wordlistxpl 2.0.0__py3-none-any.whl

wlf/__init__.py

@@ -0,0 +1,5 @@
+"""WordlistXPL-Forge — unified wordlist generation."""
+from wlf.cli.context import VERSION
+from wlf.cli.main import main
+
+__all__ = ["main", "VERSION"]

wlf/__main__.py

@@ -0,0 +1,4 @@
+"""Allow running as: python -m wlf"""
+from wlf.cli.main import main
+
+main()

wlf/cli/__init__.py

@@ -0,0 +1 @@
+"""WordlistXPL-Forge CLI package."""

wlf/cli/config.py

@@ -0,0 +1,143 @@
+"""Persistent configuration file support (~/.wlf/config.yaml)."""
+from __future__ import annotations
+
+import os
+from pathlib import Path
+from typing import Any
+
+_CONFIG_DIR = Path(os.environ.get("WLF_CONFIG_DIR", "~/.wlf")).expanduser()
+_CONFIG_FILE = _CONFIG_DIR / "config.yaml"
+
+DEFAULTS: dict[str, Any] = {
+    "threads": 5,
+    "compute_mode": "auto",
+    "use_ml": True,
+    "limit": 0,
+    "timeout": 0,
+    "min_len": 0,
+    "max_len": 0,
+    "ram_budget_pct": 50.0,
+    "vram_budget_mb": 4096,
+    "chunk_lines": 0,
+    "chunk_bytes": 0,
+    "stream": False,
+    "locale": "en",
+    "model_dir": "",
+    "output_dir": "",
+}
+
+_TEMPLATE = """\
+# WordlistXPL-Forge configuration
+# Persistent defaults — CLI flags always override these values.
+# Location: ~/.wlf/config.yaml  (override with WLF_CONFIG_DIR env var)
+
+# ── Execution ────────────────────────────────────────────────────────────────
+threads: 5                  # Worker threads (1-300)
+compute_mode: auto          # cpu | gpu | cuda | rocm | mps | auto | hybrid
+use_ml: true                # Enable ML-powered engines globally
+
+# ── Limits ───────────────────────────────────────────────────────────────────
+limit: 0                    # Global line limit (0 = unlimited)
+timeout: 0                  # Global timeout in seconds (0 = unlimited)
+min_len: 0                  # Minimum entry length (0 = no filter)
+max_len: 0                  # Maximum entry length (0 = no filter)
+
+# ── Resources ────────────────────────────────────────────────────────────────
+ram_budget_pct: 50.0        # Max % of system RAM for ResourceGovernor
+vram_budget_mb: 4096        # Max VRAM budget in MB for GPU engines
+chunk_lines: 0              # Chunk size in lines (0 = auto)
+chunk_bytes: 0              # Chunk size in bytes (0 = auto)
+stream: false               # Stream output to stdout instead of buffering
+
+# ── Locale ───────────────────────────────────────────────────────────────────
+locale: en                  # Default locale (en, pt-br, es, fr, de)
+
+# ── Paths ────────────────────────────────────────────────────────────────────
+model_dir: ""               # Directory for ML model checkpoints
+output_dir: ""              # Default output directory for generated wordlists
+"""
+
+
+def config_dir() -> Path:
