#!/usr/bin/env python3
"""
Guardrail PreToolUse Hook

Intercepts Bash, Write, and Edit tool calls to prevent dangerous operations.
Returns JSON decision: {"decision": "allow"} or {"decision": "block", "reason": "..."}
"""

import json
import os
import re
import sys
from datetime import datetime, timezone
from pathlib import Path

# Paths
HOME = Path.home()
STATE_DIR = HOME / ".claude" / "state"
LOGS_DIR = HOME / ".claude" / "logs"
CONFIG_FILE = STATE_DIR / "guardrails.json"
SESSION_FILE = STATE_DIR / "guardrail-session.json"
LOG_FILE = LOGS_DIR / "guardrail.jsonl"


def load_config():
    """Load guardrails configuration."""
    if not CONFIG_FILE.exists():
        return None
    with open(CONFIG_FILE) as f:
        return json.load(f)


def load_session_allowlist():
    """Load session allowlist of confirmed operations."""
    if not SESSION_FILE.exists():
        return {"confirmed": []}
    try:
        with open(SESSION_FILE) as f:
            return json.load(f)
    except (json.JSONDecodeError, IOError):
        return {"confirmed": []}


def is_in_allowlist(tool: str, operation: str) -> bool:
    """Check if operation was previously confirmed."""
    allowlist = load_session_allowlist()
    for item in allowlist.get("confirmed", []):
        if item.get("tool") == tool and item.get("operation") == operation:
            return True
    return False


def expand_path(path: str) -> Path:
    """Expand ~ and resolve path."""
    return Path(os.path.expanduser(path)).resolve()


def is_under_path(target: Path, parent: str) -> bool:
    """Check if target is under parent path."""
    try:
        parent_path = expand_path(parent)
        # Handle glob patterns like ~/projects/*
        if "*" in parent:
            # For ~/projects/*, check if under ~/projects
            parent_path = expand_path(parent.replace("/*", "").replace("*", ""))
        return parent_path in target.parents or target == parent_path
    except (ValueError, OSError):
        return False


def is_in_git_repo(path: Path) -> bool:
    """Check if path is inside a git repository."""
    current = path if path.is_dir() else path.parent
    while current != current.parent:
        if (current / ".git").exists():
            return True
        current = current.parent
    return False


def classify_path(target_path: str, config: dict) -> str:
    """
    Classify a path as 'blocked', 'safe', or 'outside'.

    Evaluation order:
    1. Blocked paths -> 'blocked'
    2. Safe paths -> 'safe'
    3. Git repo -> 'safe'
    4. Otherwise -> 'outside'
    """
    try:
        target = expand_path(target_path)
    except (ValueError, OSError):
        return "outside"

    # Check blocked paths first
    for blocked in config.get("blocked_paths", []):
        if is_under_path(target, blocked):
            return "blocked"

    # Check safe paths
    for safe in config.get("safe_paths", []):
        if is_under_path(target, safe):
            return "safe"

    # Check if in git repo
    if is_in_git_repo(target):
        return "safe"

    return "outside"


def extract_paths_from_command(command: str) -> list[str]:
    """Extract potential file paths from a bash command."""
    paths = []
    # Simple heuristic: look for things that look like paths
    # This catches ~/..., /..., and relative paths
    tokens = command.split()
    for token in tokens:
        # Skip flags
        if token.startswith("-"):
            continue
        # Skip common commands
        if token in ("rm", "mv", "cp", "chmod", "chown", "mkdir", "rmdir", "touch"):
            continue
        # Check if it looks like a path
        if "/" in token or token.startswith("~"):
            paths.append(token)
    return paths


def check_bash_rules(command: str, config: dict) -> tuple[str, str | None, str]:
    """
    Check bash command against rules.
    Returns: (action, rule_name, path_context)
    action: 'allow', 'block', or 'confirm'
    """
    rules = config.get("rules", {}).get("bash", [])

    for rule in rules:
        pattern = rule.get("pattern", "")
        action = rule.get("action", "allow")
        name = rule.get("name", "unnamed")
        outside_safe_only = rule.get("outside_safe_paths", False)

