From 9ddc6ea0d5b457f12e03e62e5fbb78afb94ef48b Mon Sep 17 00:00:00 2001
From: Erick Ahmed <engineering@erickahmed.com>
Date: Mon, 13 Jul 2026 22:16:56 +0200
Subject: [PATCH] Use utility function instead of internal

---
 stat/correlation.py | 16 ++--------------
 stat/entropy.py     | 16 ++--------------
 2 files changed, 4 insertions(+), 28 deletions(-)

diff --git a/stat/correlation.py b/stat/correlation.py
index dc81132..4d0f70c 100644
--- a/stat/correlation.py
+++ b/stat/correlation.py
@@ -10,19 +10,7 @@ import pandas as pd
 import plotly.graph_objects as go
 
 from utils.extractor import load_data
-
-
-def _to_int(x):
-    """Convert a hex string or integer to int, returning NaN on failure."""
-    if isinstance(x, (int, np.integer)):
-        return int(x)
-    if isinstance(x, str):
-        try:
-            return int(x, 16)
-        except ValueError:
-            return np.nan
-    return np.nan
-
+from utils.extractor import to_int
 
 def calculate_correlation(df: pd.DataFrame, method: str, target_id: str | None = None) -> pd.DataFrame:
     """Calculates inter-byte correlation grouped by identifier."""
@@ -34,7 +22,7 @@ def calculate_correlation(df: pd.DataFrame, method: str, target_id: str | None =
 
     df_bytes = df[["Identifier"] + available_cols].copy()
     for col in available_cols:
-        df_bytes[col] = df_bytes[col].apply(_to_int)
+        df_bytes[col] = df_bytes[col].apply(to_int)
 
     if target_id:
         group = df_bytes[df_bytes["Identifier"] == target_id]
diff --git a/stat/entropy.py b/stat/entropy.py
index ac19a22..ca314ea 100644
--- a/stat/entropy.py
+++ b/stat/entropy.py
@@ -10,19 +10,7 @@ import pandas as pd
 import plotly.graph_objects as go
 
 from utils.extractor import load_data
-
-
-def _to_int(x):
-    """Convert a hex string or integer to int, returning NaN on failure."""
-    if isinstance(x, (int, np.integer)):
-        return int(x)
-    if isinstance(x, str):
-        try:
-            return int(x, 16)
-        except ValueError:
-            return np.nan
-    return np.nan
-
+from utils.extractor import to_int
 
 def calculate_byte_entropy(df: pd.DataFrame) -> pd.DataFrame:
     """Calculates Shannon entropy per byte position for each identifier."""
@@ -33,7 +21,7 @@ def calculate_byte_entropy(df: pd.DataFrame) -> pd.DataFrame:
 
     df_bytes = df[available_cols].copy()
     for col in available_cols:
-        df_bytes[col] = df_bytes[col].apply(_to_int)
+        df_bytes[col] = df_bytes[col].apply(to_int)
 
     def entropy(s: pd.Series) -> float:
         s = s.dropna()