Adapted text join options to review file to be more resilient to changes in image size. Added possibility of using client secret with AWS login

app.py

@@ -458,9 +458,9 @@ with app:
     then(fn = upload_file_to_s3, inputs=[usage_logs_state, usage_s3_logs_loc_state], outputs=[s3_logs_output_textbox])
 
 # Get some environment variables and Launch the Gradio app
-COGNITO_AUTH = get_or_create_env_var('COGNITO_AUTH', '0')
+COGNITO_AUTH = get_or_create_env_var('COGNITO_AUTH', '1')
 print(f'The value of COGNITO_AUTH is {COGNITO_AUTH}')
-
+1
 RUN_DIRECT_MODE = get_or_create_env_var('RUN_DIRECT_MODE', '0')
 print(f'The value of RUN_DIRECT_MODE is {RUN_DIRECT_MODE}')
 

tools/auth.py

@@ -1,15 +1,31 @@
 
 import boto3
 import gradio as gr
+import hmac
+import hashlib
+import base64
 from tools.helper_functions import get_or_create_env_var
 
-client_id = get_or_create_env_var('AWS_CLIENT_ID', '') # This client id is borrowed from async gradio app client
+client_id = get_or_create_env_var('AWS_CLIENT_ID', '3qs30degqvip8ade8iv44c4edf')
 print(f'The value of AWS_CLIENT_ID is {client_id}')
 
-user_pool_id = get_or_create_env_var('AWS_USER_POOL_ID', '')
+client_secret = get_or_create_env_var('AWS_CLIENT_SECRET', 'cvgd27dihp88jktc71lmjaq2kgntjdkt6703m63mdfjv9j58mqo')
+print(f'The value of AWS_CLIENT_SECRET is {client_secret}')
+
+user_pool_id = get_or_create_env_var('AWS_USER_POOL_ID', 'eu-west-2_7Jhnih7D1')
 print(f'The value of AWS_USER_POOL_ID is {user_pool_id}')
 
-def authenticate_user(username:str, password:str, user_pool_id:str=user_pool_id, client_id:str=client_id):
+def calculate_secret_hash(client_id, client_secret, username):
+    message = username + client_id
+    dig = hmac.new(
+        str(client_secret).encode('utf-8'),
+        msg=str(message).encode('utf-8'),
+        digestmod=hashlib.sha256
+    ).digest()
+    secret_hash = base64.b64encode(dig).decode()
+    return secret_hash
+
+def authenticate_user(username:str, password:str, user_pool_id:str=user_pool_id, client_id:str=client_id, client_secret:str=client_secret):
     """Authenticates a user against an AWS Cognito user pool.
 
     Args:
@@ -17,6 +33,7 @@ def authenticate_user(username:str, password:str, user_pool_id:str=user_pool_id,
         client_id (str): The ID of the Cognito user pool client.
         username (str): The username of the user.
         password (str): The password of the user.
+        client_secret (str): The client secret of the app client
 
     Returns:
         bool: True if the user is authenticated, False otherwise.
@@ -24,15 +41,28 @@ def authenticate_user(username:str, password:str, user_pool_id:str=user_pool_id,
 
     client = boto3.client('cognito-idp')  # Cognito Identity Provider client
 
+    # Compute the secret hash
+    secret_hash = calculate_secret_hash(client_id, client_secret, username)
+
     try:
 
+        # response = client.initiate_auth(
+        #     AuthFlow='USER_PASSWORD_AUTH',
+        #     AuthParameters={
+        #         'USERNAME': username,
+        #         'PASSWORD': password,
+        #     },
+        #     ClientId=client_id
+        # )
+
         response = client.initiate_auth(
-            AuthFlow='USER_PASSWORD_AUTH',
-            AuthParameters={
-                'USERNAME': username,
-                'PASSWORD': password,
-            },
-            ClientId=client_id
+        AuthFlow='USER_PASSWORD_AUTH',
+        AuthParameters={
+            'USERNAME': username,
+            'PASSWORD': password,
+            'SECRET_HASH': secret_hash
+        },
+        ClientId=client_id
         )
 
