...identity

2 files changed, 22 insertions, 2 deletions

diff --git a/megapixels/app/utils/api_utils.py b/megapixels/app/utils/api_utils.py
index d9d67425..a4dad501 100644
--- a/megapixels/app/utils/api_utils.py
+++ b/megapixels/app/utils/api_utils.py
@@ -3,7 +3,7 @@ import urllib
 import urllib.request
 
 from app.settings import app_cfg
-from app.utils import file_utils, im_utils, logger_utils
+from app.utils import logger_utils
 
 
 class WikipediaAPI:
diff --git a/megapixels/app/utils/identity_utils.py b/megapixels/app/utils/identity_utils.py
index f9ed009e..775652dc 100644
--- a/megapixels/app/utils/identity_utils.py
+++ b/megapixels/app/utils/identity_utils.py
@@ -10,6 +10,25 @@ from app.utils import logger_utils
 
 log = logger_utils.Logger.getLogger()
 
+az = 'abcdefghijklmlopqrstuvwzxyz'
+AZ = az.upper()
+z9 = list(map(str, list(range(0,10))))
+aZ9 = list(az) + list(AZ) + z9
+
+def letter_strip(a, b=aZ9):
+  # strip every letter from a that is not in b
+  return ''.join([x for x in a if x in b])
+
+def letter_match(a, b):
+  # check if every letter (a-zA-Z0-9) exists in both
+  return sum([x in b for x in a]) == len(a)
+
+def names_match_strict(a, b):
+  clean_a = letter_strip(a)
+  clean_b = letter_strip(b)
+  return len(clean_a) == len(clean_b) and letter_match(clean_a, clean_b) and letter_match(clean_b, clean_a)
+
+
 '''
 class Dataset(Enum):
   LFW, VGG_FACE, VGG_FACE2, MSCELEB, UCCS, UMD_FACES, SCUT_FBP, UCF_SELFIE, UTK, \
@@ -83,6 +102,7 @@ def get_names(opt_dataset, opt_data_store=types.DataStore.HDD):
   result = {'names_orig': names_orig, 'names_query': names_query}
   return result
 
+
 def similarity(a, b):
   return difflib.SequenceMatcher(a=a.lower(), b=b.lower()).ratio()
 
@@ -111,7 +131,7 @@ def names_match(name_a, name_b, threshold=0.9, as_float=False, compound_score=Fa
     scores.append(subscores)
   
   # return result
-  ratio_similar = sum(max(x) for x in scores) / len_min
+  ratio_similar = sum(max(x) for x in scores) / len(scores)
 
   if compound_score:
     # combine with any missing letters/words