+    """Return the configuration directory path."""
+    return _CONFIG_DIR
+
+
+def config_path() -> Path:
+    """Return the configuration file path."""
+    return _CONFIG_FILE
+
+
+def load_config() -> dict[str, Any]:
+    """Load config from ~/.wlf/config.yaml, returning DEFAULTS on any error."""
+    cfg = dict(DEFAULTS)
+    if not _CONFIG_FILE.is_file():
+        return cfg
+    try:
+        import yaml
+    except ImportError:
+        try:
+            text = _CONFIG_FILE.read_text(encoding="utf-8")
+            cfg.update(_parse_simple_yaml(text))
+        except Exception:
+            pass
+        return cfg
+    try:
+        raw = yaml.safe_load(_CONFIG_FILE.read_text(encoding="utf-8"))
+        if isinstance(raw, dict):
+            for key in DEFAULTS:
+                if key in raw and raw[key] is not None:
+                    cfg[key] = type(DEFAULTS[key])(raw[key])
+    except Exception:
+        pass
+    return cfg
+
+
+def _parse_simple_yaml(text: str) -> dict[str, Any]:
+    """Minimal key: value parser for when PyYAML is not installed."""
+    result: dict[str, Any] = {}
+    for line in text.splitlines():
+        line = line.split("#", 1)[0].strip()
+        if not line or ":" not in line:
+            continue
+        key, _, val = line.partition(":")
+        key = key.strip()
+        val = val.strip()
+        if key not in DEFAULTS:
+            continue
+        default = DEFAULTS[key]
+        if isinstance(default, bool):
+            result[key] = val.lower() in ("true", "yes", "1", "on")
+        elif isinstance(default, int):
+            try:
+                result[key] = int(val)
+            except ValueError:
+                pass
+        elif isinstance(default, float):
+            try:
+                result[key] = float(val)
+            except ValueError:
+                pass
+        else:
+            if val.startswith(('"', "'")) and len(val) >= 2:
+                val = val[1:-1]
+            result[key] = val
+    return result
+
+
+def init_config(force: bool = False) -> Path:
+    """Create default config file. Returns the path written."""
+    _CONFIG_DIR.mkdir(parents=True, exist_ok=True)
+    if _CONFIG_FILE.exists() and not force:
+        raise FileExistsError(f"Config already exists: {_CONFIG_FILE}")
+    _CONFIG_FILE.write_text(_TEMPLATE, encoding="utf-8")
+    return _CONFIG_FILE
+
+
+def apply_config_to_ctx(ctx: dict[str, Any], cfg: dict[str, Any]) -> None:
+    """Merge config values into _GLOBAL_CTX as defaults (CLI overrides later)."""
+    for key in ("threads", "compute_mode", "use_ml", "limit", "timeout",
+                "min_len", "max_len", "ram_budget_pct", "vram_budget_mb",
+                "chunk_lines", "chunk_bytes", "stream"):
+        if key in cfg:
+            ctx[key] = cfg[key]

