Performance optimizations: O(n*m) to O(n) lookups, lazy OUI loading, cached FD checks

- airodump.py: Replace O(n*m) nested loops with O(1) dict lookups for both
  client-to-target mapping and old-target matching (250K+ comparisons → ~1K)
- airodump.py: Sample only first 4KB for chardet encoding detection instead
  of reading entire CSV file, reducing I/O per scan cycle
- airodump.py: Suppress repeated null-byte warnings (log once per parse)
- config.py: Lazy-load OUI manufacturer database (1.7MB file) on first access
  instead of parsing at startup, improving startup time
- process.py: Cache file descriptor count with 2-second TTL to avoid
  os.listdir('/proc/pid/fd/') on every process creation
- process.py: Reduce FD limit sleep from 500ms to 100ms since cleanup is sync
- scanner.py: Use heapq.nlargest() for O(n log k) target capping instead of
  O(n log n) full sort
- scanner.py: Remove duplicate pid.poll() system call in main scan loop

https://claude.ai/code/session_012qvM97c3D9M98CrMjmzuQd

Author: claude

wifite/config.py

@@ -119,6 +119,27 @@ class Configuration:
     # System check mode
     syscheck = None
 
+    @classmethod
+    def load_manufacturers(cls):
+        """Lazy-load OUI manufacturer database on first access."""
+        if cls._manufacturers_loaded:
+            return
+        cls._manufacturers_loaded = True
+        if os.path.isfile('/usr/share/ieee-data/oui.txt'):
+            mfr_file = '/usr/share/ieee-data/oui.txt'
+        else:
+            mfr_file = 'ieee-oui.txt'
+        if os.path.exists(mfr_file):
+            cls.manufacturers = {}
+            with open(mfr_file, 'r', encoding='utf-8') as f:
+                for line in f:
+                    if not re.match(r'^\w', line):
+                        continue
+                    line = line.replace('(hex)', '').replace('(base 16)', '')
+                    fields = line.split()
+                    if len(fields) >= 2:
+                        cls.manufacturers[fields[0]] = ' '.join(fields[1:]).rstrip('.')
+
     @classmethod
     def initialize(cls, load_interface=True):
         """
@@ -249,22 +270,9 @@ def initialize(cls, load_interface=True):
                 cls.wordlists = [wlist]
                 break
 
-        if os.path.isfile('/usr/share/ieee-data/oui.txt'):
-            manufacturers = '/usr/share/ieee-data/oui.txt'
-        else:
-            manufacturers = 'ieee-oui.txt'
-
-        if os.path.exists(manufacturers):
-            cls.manufacturers = {}
-            with open(manufacturers, "r", encoding='utf-8') as f:
-                # Parse txt format into dict
-                for line in f:
-                    if not re.match(r"^\w", line):
-                        continue
-                    line = line.replace('(hex)', '').replace('(base 16)', '')
-                    fields = line.split()
-                    if len(fields) >= 2:
-                        cls.manufacturers[fields[0]] = " ".join(fields[1:]).rstrip('.')
+        # Manufacturers database is lazy-loaded on first access via load_manufacturers()
+        cls.manufacturers = None
+        cls._manufacturers_loaded = False
 
         # WPS variables
         cls.wps_filter = False  # Only attack WPS networks

wifite/model/target.py

@@ -268,7 +268,8 @@ def to_str(self, show_bssid=False, show_manufacturer=False):
         bssid = Color.s('{D}%s{W}' % self.bssid) if show_bssid else ''
         if show_manufacturer:
             oui = ''.join(self.bssid.split(':')[:3])
-            self.manufacturer = Configuration.manufacturers.get(oui, "")
+            Configuration.load_manufacturers()
+            self.manufacturer = Configuration.manufacturers.get(oui, "") if Configuration.manufacturers else ""
 
             max_oui_len = 21
             mfg_name = self.manufacturer

wifite/tools/airodump.py

@@ -184,23 +184,17 @@ def get_targets(self, old_targets=None, apply_filter=True, target_archives=None)
         new_targets = Airodump.get_targets_from_csv(csv_filename)
 
         # Check if one of the targets is also contained in the old_targets
+        # Use dict lookup (O(1)) instead of nested loop (O(n*m))
+        old_by_bssid = {t.bssid: t for t in old_targets}
         for new_target in new_targets:
-            just_found = True
-            for old_target in old_targets:
-                # If the new_target is found in old_target copy attributes from old target
-                if old_target == new_target:
-                    # Identify decloaked targets
-                    if new_target.essid_known and not old_target.essid_known:
-                        # We decloaked a target!
-                        new_target.decloaked = True
-
-                    old_target.transfer_info(new_target)
-                    just_found = False
-                    break
-
-            # If the new_target is not in old_targets, check target_archives
-            # and copy attributes from there
-            if just_found and new_target.bssid in target_archives:
+            old_target = old_by_bssid.get(new_target.bssid)
+            if old_target is not None:
+                # Identify decloaked targets
+                if new_target.essid_known and not old_target.essid_known:
+                    new_target.decloaked = True
+                old_target.transfer_info(new_target)
+            elif new_target.bssid in target_archives:
+                # If the new_target is not in old_targets, check target_archives
                 target_archives[new_target.bssid].transfer_info(new_target)
 
         # Check targets for WPS
@@ -237,18 +231,22 @@ def get_targets_from_csv(csv_filename):
         targets2 = []
         import csv
 
