Upload files to "/"

block.py

@@ -6,6 +6,8 @@ import regex as re
 from pre_processing import pre_processing
 from processing import processing
 from post_processing import post_processing
+import json_repair
+
 
 # Configure logging
 logging.basicConfig(
@@ -14,6 +16,8 @@ logging.basicConfig(
 )
 logger = logging.getLogger(__name__)
 
+_JSON_LIKE = re.compile(r'^\s*\?*[\{\[].*[\}\]]\s*$', re.DOTALL)
+
 
 def extract_value(blob, expression):
     try:
@@ -21,7 +25,6 @@ def extract_value(blob, expression):
     except Exception:
         return None
 
-# Coalesce function to return the first non-None value
 def coalesce(*args):
     for value in args:
         if value is not None:
@@ -29,57 +32,100 @@ def coalesce(*args):
     return None
 
 # New sanitize blob function
+
+
+def deep_repair(obj):
+    # 1) If it's a string that *looks* like JSON (with or without one leading '?'),
+    #    strip exactly one leading '?', reparses, and recurse.
+    if isinstance(obj, str):
+        s = obj.strip()
+        if _JSON_LIKE.match(s):
+            # strip one leading '?' if present
+            if s.startswith('?'):
+                s = s[1:]
+            parsed = json_repair.loads(s)
+            return deep_repair(parsed)
+        return obj
+
+    # 2) Dict → recurse on each value
+    if isinstance(obj, dict):
+        return {k: deep_repair(v) for k, v in obj.items()}
+
+    # 3) List → recurse on each element
+    if isinstance(obj, list):
+        return [deep_repair(v) for v in obj]
+
+    # 4) Otherwise, leave it alone
+    return obj
+
+
 def sanitize_blob(blob):
     try:
-        blob = re.sub(r'"(\w+)":"(\{[^}]+\})"', r'"\1":\2', blob)
+        return deep_repair(blob)
-        blob = re.sub(r'"tps_vendor_raw_response"\s*:\s*"\?\{', '"tps_vendor_raw_response":{', blob)
+    except Exception as e:
-        blob = blob.replace('\\"', '"')
+        logger.error("Failed to sanitize blob: %s", e)
-        blob = blob.replace('\\n', '')
-        blob = blob.replace('\\t', '')
-        blob = blob.replace('\\\\', '')
-        blob = re.sub(r'(\}\})"', r'\1', blob)
-        blob = re.sub(r',\s*([\}\]])', r'\1', blob)
-        return json.loads(blob)
-    except json.JSONDecodeError as e:
-        logger.error(f"JSON Decode Error: {e}")
-        error_pos = e.pos
-        snippet = blob[max(0, error_pos - 50): error_pos + 50]
-        logger.error(f"Error near:\n{snippet}")
         return None
-#---------------- Sanitise ends here 
     