wlf/cli/context.py

@@ -0,0 +1,101 @@
+"""Global execution context, constants, and terminal output setup."""
+from __future__ import annotations
+
+import logging
+import signal
+import sys
+import types
+from pathlib import Path
+from typing import Any
+
+# ── Colorama ─────────────────────────────────────────────────────────────────
+try:
+    from colorama import Fore, Style, init as colorama_init
+    colorama_init(autoreset=True)
+    _COLOR = True
+except ImportError:
+    _COLOR = False
+    class Fore:  # type: ignore[no-redef]
+        CYAN = GREEN = YELLOW = RED = MAGENTA = WHITE = RESET = ""
+    class Style:  # type: ignore[no-redef]
+        BRIGHT = RESET_ALL = ""
+
+# ── tqdm ─────────────────────────────────────────────────────────────────────
+try:
+    from tqdm import tqdm as _tqdm
+    _TQDM = True
+except ImportError:
+    _TQDM = False
+    _tqdm = None
+
+# ── Path setup ───────────────────────────────────────────────────────────────
+_HERE = Path(__file__).resolve().parent.parent.parent
+sys.path.insert(0, str(_HERE))
+
+logging.basicConfig(
+    level=logging.WARNING,
+    format="%(levelname)s %(name)s: %(message)s",
+)
+logger = logging.getLogger("wlf")
+
+VERSION = "2.0.0"
+
+# ── Graceful shutdown ────────────────────────────────────────────────────────
+_SHUTDOWN_REQUESTED = False
+
+
+def _signal_handler(signum: int, frame: types.FrameType | None) -> None:
+    """Handle SIGINT/SIGTERM for graceful shutdown."""
+    global _SHUTDOWN_REQUESTED
+    _SHUTDOWN_REQUESTED = True
+    print(f"\n{Fore.YELLOW}[!]{Style.RESET_ALL} Shutdown requested - finishing current batch...")
+
+
+signal.signal(signal.SIGINT, _signal_handler)
+if hasattr(signal, "SIGTERM"):
+    signal.signal(signal.SIGTERM, _signal_handler)
+
+
+def is_shutdown() -> bool:
+    """Check if a graceful shutdown has been requested."""
+    return _SHUTDOWN_REQUESTED
+
+
+# ── Global execution context ─────────────────────────────────────────────────
+_GLOBAL_CTX: dict[str, Any] = {
+    "threads":      5,      # thread count (1-300)
+    "compute_mode": "auto", # cpu | gpu | cuda | rocm | mps | auto | hybrid
+    "use_ml":       True,   # ML enabled globally
+    "limit":        0,      # global line limit (0=unlimited)
+    "timeout":      0,      # global timeout in seconds (0=unlimited)
+    "start_time":   0.0,    # epoch when execution started
+    "min_len":      0,      # global minimum entry length (0=no filter)
+    "max_len":      0,      # global maximum entry length (0=no filter)
+    "ram_budget_pct": 50.0,
+    "min_available_ram_mb": 512,
+    "vram_budget_mb": 4096,
+    "chunk_lines": 0,
+    "chunk_bytes": 0,
+    "gov_poll_every": 10_000,
+    "enforce_safe_default": False,
+    "safe_default_max": 5_000_000,
+    "stream": False,
+}
+
+
+_BANNER_ART = (
+    " __          _______ _    _         \n"
+    r" \ \        / /  ____| |  | |        " + "\n"
+    r"  \ \  /\  / /| |__  | |__| |       " + "\n"
+    r"   \ \/  \/ / |  __| |  __  |       " + "\n"
+    r"    \  /\  /  | |    | |  | |       " + "\n"
+    r"     \/  \/   |_|    |_|  |_|       " + "\n"
+)
+BANNER = (
+    f"\n{Fore.CYAN}{Style.BRIGHT}\n"
+    + _BANNER_ART
+    + f"\n  WordlistXPL-Forge  v{VERSION}\n"
+    + "  Author: André Henrique (@mrhenrike)\n"
+    + "  Unified wordlist generation for pentest & red team\n"
+    + f"{Style.RESET_ALL}"
+)

