Merge branch 'master' of github.com:adamhrv/megapixels_dev

1 files changed, 44 insertions, 0 deletions

diff --git a/megapixels/commands/datasets/add_uuid.py b/megapixels/commands/datasets/add_uuid.py
new file mode 100644
index 00000000..9c14c0e3
--- /dev/null
+++ b/megapixels/commands/datasets/add_uuid.py
@@ -0,0 +1,44 @@
+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('-f', '--force', 'opt_force', is_flag=True,
+  help='Force overwrite file')
+@click.pass_context
+def cli(ctx, opt_fp_in, opt_fp_out, opt_force):
+  """Appends UUID to records CSV"""
+  
+  from glob import glob
+  from os.path import join
+  from pathlib import Path
+  import base64
+  import uuid
+
+  from tqdm import tqdm
+  import pandas as pd
+  
+  if not opt_force and Path(opt_fp_out).exists():
+    log.error('File exists. Use "-f / --force" to overwite')
+    return
+
+  # load names
+  df_records = pd.read_csv(opt_fp_in)
+  records = df_records.to_dict('index')
+  # append a UUID to every entry
+  for idx, item in records.items():
+    records[idx]['uuid'] = uuid.uuid4()
+  # save to csv
+  df_uuid = pd.DataFrame.from_dict(list(records.values()))  # ignore the indices
+  df_uuid.to_csv(opt_fp_out, index=False)
+
+  log.info('done')
\ No newline at end of file