Normalize CAN IDs number of bits

parser.py

@@ -19,7 +19,7 @@ def parse_log(input_path: PathLike, out_bus1: PathLike, out_bus2: PathLike) -> N
     out1_file = Path(out_bus1)
     out2_file = Path(out_bus2)
 
-    start_pattern = re.compile(r'(C[12]):([0-9A-Fa-f]{1,8})\s+([0-9A-Fa-f]{1,2})\s+')
+    start_pattern = re.compile(r'(C[12]):([0-9A-Fa-f]{7,8})\s+([0-9A-Fa-f]{1,2})\s+')
     byte_pattern = re.compile(r'^[0-9A-Fa-f]{2}$')
 
     with input_file.open('r', encoding='utf-8') as f_in, \
@@ -35,7 +35,12 @@ def parse_log(input_path: PathLike, out_bus1: PathLike, out_bus2: PathLike) -> N
         for line in f_in:
             for match in start_pattern.finditer(line):
                 bus = match.group(1)
-                can_id = match.group(2).upper()
+
+                can_id = match.group(2).upper().zfill(8)
+
+                if int(can_id, 16) > 0x1FFFFFFF:
+                    continue
+
                 dlc_str = match.group(3)
 
                 try:
@@ -116,4 +121,3 @@ if __name__ == '__main__':
         print(f"[*] Processing {args.input_csv}...")
         lf = parse_csv(args.input_csv)
         lf.sink_parquet(args.output_parquet)
-        print(f"[+] Saved parquet file to {args.output_parquet}")

stat/correlation.py

@@ -12,6 +12,20 @@ import plotly.graph_objects as go
 from utils.extractor import load_data
 from utils.extractor import to_int
 
+def _format_can_id(x):
+    """Safely cleans CAN ID strings without altering their length or value."""
+    if pd.isna(x):
+        return "UNKNOWN"
+
+    s = str(x).strip()
+    if not s:
+        return "UNKNOWN"
+
+    if s.lower().startswith('0x'):
+        s = s[2:]
+
+    return s.upper()
+
 def calculate_correlation(df: pd.DataFrame, method: str, target_id: str | None = None) -> pd.DataFrame:
     """Calculates inter-byte correlation grouped by identifier."""
     byte_cols = [f"b{i}" for i in range(8)]
@@ -20,12 +34,16 @@ def calculate_correlation(df: pd.DataFrame, method: str, target_id: str | None =
     if not available_cols:
         raise ValueError("No byte columns (b0-b7) found in the DataFrame")
 
-    df_bytes = df[["Identifier"] + available_cols].copy()
+    can_id_col = 'ID' if 'ID' in df.columns else 'Identifier'
+    identifiers = df[can_id_col].apply(_format_can_id)
+
+    df_bytes = df[available_cols].copy()
     for col in available_cols:
         df_bytes[col] = df_bytes[col].apply(to_int)
 
-    if target_id:
+    if target_id is not None:
-        group = df_bytes[df_bytes["Identifier"] == target_id]
+        target_id = _format_can_id(target_id)
+        group = df_bytes[identifiers == target_id]
         if group.empty:
             raise ValueError(f"Identifier '{target_id}' not found in data")
         return group[available_cols].corr(method=method).fillna(0.0)
@@ -35,7 +53,9 @@ def calculate_correlation(df: pd.DataFrame, method: str, target_id: str | None =
         np.fill_diagonal(corr_arr, 0.0)
         return pd.Series(corr_arr.max(axis=0), index=group.columns).fillna(0.0)
 
-    return df_bytes.groupby("Identifier")[available_cols].apply(max_abs_corr)
+    result = df_bytes.groupby(identifiers)[available_cols].apply(max_abs_corr)
+    result.index.name = 'Identifier'
+    return result
 
 
 def plot_correlation_heatmap(corr_df: pd.DataFrame, target_id: str | None, title: str) -> go.Figure:

stat/entropy.py

@@ -12,6 +12,20 @@ import plotly.graph_objects as go
 from utils.extractor import load_data
 from utils.extractor import to_int
 
+def _format_can_id(x):
+    """Safely cleans CAN ID strings without altering their length or value."""
+    if pd.isna(x):
+        return "UNKNOWN"
+
+    s = str(x).strip()
+    if not s:
+        return "UNKNOWN"
+
+    if s.lower().startswith('0x'):
+        s = s[2:]
+
+    return s.upper()
+
 def calculate_byte_entropy(df: pd.DataFrame) -> pd.DataFrame:
     """Calculates Shannon entropy per byte position for each identifier."""
     byte_cols = [f"b{i}" for i in range(8)]
@@ -19,6 +33,9 @@ def calculate_byte_entropy(df: pd.DataFrame) -> pd.DataFrame:
     if not available_cols:
         raise ValueError("No byte columns (b0-b7) found in the DataFrame")
 
+    can_id_col = 'ID' if 'ID' in df.columns else 'Identifier'
+    identifiers = df[can_id_col].apply(_format_can_id)
+
     df_bytes = df[available_cols].copy()
     for col in available_cols:
         df_bytes[col] = df_bytes[col].apply(to_int)
@@ -30,7 +47,9 @@ def calculate_byte_entropy(df: pd.DataFrame) -> pd.DataFrame:
         p = s.value_counts(normalize=True)
         return -np.sum(p * np.log2(p))
 
-    return df.groupby("Identifier")[available_cols].agg(entropy)
+    result = df_bytes.groupby(identifiers)[available_cols].agg(entropy)
+    result.index.name = 'Identifier'
+    return result
 
 
 def plot_entropy_heatmap(entropy_df: pd.DataFrame, title: str) -> go.Figure:

stat/frequency.py

@@ -9,10 +9,29 @@ import plotly.express as px
 import plotly.graph_objects as go
 from utils.extractor import load_data
 
+def _format_can_id(x):
+    """Safely cleans CAN ID strings without altering their length or value."""
+    if pd.isna(x):
+        return "UNKNOWN"
+
+    s = str(x).strip()
+    if not s:
+        return "UNKNOWN"
+
+    if s.lower().startswith('0x'):
+        s = s[2:]
+
+    return s.upper()
+
 def calc_freq(df: pd.DataFrame) -> pd.DataFrame:
     """Calculates frequency counts and percentages for identifiers."""
-    freq_df = df['Identifier'].value_counts().reset_index()
+    can_id_col = 'ID' if 'ID' in df.columns else 'Identifier'
+
+    df['Formatted_ID'] = df[can_id_col].apply(_format_can_id)
+
+    freq_df = df['Formatted_ID'].value_counts().reset_index()
     freq_df.columns = ['Identifier', 'Count']
+
     total = freq_df['Count'].sum()
     freq_df['Percentage'] = (freq_df['Count'] / total * 100).round(2)
     return freq_df.sort_values('Count', ascending=True)
@@ -43,7 +62,6 @@ def plot_freq(stats_df: pd.DataFrame, title: str) -> go.Figure:
         ),
         yaxis=dict(
             title=dict(text="PGN or CAN ID", font=dict(size=13, color="#1a1a1a")),
-            #autorange="",
             showgrid=False,
             linecolor="#bdbdbd",
             tickfont=dict(size=12, color="#2a2a2a"),
@@ -51,6 +69,7 @@ def plot_freq(stats_df: pd.DataFrame, title: str) -> go.Figure:
             ticklen=4,
             tickcolor="#cccccc",
             automargin=True,
+            type='category'
         ),
         font=dict(family="Segoe UI, Arial, sans-serif", size=12, color='#2a2a2a'),
         hoverlabel=dict(bgcolor="white", font_size=13, font_family="Segoe UI",