        # Check if pattern matches
        if re.search(pattern, command):
            if outside_safe_only:
                # Only apply rule if operating outside safe paths
                paths = extract_paths_from_command(command)
                for path in paths:
                    path_class = classify_path(path, config)
                    if path_class in ("blocked", "outside"):
                        return (action, name, path_class)
                # All paths are safe, allow
                continue
            else:
                # Rule applies regardless of path
                return (action, name, "n/a")

    return ("allow", None, "safe")


def check_file_rules(file_path: str, tool: str, config: dict) -> tuple[str, str | None, str]:
    """
    Check Write/Edit file path against rules.
    Returns: (action, rule_name, path_context)
    """
    rules = config.get("rules", {}).get(tool.lower(), [])
    path_class = classify_path(file_path, config)

    for rule in rules:
        path_match = rule.get("path_match", "")
        action = rule.get("action", "allow")
        name = rule.get("name", "unnamed")

        if path_match == "blocked_paths" and path_class == "blocked":
            return (action, name, path_class)
        elif path_match == "outside_safe_paths" and path_class == "outside":
            return (action, name, path_class)

    return ("allow", None, path_class)


def log_action(tool: str, operation: str, action: str, rule: str | None, path_context: str):
    """Log guardrail action to audit log."""
    LOGS_DIR.mkdir(parents=True, exist_ok=True)

    entry = {
        "ts": datetime.now(timezone.utc).isoformat().replace("+00:00", "Z"),
        "tool": tool,
        "operation": operation[:200],  # Truncate long operations
        "action": action,
        "rule": rule or "none",
        "path_context": path_context
    }

    with open(LOG_FILE, "a") as f:
        f.write(json.dumps(entry) + "\n")


def allow():
    """Return allow decision."""
    print(json.dumps({"decision": "allow"}))
    sys.exit(0)


def block(reason: str):
    """Return block decision with reason."""
    print(json.dumps({"decision": "block", "reason": reason}))
    sys.exit(0)


def main():
    # Read input from stdin
    try:
        input_data = json.load(sys.stdin)
    except json.JSONDecodeError:
        allow()  # If we can't parse input, allow (fail open)

    tool_name = input_data.get("tool_name", "")
    tool_input = input_data.get("tool_input", {})

    # Only check Bash, Write, Edit
    if tool_name not in ("Bash", "Write", "Edit"):
        allow()

    # Load config
    config = load_config()
    if not config:
        allow()  # No config, allow everything

    # Determine operation string for allowlist check
    if tool_name == "Bash":
        operation = tool_input.get("command", "")
    else:
        operation = tool_input.get("file_path", "")

    # Check session allowlist first
    if is_in_allowlist(tool_name, operation):
        log_action(tool_name, operation, "confirmed_allow", "session_allowlist", "n/a")
        allow()

    # Check rules based on tool type
    if tool_name == "Bash":
        action, rule_name, path_context = check_bash_rules(operation, config)
    else:
        action, rule_name, path_context = check_file_rules(operation, tool_name, config)

    # Take action
    if action == "allow":
        allow()

    # Log blocked/confirm actions
    log_action(tool_name, operation, action if action == "block" else "confirm_required", rule_name, path_context)

    # Build block message
    if action == "block":
        reason = f"""GUARDRAIL BLOCKED: Operation not allowed.
Tool: {tool_name}
Operation: {operation}
Rule: {rule_name}
Path context: {path_context}

This operation is blocked by guardrail policy and cannot proceed."""
    else:  # confirm
        confirm_cmd = f'python3 ~/.claude/hooks/scripts/guardrail-confirm.py "{tool_name}" "{operation}"'
        reason = f"""GUARDRAIL: User confirmation required.
Tool: {tool_name}
Operation: {operation}
Rule: {rule_name}
Path context: {path_context}

To proceed after user confirms, run:
{confirm_cmd}

Then retry the original operation."""

    block(reason)


if __name__ == "__main__":
    main()