+        # Detect encoding from first 4KB sample to avoid reading entire file twice
         try:
             import chardet
-            with open(csv_filename, "rb") as rawdata:
-                encoding = chardet.detect(rawdata.read())['encoding'] or 'utf-8'
+            with open(csv_filename, 'rb') as rawdata:
+                encoding = chardet.detect(rawdata.read(4096))['encoding'] or 'utf-8'
         except ImportError:
             encoding = 'utf-8'
 
         with open(csv_filename, 'r', encoding=encoding, errors='ignore') as csvopen:
             lines = []
+            has_null = False
             for line in csvopen:
                 if '\0' in line:
-                    log_warning('Airodump', 'Null bytes found in CSV data, stripping them')
+                    if not has_null:
+                        log_warning('Airodump', 'Null bytes found in CSV data, stripping them')
+                        has_null = True
                     line = line.replace('\0', '')
                 lines.append(line)
 
@@ -272,6 +270,12 @@ def get_targets_from_csv(csv_filename):
                 elif row[0].strip() == 'Station MAC':
                     # This is the 'header' for the list of Clients
                     hit_clients = True
+                    # Build BSSID lookup dict for O(1) client-to-target matching
+                    # Use first occurrence per BSSID to match original behavior
+                    targets_by_bssid = {}
+                    for t in targets2:
+                        if t.bssid not in targets_by_bssid:
+                            targets_by_bssid[t.bssid] = t
                     continue
 
                 if hit_clients:
@@ -286,11 +290,10 @@ def get_targets_from_csv(csv_filename):
                         # Ignore unassociated clients
                         continue
 
-                    # Add this client to the appropriate Target
-                    for t in targets2:
-                        if t.bssid == client.bssid:
-                            t.clients.append(client)
-                            break
+                    # Add this client to the appropriate Target (O(1) dict lookup)
+                    target = targets_by_bssid.get(client.bssid)
+                    if target:
+                        target.clients.append(client)
 
                 else:
                     # The current row corresponds to a 'Target' (router)

wifite/ui/scanner_view.py

@@ -344,7 +344,8 @@ def _format_manufacturer(self, target) -> Text:
 
         # Get OUI (first 3 octets of BSSID)
         oui = ''.join(target.bssid.split(':')[:3])
-        manufacturer = Configuration.manufacturers.get(oui, "Unknown")
+        Configuration.load_manufacturers()
+        manufacturer = Configuration.manufacturers.get(oui, "Unknown") if Configuration.manufacturers else "Unknown"
 
         # Truncate if too long
         max_len = 20

wifite/ui/selector_view.py

@@ -412,6 +412,7 @@ def _format_manufacturer(self, target) -> Text:
 
         # Get OUI (first 3 octets of BSSID)
         oui = ''.join(target.bssid.split(':')[:3])
+        Configuration.load_manufacturers()
         manufacturer = Configuration.manufacturers.get(oui, "Unknown") if Configuration.manufacturers else "Unknown"
 
         # Truncate if too long

wifite/util/process.py

@@ -176,7 +176,7 @@ def __init__(self, command, devnull=False, stdout=PIPE, stderr=PIPE, cwd=None, b
             log_warning('Process', 'Delaying process creation due to high FD usage')
             if Configuration.verbose > 0:
                 Color.pl('{!} {O}Delaying process creation due to high FD usage{W}')
-            time.sleep(0.5)  # Brief delay to allow cleanup to complete
+            time.sleep(0.1)  # Brief delay to allow cleanup to complete
 
         self.out = None
         self.err = None
@@ -447,15 +447,27 @@ def cleanup_zombies():
         except Exception:
             pass
 
+    # Cache for FD count to avoid filesystem scan on every process creation
+    _fd_cache_time = 0
+    _fd_cache_value = -1
+    _FD_CACHE_TTL = 2.0  # seconds
+
     @staticmethod
     def get_open_fd_count():
-        """Get current open file descriptor count from /proc/{pid}/fd"""
+        """Get current open file descriptor count from /proc/{pid}/fd (cached with TTL)"""
+        now = time.time()
+        if now - Process._fd_cache_time < Process._FD_CACHE_TTL:
+            return Process._fd_cache_value
         try:
             proc_fd_dir = f'/proc/{os.getpid()}/fd'
             if os.path.exists(proc_fd_dir):
-                return len(os.listdir(proc_fd_dir))
+                Process._fd_cache_value = len(os.listdir(proc_fd_dir))
+                Process._fd_cache_time = now
+                return Process._fd_cache_value
         except Exception:
             pass
+        Process._fd_cache_value = -1
+        Process._fd_cache_time = now
         return -1
 
     @staticmethod

wifite/util/scanner.py

@@ -108,9 +108,6 @@ def find_targets(self):
                     if self.found_target():
                         return True  # We found the target we want
 
-                    if airodump.pid.poll() is not None:
-                        return True  # Airodump process died
-
                     # Update display based on mode
                     if self.use_tui and self.view:
                         self.view.update_targets(self.targets, airodump.decloaking)
@@ -561,13 +558,13 @@ def _cleanup_memory(self):
 
         # 2. Limit target list size (keep strongest signals)
         if len(self.targets) > self._max_targets:
-            # Sort by power (strongest first)
-            self.targets.sort(key=lambda x: x.power, reverse=True)
+            import heapq
             removed_count = len(self.targets) - self._max_targets
-            self.targets = self.targets[:self._max_targets]
-            
+            # Use heapq.nlargest: O(n log k) vs O(n log n) for full sort
+            self.targets = heapq.nlargest(self._max_targets, self.targets, key=lambda x: x.power)
+
             if Configuration.verbose > 1:
-                Color.pl('{!} {O}Trimmed %d weak targets (limit: %d){W}' % 
+                Color.pl('{!} {O}Trimmed %d weak targets (limit: %d){W}' %
                         (removed_count, self._max_targets))
 
         # 3. Clean up old archived targets with time-based expiration