.

1 files changed, 90 insertions, 0 deletions

diff --git a/megapixels/commands/datasets/sha256.py b/megapixels/commands/datasets/sha256.py
new file mode 100644
index 00000000..c04fb504
--- /dev/null
+++ b/megapixels/commands/datasets/sha256.py
@@ -0,0 +1,90 @@
+import click
+
+from app.settings import types
+from app.utils import click_utils
+from app.settings import app_cfg as cfg
+from app.utils.logger_utils import Logger
+
+log = Logger.getLogger()
+
+@click.command()
+@click.option('-i', '--input', 'opt_fp_in', required=True,
+  help='Input directory')
+@click.option('-o', '--output', 'opt_fp_out',
+  help='Output directory')
+@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None),
+  help='Slice list of files')
+@click.option('--recursive/--no-recursive', 'opt_recursive', is_flag=True, default=False,
+  help='Use glob recursion (slower)')
+@click.option('-t', '--threads', 'opt_threads', default=4,
+  help='Number of threads')
+@click.option('-f', '--force', 'opt_force', is_flag=True,
+  help='Force overwrite file')
+@click.pass_context
+def cli(ctx, opt_fp_in, opt_fp_out, opt_slice, opt_recursive, opt_threads, opt_force):
+  """Multithreading test"""
+  
+  from glob import glob
+  from os.path import join
+  from pathlib import Path
+  import time
+  from multiprocessing.dummy import Pool as ThreadPool 
+  import random
+
+  import pandas as pd
+  from tqdm import tqdm
+  from glob import glob
+  
+  from app.utils import file_utils, im_utils
+
+
+  if not opt_force and Path(opt_fp_out).exists():
+    log.error('File exists. Use "-f / --force" to overwite')
+    return
+
+  fp_ims = []
+  for ext in ['jpg', 'png']:
+    if opt_recursive:
+      fp_glob = join(opt_fp_in, '**/*.{}'.format(ext))
+      fp_ims += glob(fp_glob, recursive=True)
+    else:
+      fp_glob = join(opt_fp_in, '*.{}'.format(ext))
+      fp_ims += glob(fp_glob)
+
+  if opt_slice:
+    fp_ims = fp_ims[opt_slice[0]:opt_slice[1]]
+
+  log.info('Processing {:,} images'.format(len(fp_ims)))
+
+  pbar = tqdm(total=100)
+
+  def as_sha256(fp_im):
+    pbar.update(1)
+    return file_utils.sha256(fp_im)
+
+  # multithread pool
+  st = time.time()
+  pool = ThreadPool(opt_threads) 
+  with tqdm(total=len(fp_ims)) as pbar:
+    sha256s = pool.map(as_sha256, fp_ims)
+  pbar.close()
+
+  # convert data to dict
+  data = []
+  for i, fp_im in enumerate(fp_ims):
+    fpp_im = Path(fp_im)
+    subdir = str(fpp_im.parent.relative_to(opt_fp_in))
+    sha256 = sha256s[i]
+    data.append( {
+      'sha256': sha256, 
+      'subdir': subdir,
+      'fn': fpp_im.stem,
+      'ext': fpp_im.suffix.replace('.','')
+      })
+
+  # save to CSV
+  df = pd.DataFrame.from_dict(data)
+  df.to_csv(opt_fp_out, index=False)
+
+  # timing
+  log.info('time: {:.2f}, theads: {}'.format(time.time() - st, opt_threads))
\ No newline at end of file