-# Function to extract a value using JMESPath
 # Expressions to extract values
 expressions = {
     "first_seen_days": [
-        "tps_vendor_raw_response.query.results[0].first_seen_days",
+        # 1) any vendor under integration_hub_results → first_seen_days
-        "emailage.emailriskscore.first_seen_days"
+        "(Blob.integration_hub_results.*.tps_vendor_raw_response.query.results[0].first_seen_days)[0]",
+
+        # 2) the flat “dotted” key
+        "Blob.\"emailage.emailriskscore.first_seen_days\"",
+
+        # 3) fallback to the top level tps_vendor_raw_response path
+        "Blob.tps_vendor_raw_response.query.results[0].first_seen_days",
     ],
     "ea_score": [
-        "tps_vendor_raw_response.query.results[0].EAScore",
+        # 1) any vendor under integration_hub_results
-        "emailage.emailriskscore.eascore"
+        'Blob.integration_hub_results.*.tps_vendor_raw_response.query.results[0].EAScore',
+
+        # 2) the flat “dotted” key
+        'Blob."emailage.emailriskscore.eascore"',
+
+        # 3) fallback to the top level tps_vendor_raw_response
+        'Blob.tps_vendor_raw_response.query.results[0].EAScore',
     ],
     "email_creation_days": [
-        "tps_vendor_raw_response.query.results[0].email_creation_days"
+        # 1) any vendor under integration_hub_results → results[0].email_creation_days
+        "(Blob.integration_hub_results.*"
+        ".tps_vendor_raw_response.query.results[0].email_creation_days)[0]",
+
+        # 2) fallback to the top level tps_vendor_raw_response path
+        "Blob.tps_vendor_raw_response.query.results[0].email_creation_days",
     ],
-    "summary_risk_score": ["summary_risk_score"],
+    "summary_risk_score": ["Blob.summary_risk_score"],
-    "digital_id_trust_score_rating": ["digital_id_trust_score_rating"],
+    "digital_id_trust_score_rating": ["Blob.digital_id_trust_score_rating"],
-    "os_version": ["os_version"],
+    "os_version": ["Blob.os_version"],
-    "account_email_worst_score": ["account_email_worst_score"],
+    "account_email_worst_score": ["Blob.account_email_worst_score"],
-    "true_ip_score": ["true_ip_score"],
+    "true_ip_score": ["Blob.true_ip_score"],
     "ip_net_speed_cell": [
-        "tps_vendor_raw_response.query.results[0].ip_netSpeedCell",
+        # 1) any vendor under integration_hub_results → results[0].ip_netSpeedCell
-        # "true_ip_connection_type"
+        "(Blob.integration_hub_results.*"
+        ".tps_vendor_raw_response.query.results[0].ip_netSpeedCell)[0]",
+
+        # 2) fallback to the top level tps_vendor_raw_response path
+        "Blob.tps_vendor_raw_response.query.results[0].ip_netSpeedCell",
     ],
-    "account_email_score": ["account_email_score"],
+    "account_email_score": ["Blob.account_email_score"],
-    "true_ip_worst_score": ["true_ip_worst_score"],
+    "true_ip_worst_score": ["Blob.true_ip_worst_score"],
-    "proxy_ip_worst_score": ["proxy_ip_worst_score"],
+    "proxy_ip_worst_score": ["Blob.proxy_ip_worst_score"],
-    "proxy_ip_score": ["proxy_ip_score"],
+    "proxy_ip_score": ["Blob.proxy_ip_score"],
-    "fuzzy_device_score": ["fuzzy_device_score"],
+    "fuzzy_device_score": ["Blob.fuzzy_device_score"],
-    "ip_region_confidence": ["tps_vendor_raw_response.query.results[0].ip_regionconf"],
+    "ip_region_confidence": [
-    "true_ip_state_confidence": ["true_ip_state_confidence"],
+        # 1) any vendor under integration_hub_results → results[0].ip_regionconf
-    "fuzzy_device_worst_score": ["fuzzy_device_worst_score"],
+        "(Blob.integration_hub_results.*"
-    "digital_id_confidence_rating": ["digital_id_confidence_rating"]
+        ".tps_vendor_raw_response.query.results[0].ip_regionconf)[0]",
+
+        # 2) fallback to the top level tps_vendor_raw_response path
+        "Blob.tps_vendor_raw_response.query.results[0].ip_regionconf",
+    ],
+    "true_ip_state_confidence": ["Blob.true_ip_state_confidence"],
+    "fuzzy_device_worst_score": ["Blob.fuzzy_device_worst_score"],
+    "digital_id_confidence_rating": ["Blob.digital_id_confidence_rating"],
+    "trueipgeo": ["TrueIpGeo","Blob.true_ip_geo"],
 }
 
 
@@ -150,7 +196,8 @@ def __main__(
 
         # Step 2: Extract values using the expressions dictionary
         for column, expressions_list in expressions.items():
-            combined_df[column] = combined_df["blob"].apply(lambda x: coalesce(*[extract_value(x, expr) for expr in expressions_list]))
+            combined_df[column] = combined_df["blob"].apply(lambda x: coalesce(
+                *[extract_value(x, expr) for expr in expressions_list]))
 
         logger.info("pre_flowx data")
         logger.info(combined_df.iloc[0].drop('blob').to_dict())
@@ -164,7 +211,7 @@ def __main__(
     logger.info("pre_processed data")
     logger.info(pre_processed_data.iloc[0].to_dict())
     df = processing(pre_processed_data)
-    logger.info("procesed_data")
+    logger.info("processed_data")
     logger.info(df.iloc[0].to_dict())
     df["application_timestamp"] = df["application_timestamp"].astype(str)
     # logger.info("prediction: %.8f", float(df['prediction'].iloc[0]))

requirements.txt

@@ -4,3 +4,4 @@ xgboost == 2.1.4
 joblib == 1.4.2
 jmespath == 1.0.1
 regex == 2023.12.25
+json_repair == 0.47.6