filename))
rc.frame = filename
subject.records.append(rc)
print('Loading', subject_id, filename, rc.label)
if(duplicate == None):
self.dataset.subjects.append(subject)
def rsync_done_opener(main_path):
"""rsync_done_opener(string) --> array(file_descriptor)
Receives an initial path to search for "rsync_done" files.
Yields an array with such paths.
Opens each path and returns an array with such opened files."""
# Creates a list to store "rsync_done" files descriptor
rsync_done_files = list()
for file_path in recursive_walk(main_path, files_only=True):
if basename(file_path) == RSYNC_PATTERN:
# Opens each file
try:
rsync_done_files.append(open(file_path, "r"))
except IOError:
print >> stderr, "Invalid argument - [" + path + "] is not an openable file."
continue
return rsync_done_files
