[DEVX-876]: Fixed Issue with Filename as Invalid Input ID (#501)

* [DEVX-876]: Fixed Issue with Filename as Invalid Input ID

* [DEVX-876]: Fixed Issue with Filename as Invalid Input ID

* [WFP-902]: Fixed Deployment Tests (#502)

* [WFP-902]: Fixed Deployment Tests

* [WFP-902]: Fixed Deployment Tests

Author: srikanthbachala20

clarifai/client/input.py

@@ -22,7 +22,7 @@
 from clarifai.constants.input import MAX_UPLOAD_BATCH_SIZE
 from clarifai.errors import UserError
 from clarifai.utils.logging import logger
-from clarifai.utils.misc import BackoffIterator, Chunker
+from clarifai.utils.misc import BackoffIterator, Chunker, clean_input_id
 
 
 class Inputs(Lister, BaseClient):
@@ -282,7 +282,7 @@ def get_image_inputs_from_folder(folder_path: str, dataset_id: str = None,
     for filename in os.listdir(folder_path):
       if filename.split('.')[-1] not in ['jpg', 'jpeg', 'png', 'tiff', 'webp']:
         continue
-      input_id = filename.split('.')[0]
+      input_id = clean_input_id(filename.split('.')[0])
       image_pb = resources_pb2.Image(base64=open(os.path.join(folder_path, filename), 'rb').read())
       input_protos.append(
           Inputs._get_proto(
@@ -473,7 +473,7 @@ def get_text_inputs_from_folder(folder_path: str, dataset_id: str = None,
     for filename in os.listdir(folder_path):
       if filename.split('.')[-1] != 'txt':
         continue
-      input_id = filename.split('.')[0]
+      input_id = clean_input_id(filename.split('.')[0])
       text_pb = resources_pb2.Text(raw=open(os.path.join(folder_path, filename), 'rb').read())
       input_protos.append(
           Inputs._get_proto(

clarifai/utils/misc.py

@@ -1,4 +1,5 @@
 import os
+import re
 import uuid
 from typing import Any, Dict, List
 
@@ -75,3 +76,13 @@ def concept_relations_accumulation(relations_dict: Dict[str, Any], subject_conce
 def get_uuid(val: int) -> str:
   """Generates a UUID."""
   return uuid.uuid4().hex[:val]
+
+
+def clean_input_id(input_id: str) -> str:
+  """Clean input_id string into a valid input ID"""
+  input_id = re.sub('[., /]+', '_', input_id)
+  input_id = re.sub('[_]+', '_', input_id)
+  input_id = re.sub('[-]+', '-', input_id)
+  input_id = input_id.lower().strip('_-')
+  input_id = re.sub('[^a-z0-9-_]+', '', input_id)
+  return input_id