wlf/cli/handlers/__init__.py

@@ -0,0 +1,106 @@
+"""Command handlers — re-export from category modules."""
+from wlf.cli.handlers.generation import (  # noqa: F401
+    cmd_charset,
+    cmd_pattern,
+    cmd_mutate,
+    cmd_num2text,
+    cmd_phrase,
+    cmd_leet,
+    cmd_leet_perm,
+    cmd_combiner,
+    cmd_pcfg,
+    cmd_markov,
+    cmd_kwalk,
+    cmd_rule_mine,
+    cmd_finetune_data,
+    cmd_nflow,
+    cmd_combo,
+    cmd_corp_conv,
+    cmd_phonetic,
+    cmd_prince,
+    cmd_br_names,
+    cmd_iwlgen,
+    cmd_neural,
+    cmd_passphrase,
+    cmd_br_deep,
+    cmd_locale,
+    cmd_pbmp,
+    cmd_evolve,
+    cmd_graph_expand,
+    cmd_temporal_model,
+    cmd_domain_pcfg,
+    cmd_vae_interp,
+)
+from wlf.cli.handlers.analysis import (  # noqa: F401
+    cmd_analyze,
+    cmd_compare,
+    cmd_cluster,
+    cmd_entropy,
+    cmd_hcmon,
+    cmd_hibp,
+    cmd_intelx,
+    cmd_maskgen,
+    cmd_password_dna,
+    cmd_dna_extract,
+    cmd_cover,
+    cmd_benchmark,
+    cmd_maya_rank,
+    cmd_pattern_rank,
+    cmd_anomaly_score,
+    cmd_strength,
+    cmd_hash_id,
+    cmd_hash_gen,
+    cmd_hcmask,
+    cmd_evaluate,
+    cmd_score,
+    cmd_explain_cmd,
+)
+from wlf.cli.handlers.osint import (  # noqa: F401
+    cmd_profile,
+    cmd_corp,
+    cmd_corp_users,
+    cmd_phone,
+    cmd_scrape,
+    cmd_ocr,
+    cmd_extract,
+    cmd_dns,
+    cmd_pharma,
+    cmd_default_creds,
+    cmd_isp_keygen,
+    cmd_corp_prefixes,
+    cmd_osint_perm,
+    cmd_cupp,
+    cmd_scrape_target,
+    cmd_osint,
+)
+from wlf.cli.handlers.ops import (  # noqa: F401
+    cmd_xor,
+    cmd_merge,
+    cmd_sanitize,
+    cmd_reverse,
+    cmd_emit,
+    cmd_replay,
+    cmd_rulegen,
+    cmd_mangle,
+    cmd_improve,
+    cmd_rules,
+    cmd_affix,
+    cmd_dedup,
+    cmd_subtract,
+    cmd_split,
+    cmd_keyspace,
+    cmd_curate,
+    cmd_test,
+)
+from wlf.cli.handlers.infra import (  # noqa: F401
+    cmd_strategy,
+    cmd_bandit,
+    cmd_sysinfo,
+    cmd_train,
+    cmd_pipeline,
+    cmd_session,
+    cmd_serve,
+    cmd_plugin,
+)
+
+__all__ = ['cmd_affix', 'cmd_analyze', 'cmd_anomaly_score', 'cmd_cluster', 'cmd_compare', 'cmd_entropy', 'cmd_hcmon', 'cmd_hibp', 'cmd_intelx', 'cmd_bandit', 'cmd_benchmark', 'cmd_br_deep', 'cmd_br_names', 'cmd_charset', 'cmd_combo', 'cmd_combiner', 'cmd_corp', 'cmd_corp_conv', 'cmd_corp_prefixes', 'cmd_corp_users', 'cmd_cover', 'cmd_cupp', 'cmd_curate', 'cmd_dedup', 'cmd_default_creds', 'cmd_dna_extract', 'cmd_dns', 'cmd_domain_pcfg', 'cmd_emit', 'cmd_evaluate', 'cmd_evolve', 'cmd_finetune_data', 'cmd_nflow', 'cmd_explain_cmd', 'cmd_extract', 'cmd_graph_expand', 'cmd_hash_gen', 'cmd_hash_id', 'cmd_hcmask', 'cmd_improve', 'cmd_isp_keygen', 'cmd_iwlgen', 'cmd_keyspace', 'cmd_kwalk', 'cmd_leet', 'cmd_leet_perm', 'cmd_locale', 'cmd_mangle', 'cmd_markov', 'cmd_maskgen', 'cmd_maya_rank', 'cmd_merge', 'cmd_mutate', 'cmd_neural', 'cmd_num2text', 'cmd_ocr', 'cmd_osint', 'cmd_osint_perm', 'cmd_passphrase', 'cmd_password_dna', 'cmd_pattern', 'cmd_pattern_rank', 'cmd_pbmp', 'cmd_pcfg', 'cmd_pharma', 'cmd_phone', 'cmd_phonetic', 'cmd_phrase', 'cmd_pipeline', 'cmd_plugin', 'cmd_prince', 'cmd_rule_mine', 'cmd_profile', 'cmd_replay', 'cmd_reverse', 'cmd_rulegen', 'cmd_rules', 'cmd_sanitize', 'cmd_score', 'cmd_scrape', 'cmd_scrape_target', 'cmd_serve', 'cmd_session', 'cmd_split', 'cmd_strategy', 'cmd_strength', 'cmd_subtract', 'cmd_sysinfo', 'cmd_temporal_model', 'cmd_test', 'cmd_train', 'cmd_vae_interp', 'cmd_xor']