#!/bin/bash
# Incremental unauthorized connection checker
# Reads the dedicated unauthorized-connections.log (populated by log-splitter.sh),
# compares against seen-connections.json and authorized-ips.json,
# and outputs structured JSON categorizing IPs as new or returning.
#
# Usage: bash check.sh
#
# Output JSON:
# {
#   "timestamp": "2026-02-16T12:00:00Z",
#   "new_ips": [ { "ip": "...", "first_seen": "...", "reason": "...", ... } ],
#   "returning_ips": [ { "ip": "...", "new_attempts": 3, "latest": "...", ... } ],
#   "total_events": 12,
#   "whitelisted_skipped": 2
# }

set -e

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
SKILL_DIR="$(dirname "$SCRIPT_DIR")"
UNAUTH_LOG="/tmp/openclaw/unauthorized-connections.log"
STATE_DIR="/home/node/.openclaw/workspace-security/memory"
OFFSET_FILE="$STATE_DIR/unauth-check-offset"
SEEN_FILE="$SKILL_DIR/seen-connections.json"
AUTH_FILE="$SKILL_DIR/authorized-ips.json"

mkdir -p "$STATE_DIR"

# Initialize state files if missing
[ ! -s "$SEEN_FILE" ] && echo '{}' > "$SEEN_FILE"
[ ! -s "$AUTH_FILE" ] && echo '{"whitelist":["127.0.0.1","::1","localhost"]}' > "$AUTH_FILE"

# Check log exists
if [ ! -f "$UNAUTH_LOG" ]; then
    echo '{"timestamp":"'"$(date -u +%Y-%m-%dT%H:%M:%SZ)"'","new_ips":[],"returning_ips":[],"total_events":0,"whitelisted_skipped":0}'
    exit 0
fi

FILE_SIZE=$(stat -c%s "$UNAUTH_LOG")

# Read offset
LAST_OFFSET=0
if [ -f "$OFFSET_FILE" ]; then
    LAST_OFFSET=$(cat "$OFFSET_FILE")
fi

# Handle log rotation / truncation
if [ "$LAST_OFFSET" -gt "$FILE_SIZE" ]; then
    LAST_OFFSET=0
fi

BYTES_NEW=$((FILE_SIZE - LAST_OFFSET))

if [ "$BYTES_NEW" -le 0 ]; then
    echo "$FILE_SIZE" > "$OFFSET_FILE"
    echo '{"timestamp":"'"$(date -u +%Y-%m-%dT%H:%M:%SZ)"'","new_ips":[],"returning_ips":[],"total_events":0,"whitelisted_skipped":0}'
    exit 0
fi

# Load whitelist
WHITELIST=$(jq -r '.whitelist[]' "$AUTH_FILE" 2>/dev/null | tr '\n' '|' | sed 's/|$//')

is_whitelisted() {
    local ip="$1"
    [[ "$ip" == "127.0.0.1" || "$ip" == "::1" || "$ip" == "localhost" ]] && return 0
    [ -n "$WHITELIST" ] && echo "$ip" | grep -qE "^($WHITELIST)$" && return 0
    return 1
}

# Parse new log entries into per-IP aggregated data
TMPFILE=$(mktemp)
trap "rm -f $TMPFILE" EXIT

tail -c +"$((LAST_OFFSET + 1))" "$UNAUTH_LOG" > "$TMPFILE"

TOTAL_EVENTS=0
WHITELISTED=0
declare -A IP_EVENTS  # ip -> JSON array of events
declare -A IP_LATEST  # ip -> latest timestamp
declare -A IP_COUNT   # ip -> count of events in this batch

while IFS= read -r line; do
    [ -z "$line" ] && continue
    TOTAL_EVENTS=$((TOTAL_EVENTS + 1))

    # Extract fields from JSON log line
    PARSED=$(echo "$line" | jq -r '
        [
            .time // "",
            (.["1"].forwardedFor // ""),
            (.["1"].authReason // .["1"].reason // .["1"].cause // ""),
            (.["1"].origin // ""),
            (.["1"].userAgent // ""),
            ((.["2"] // "") | tostring | (capture("remote=(?<r>[0-9.]+)") | .r) // "")
        ] | @tsv
    ' 2>/dev/null) || continue

    IFS=$'\t' read -r ts ip reason origin ua remote <<< "$PARSED"
    [ -z "$ip" ] && continue

    if is_whitelisted "$ip"; then
        WHITELISTED=$((WHITELISTED + 1))
        continue
    fi