         # If successful, you'll receive an AuthenticationResult in the response

tools/file_conversion.py

@@ -650,6 +650,53 @@ def convert_text_pdf_to_img_pdf(in_file_path:str, out_text_file_path:List[str],
 
     return out_message, out_file_paths
 
+# Example DataFrames
+# df1 = pd.DataFrame({
+#     'xmin': [10, 20, 30],
+#     'xmax': [15, 25, 35],
+#     'ymin': [40, 50, 60],
+#     'ymax': [45, 55, 65],
+#     'info1': ['A', 'B', 'C']
+# })
+
+# df2 = pd.DataFrame({
+#     'xmin': [12, 18, 32],
+#     'xmax': [14, 24, 34],
+#     'ymin': [42, 48, 62],
+#     'ymax': [44, 54, 66],
+#     'info2': ['X', 'Y', 'Z']
+# })
+
+def join_values_within_threshold(df1, df2):
+    # Threshold for matching
+    threshold = 5
+
+    # Perform a cross join
+    df1['key'] = 1
+    df2['key'] = 1
+    merged = pd.merge(df1, df2, on='key').drop(columns=['key'])
+
+    # Apply conditions for all columns
+    conditions = (
+        (abs(merged['xmin_x'] - merged['xmin_y']) <= threshold) &
+        (abs(merged['xmax_x'] - merged['xmax_y']) <= threshold) &
+        (abs(merged['ymin_x'] - merged['ymin_y']) <= threshold) &
+        (abs(merged['ymax_x'] - merged['ymax_y']) <= threshold)
+    )
+
+    # Filter rows that satisfy all conditions
+    filtered = merged[conditions]
+
+    # Drop duplicates if needed (e.g., keep only the first match for each row in df1)
+    result = filtered.drop_duplicates(subset=['xmin_x', 'xmax_x', 'ymin_x', 'ymax_x'])
+
+    # Merge back into the original DataFrame (if necessary)
+    final_df = pd.merge(df1, result, left_on=['xmin', 'xmax', 'ymin', 'ymax'], right_on=['xmin_x', 'xmax_x', 'ymin_x', 'ymax_x'], how='left')
+
+    # Clean up extra columns
+    final_df = final_df.drop(columns=['key'])
+    print(final_df)
+
 
 def convert_review_json_to_pandas_df(data:List[dict], text_join_data=pd.DataFrame) -> pd.DataFrame:
     # Flatten the data
@@ -691,8 +738,11 @@ def convert_review_json_to_pandas_df(data:List[dict], text_join_data=pd.DataFram
         text_join_data['page'] = text_join_data['page'].astype(str)
         df['page'] = df['page'].astype(str)
         text_join_data = text_join_data[['xmin', 'ymin', 'xmax', 'ymax', 'label', 'page', 'text']]
-        text_join_data[['xmin', 'ymin', 'xmax', 'ymax']] = text_join_data[['xmin', 'ymin', 'xmax', 'ymax']].astype(float).round(0)
-        df[['xmin1', 'ymin1', 'xmax1', 'ymax1']] = df[['xmin', 'ymin', 'xmax', 'ymax']].astype(float).round(0)
+        # Round to the closest number divisible by 5
+        text_join_data[['xmin', 'ymin', 'xmax', 'ymax']] = (text_join_data[['xmin', 'ymin', 'xmax', 'ymax']].astype(float) / 5).round() * 5
+        text_join_data = text_join_data.drop_duplicates(['xmin', 'ymin', 'xmax', 'ymax', 'label', 'page'])
+        
+        df[['xmin1', 'ymin1', 'xmax1', 'ymax1']] = (df[['xmin', 'ymin', 'xmax', 'ymax']].astype(float) / 5).round() * 5
 
         df = df.merge(text_join_data, left_on = ['xmin1', 'ymin1', 'xmax1', 'ymax1', 'label', 'page'], right_on = ['xmin', 'ymin', 'xmax', 'ymax', 'label', 'page'], how = "left", suffixes=("", "_y"))
 

tools/redaction_review.py

@@ -41,7 +41,7 @@ def increase_page(number:int, image_annotator_object:AnnotatedImageData):
 
 def update_zoom(current_zoom_level:int, annotate_current_page:int, decrease:bool=True):
     if decrease == False:
-        if current_zoom_level >= 50:
+        if current_zoom_level >= 70:
             current_zoom_level -= 10
     else:    
         if current_zoom_level < 100: