1 files changed, 102 insertions, 0 deletions
diff --git a/megapixels/commands/datasets/gen_filepath.py b/megapixels/commands/datasets/gen_filepath.py
new file mode 100644
index 00000000..e06fee6b
--- /dev/null
+++ b/megapixels/commands/datasets/gen_filepath.py
@@ -0,0 +1,102 @@
+"""
+Begin with this file to process folder of images
+- Converts folders and subdirectories into CSV with file attributes split
+"""
+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',
+  help='Override enum input filename CSV')
+@click.option('-o', '--output', 'opt_fp_out',
+  help='Override enum output filename CSV')
+@click.option('--data_store', 'opt_data_store',
+  type=cfg.DataStoreVar,
+  default=click_utils.get_default(types.DataStore.NAS),
+  show_default=True,
+  help=click_utils.show_help(types.Dataset))
+@click.option('--dataset', 'opt_dataset',
+  type=cfg.DatasetVar,
+  required=True,
+  show_default=True,
+  help=click_utils.show_help(types.Dataset))
+@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_data_store, opt_dataset, 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.models import DataStore
+  from app.utils import file_utils, im_utils
+
+  data_store = DataStore(opt_data_store, opt_dataset)
+  fp_out = opt_fp_out if opt_fp_out is not None else data_store.metadata(types.Metadata.FILEPATH)
+  if not opt_force and Path(fp_out).exists():
+    log.error('File exists. Use "-f / --force" to overwite')
+    return
+
+
+  # glob files
+  fp_in = opt_fp_in if opt_fp_in is not None else data_store.media_images_original()
+  fp_ims = []
+  log.info(f'Globbing {fp_in}')
+  for ext in ['jpg', 'png']:
+    if opt_recursive:
+      fp_glob = join(fp_in, '**/*.{}'.format(ext))
+      fp_ims += glob(fp_glob, recursive=True)
+    else:
+      fp_glob = join(fp_in, '*.{}'.format(ext))
+      fp_ims += glob(fp_glob)
+
+  if not fp_ims:
+    log.warn('No images. Try with "--recursive"')
+    return
+
+  if opt_slice:
+    fp_ims = fp_ims[opt_slice[0]:opt_slice[1]]
+
+  log.info('Found {:,} images'.format(len(fp_ims)))
+
+
+  # convert data to dict
+  data = []
+  for i, fp_im in enumerate(tqdm(fp_ims)):
+    fpp_im = Path(fp_im)
+    subdir = str(fpp_im.parent.relative_to(fp_in))
+    data.append( {
+      'subdir': subdir,
+      'fn': fpp_im.stem,
+      'ext': fpp_im.suffix.replace('.','')
+      })
+
+  # save to CSV
+  file_utils.mkdirs(fp_out)
+  df_filepath = pd.DataFrame.from_dict(data)
+  df_filepath = df_filepath.sort_values(by=['subdir'], ascending=True)
+  df_filepath = df_filepath.reset_index(drop=True)
+  df_filepath.index.name = 'index'
+  df_filepath.to_csv(fp_out)
+\ No newline at end of file