Added pipe

pipeline.py

@@ -0,0 +1,57 @@
+import pandas as pd
+import re
+from utils import *
+from config import URL_FEATURES
+
+class EmailFeatureExtractor:
+    def __init__(self):
+        self.required_features = URL_FEATURES
+
+    def transform(self, subject: str, body: str) -> pd.DataFrame:
+        # Create initial DataFrame from user input
+        df = pd.DataFrame([{'subject': subject, 'body': body}])
+
+        # 1. URL & Attachment Extraction
+        df['URL'] = df.apply(extract_urls_from_body, axis=1)
+        df['URL_COUNT'] = df['URL'].apply(count_urls)
+        
+        
+
+        # 2. Combined Text for BERT
+        df['text_combined'] = df.apply(create_combined_text, axis=1)
+
+        # 3. IP Address Detection
+        df['USE_OF_IP'] = df['URL'].apply(
+            lambda x: having_ip_address(x) if x else 0
+        )
+
+        # 4. Basic URL Stats
+        # Note: We apply result_type='expand' if utils returns a Series
+        stats = df['URL'].apply(extract_basic_url_stats)
+        df[['url_length_max', 'url_length_avg', 'url_subdom_max', 'url_subdom_avg']] = stats
+
+        # 5. Shorteners & Suspicious Keywords
+        df['short_url_count'] = df['URL'].apply(count_shortened_urls)
+        df['sus_url_count'] = df['URL'].apply(suspicious_words_count)
+        df['sus_url_flag'] = (df['sus_url_count'] > 0).astype(int)
+
+        # 6. Dot Features
+        df[['dot_count_max', 'dot_count_avg']] = df['URL'].apply(extract_dot_features)
+
+        # 7. Generic Character Counts
+        char_map = {'perc': '%', 'ques': '?', 'hyphen': '-', 'equal': '='}
+        for name, char in char_map.items():
+            df[[f'{name}_max', f'{name}_avg']] = df['URL'].apply(
+                lambda x: extract_char_features(x, char, name)
+            )
+
+        return self._verify_and_order(df)
+
+    def _verify_and_order(self, df: pd.DataFrame) -> pd.DataFrame:
+        missing = [col for col in self.required_features if col not in df.columns]
+        if missing:
+            for col in missing:
+                df[col] = 0
+        
+        cols_to_return = self.required_features + ['text_combined']
+        return df[cols_to_return]