root/software/similar images/build_index.py @ 864b608c
| e28ae23a | dsorber | #!/opt/local/bin/python2.7
|
|
import bz2
|
|||
import cPickle
|
|||
import imghdr
|
|||
import os
|
|||
import sys
|
|||
import pHash
|
|||
from image import Image
|
|||
# Build index
|
|||
# TODO: write more schtuff here
|
|||
def main():
|
|||
image_list = []
|
|||
# Make sure at least one command line argument was provided
|
|||
if len(sys.argv) < 2:
|
|||
print 'Usage: build_index.py <path>'
|
|||
return -1;
|
|||
# Print out the path we're walking
|
|||
path = sys.argv[1]
|
|||
print 'Building image index from path: {:s}\n'.format(path)
|
|||
# Walk the root path and count all images
|
|||
img_counter = 0
|
|||
for root, dirs, files in os.walk(path):
|
|||
for file in files:
|
|||
img_path = os.path.join(root, file)
|
|||
# Check the make sure the file is a JPEG
|
|||
if not imghdr.what(img_path) == 'jpeg':
|
|||
continue
|
|||
img_counter += 1
|
|||
print 'Done counting, {:d} images total.'.format(img_counter)
|
|||
# Walk the root path
|
|||
ctr = 0
|
|||
for root, dirs, files in os.walk(path):
|
|||
for file in files:
|
|||
img_path = os.path.join(root, file)
|
|||
# Check the make sure the file is a JPEG
|
|||
if not imghdr.what(img_path) == 'jpeg':
|
|||
continue
|
|||
ctr += 1
|
|||
percent_done = int((float(ctr) / img_counter) * 100)
|
|||
print '{:3d}% -- {:s}'.format(percent_done, img_path)
|
|||
img_obj = Image(img_path)
|
|||
# print '{:s} -> {:016X}'.format(img_path, img_obj.hash)
|
|||
image_list.append(img_obj)
|
|||
# Write index as a bzip2'd file to save space
|
|||
index_file = bz2.BZ2File('images_index.bz2', 'w')
|
|||
cPickle.dump(image_list, index_file)
|
|||
index_file.close()
|
|||
print '\nIndex file images_index.bz2 created. Done.'
|
|||
if __name__ == '__main__':
|
|||
sys.exit(main())
|