    # Build event JSON
    EVENT=$(jq -cn \
        --arg ts "$ts" \
        --arg ip "$ip" \
        --arg reason "$reason" \
        --arg origin "$origin" \
        --arg ua "$ua" \
        --arg remote "$remote" \
        '{timestamp:$ts, ip:$ip, reason:$reason, origin:$origin, user_agent:$ua, remote:$remote}')

    # Aggregate by IP
    if [ -z "${IP_EVENTS[$ip]+x}" ]; then
        IP_EVENTS[$ip]="$EVENT"
        IP_COUNT[$ip]=1
    else
        IP_EVENTS[$ip]="${IP_EVENTS[$ip]}"$'\n'"$EVENT"
        IP_COUNT[$ip]=$(( ${IP_COUNT[$ip]} + 1 ))
    fi
    IP_LATEST[$ip]="$ts"

done < "$TMPFILE"

# Categorize IPs as new or returning
NEW_IPS="[]"
RETURNING_IPS="[]"

for ip in "${!IP_EVENTS[@]}"; do
    COUNT=${IP_COUNT[$ip]}
    LATEST=${IP_LATEST[$ip]}

    # Get first event for details
    FIRST_EVENT=$(echo "${IP_EVENTS[$ip]}" | head -1)
    REASON=$(echo "$FIRST_EVENT" | jq -r '.reason')
    ORIGIN=$(echo "$FIRST_EVENT" | jq -r '.origin')
    UA=$(echo "$FIRST_EVENT" | jq -r '.user_agent')
    REMOTE=$(echo "$FIRST_EVENT" | jq -r '.remote')

    # Check if IP was previously seen
    if jq -e --arg ip "$ip" 'has($ip)' "$SEEN_FILE" >/dev/null 2>&1; then
        # Returning IP — update seen record, add to returning list
        PREV_COUNT=$(jq -r --arg ip "$ip" '.[$ip].total_attempts // 0' "$SEEN_FILE")
        NEW_TOTAL=$((PREV_COUNT + COUNT))

        STMP=$(mktemp)
        jq --arg ip "$ip" \
           --arg latest "$LATEST" \
           --argjson count "$NEW_TOTAL" \
           --argjson batch "$COUNT" \
           '.[$ip].last_seen = $latest | .[$ip].total_attempts = $count | .[$ip].attempts_this_batch = $batch' \
           "$SEEN_FILE" > "$STMP" && mv "$STMP" "$SEEN_FILE"

        RETURNING_IPS=$(echo "$RETURNING_IPS" | jq \
            --arg ip "$ip" \
            --arg latest "$LATEST" \
            --argjson new_attempts "$COUNT" \
            --argjson total "$NEW_TOTAL" \
            --arg reason "$REASON" \
            --arg origin "$ORIGIN" \
            --arg ua "$UA" \
            --arg remote "$REMOTE" \
            '. += [{ip:$ip, latest:$latest, new_attempts:$new_attempts, total_attempts:$total, reason:$reason, origin:$origin, user_agent:$ua, remote:$remote}]')
    else
        # New IP — record it, add to new list
        STMP=$(mktemp)
        jq --arg ip "$ip" \
           --arg ts "$LATEST" \
           --arg reason "$REASON" \
           --arg origin "$ORIGIN" \
           --arg ua "$UA" \
           --arg remote "$REMOTE" \
           --argjson count "$COUNT" \
           '. + {($ip): {first_seen: $ts, last_seen: $ts, reason: $reason, origin: $origin, user_agent: $ua, remote: $remote, total_attempts: $count}}' \
           "$SEEN_FILE" > "$STMP" && mv "$STMP" "$SEEN_FILE"

        NEW_IPS=$(echo "$NEW_IPS" | jq \
            --arg ip "$ip" \
            --arg first_seen "$LATEST" \
            --argjson attempts "$COUNT" \
            --arg reason "$REASON" \
            --arg origin "$ORIGIN" \
            --arg ua "$UA" \
            --arg remote "$REMOTE" \
            '. += [{ip:$ip, first_seen:$first_seen, attempts:$attempts, reason:$reason, origin:$origin, user_agent:$ua, remote:$remote}]')
    fi
done

# Save new offset
echo "$FILE_SIZE" > "$OFFSET_FILE"

# Output structured result
jq -n \
    --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
    --argjson new_ips "$NEW_IPS" \
    --argjson returning_ips "$RETURNING_IPS" \
    --argjson total "$TOTAL_EVENTS" \
    --argjson whitelisted "$WHITELISTED" \
    '{
        timestamp: $ts,
        new_ips: $new_ips,
        returning_ips: $returning_ips,
        total_events: $total,
        whitelisted_skipped: $whitelisted
    }'