.

1 files changed, 167 insertions, 0 deletions

diff --git a/megapixels/commands/datasets/records.py b/megapixels/commands/datasets/records.py
new file mode 100644
index 00000000..b6ef618b
--- /dev/null
+++ b/megapixels/commands/datasets/records.py
@@ -0,0 +1,167 @@
+'''
+
+'''
+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()
+
+identity_sources = ['subdir', 'subdir_head', 'subdir_tail']
+
+@click.command()
+@click.option('-i', '--input', 'opt_fp_in', default=None,
+  help='Override enum input filename CSV')
+@click.option('-o', '--output', 'opt_fp_out', default=None,
+  help='Override enum output filename CSV')
+@click.option('-m', '--media', 'opt_dir_media', default=None,
+  help='Override enum media directory')
+@click.option('--data_store', 'opt_data_store',
+  type=cfg.DataStoreVar,
+  default=click_utils.get_default(types.DataStore.SSD),
+  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('-t', '--threads', 'opt_threads', default=12,
+  help='Number of threads')
+@click.option('-f', '--force', 'opt_force', is_flag=True,
+  help='Force overwrite file')
+@click.option('--identity', 'opt_identity', default=None, type=click.Choice(identity_sources),
+  help='Identity source, blank for no identity')
+@click.option('--recursive/--no-recursive', 'opt_recursive', is_flag=True, default=False,
+  help='Use glob recursion (slower)')
+@click.pass_context
+def cli(ctx, opt_fp_in, opt_fp_out, opt_dataset, opt_data_store, opt_dir_media, opt_slice, opt_threads,
+  opt_identity, opt_force, opt_recursive):
+  """Generates sha256, uuid, and identity index CSV file"""
+  
+  import sys
+  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 uuid
+
+  import pandas as pd
+  from tqdm import tqdm
+  from glob import glob
+
+  from app.models.data_store import DataStore
+  from app.utils import file_utils, im_utils
+
+
+  # set data_store
+  data_store = DataStore(opt_data_store, opt_dataset)
+  # get filepath out
+  fp_out = data_store.metadata(types.Metadata.FILE_RECORD) if opt_fp_out is None else opt_fp_out
+  # exit if exists
+  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()
+  log.info(f'Globbing {fp_in}')
+  fp_ims = file_utils.glob_multi(fp_in, ['jpg', 'png'], recursive=opt_recursive)
+  # fail if none
+  if not fp_ims:
+    log.error('No images. Try with "--recursive"')
+    return
+  # slice to reduce
+  if opt_slice:
+    fp_ims = fp_ims[opt_slice[0]:opt_slice[1]]
+  log.info('Found {:,} images'.format(len(fp_ims)))
+
+
+  # ----------------------------------------------------------------
+  # multithread process into SHA256
+
+  pbar = tqdm(total=len(fp_ims))
+
+  def as_sha256(fp_im):
+    pbar.update(1)
+    return file_utils.sha256(fp_im)
+
+  # convert to thread pool
+  sha256s = []  # ?
+  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 = []
+  indentity_count = 0
+  for sha256, fp_im in zip(sha256s, fp_ims):
+    fpp_im = Path(fp_im)
+    subdir = str(fpp_im.parent.relative_to(fp_in))
+    
+
+    if opt_identity:
+      subdirs = subdir.split('/')
+      if not len(subdirs) > 0:
+        log.error(f'Could not split subdir: "{subdir}. Try different option for "--identity"')
+        log.error('exiting')
+        return
+      if opt_identity == 'subdir':
+        identity = subdirs[0]  # use first/only part
+      elif opt_identity == 'subdir_head':
+        identity = subdirs[0]  # use first part of subdir path
+      elif opt_identity == 'subdir_tail':
+        identity = subdirs[-1]  # use last part of subdir path
+    else:
+      identity = indentity_count  # use incrementing number
+      indentity_count += 1
+
+    data.append({
+      'subdir': subdir,
+      'fn': fpp_im.stem,
+      'ext': fpp_im.suffix.replace('.',''),
+      'sha256': sha256,
+      'uuid': uuid.uuid4(),
+      'identity_key': identity
+      })
+
+  df_records = pd.DataFrame.from_dict(data)
+  if opt_identity:
+    log.info(f'adding identity index using: "{opt_identity}". This may take a while...')
+    # convert dict to DataFrame
+    # sort based on identity_key
+    df_records = df_records.sort_values(by=['identity_key'], ascending=True)
+    # add new column for identity
+    df_records['identity_index'] = [-1] * len(df_records)
+    # populate the identity_index
+    df_records_identity_groups = df_records.groupby('identity_key')
+    # enumerate groups to create identity indices
+    for identity_index, df_records_identity_group_tuple in enumerate(df_records_identity_groups):
+      identity_key, df_records_identity_group = df_records_identity_group_tuple
+      for ds_record in df_records_identity_group.itertuples():
+        df_records.at[ds_record.Index, 'identity_index'] = identity_index
+    # reset index after being sorted
+    df_records = df_records.reset_index(drop=True)
+  else:
+    # name everyone person 1, 2, 3...
+    pass
+
+  df_records.index.name = 'index'  # reassign 'index' as primary key column
+  # write to CSV
+  file_utils.mkdirs(fp_out)
+  df_records.to_csv(fp_out)
+  # done
+  log.info(f'wrote rows: {len(df_records)} to {fp_out}')
\ No newline at end of file