Check for blob files files which are not referenced in XYF_BLOBS.STORAGE_FILENAME

unref.py

# Define file locations:
## dir C:\bb_content\storage\ /b /a /s > storage.txt
storageFileLoc = r"C:\Users\jfeocco\Downloads\dupage\storage.txt"
## select concat('C:/bb_content/storage', STORAGE_FILENAME) from XYF_BLOBS; -- COPY/PASTE INTO dbStorage.txt
dbStorageFileLoc = r"C:\Users\jfeocco\Downloads\dupage\dbStorage.txt"


# Open storage files
stor = open(storageFileLoc, encoding='utf8')
dbStor = open(dbStorageFileLoc, encoding='utf8')


# Create dicts
storList = {}
dbStorList = {}
unreferenced = {}


# Create dict of file locations
for line in stor:
	line = line.replace('\\', '/').replace('\n', '')
	# Get rid of non-file records, 8 is dependent on F:\blackboard\content location
	if line.count('/') == 8:
		storList[line] = 0
print('Length of storList: ', len(storList), '\nExample storList Value: ', repr(list(storList.keys())[0]))


# Create dict of STORAGE_FILENAME's
for line in dbStor:
	dbStorList[line.replace('\n', '')] = 0
print('Length of dbStorList: ', len(dbStorList), '\nExample dbStorList Value: ', repr(list(dbStorList.keys())[0]))


# Check records against eachother
for key in storList.keys():
	if key not in dbStorList:
		unreferenced[key] = 0
print('Length of unreferenced after remove\'s: ', len(unreferenced), '\nExample unreferenced Value: ', repr(list(unreferenced.keys())[0]))


# Open file to store results
results = open('results.txt', 'w')


# Write to file
for key in unreferenced.keys():
	results.write(key + '\n')