routewatch/internal/iplist/iplist.go

// Package iplist downloads public IP lists on a schedule, keeps the last good
// copy of each on disk and in memory, and answers which lists contain an
// address.
package iplist

import (
	"context"
	"log/slog"
	"net/netip"
	"sync"
	"time"

	"go4.org/netipx"
)

// Format is how a list's file is written.
type Format int

const (
	// FormatLines has one address or network per line, such as 192.0.2.1 or
	// 192.0.2.0/24. Lines that start with # are comments.
	FormatLines Format = iota

	// FormatSpamhausJSON has one JSON object per line, with a network in its
	// cidr field. The last line holds the file's metadata and no network.
	FormatSpamhausJSON

	// FormatDShield has one network per line, as tab-separated fields that
	// start with the network's first and last address. Lines that start
	// with # are comments.
	FormatDShield

	// FormatOnionooJSON is one Onionoo details document. Its relays have
	// addresses in two fields: exit_addresses, which has IPv4 only, and
	// or_addresses, which has IPv4 and IPv6, each with a port.
	FormatOnionooJSON

	// FormatMullvadJSON is Mullvad's JSON list of relays. A relay's addresses
	// are in ipv4_addr_in, ipv6_addr_in and ipv4_v2ray.
	FormatMullvadJSON

	// FormatNordVPNJSON is NordVPN's JSON list of servers. A server's
	// addresses are in station and ipv6_station.
	FormatNordVPNJSON

	// FormatPIAJSON is Private Internet Access's JSON server list, then a
	// blank line and a signature. Each region's servers has lists of servers
	// by protocol, and each server has its address in ip.
	FormatPIAJSON

	// FormatIVPNJSON is IVPN's JSON server list. The hosts of its wireguard
	// and openvpn gateways have their addresses in host and v2ray.
	FormatIVPNJSON

	// FormatProtonVPN has one address or network per line, with comment lines
	// that start with #. Unlike FormatLines, a file with no addresses or
	// networks fails.
	FormatProtonVPN
)

// List is one public IP list.
type List struct {
	// Name names the list in lookup answers, and names its copy on disk.
	Name string

	// Description says in one line what being on the list means.
	Description string

	// URL is where the publisher serves the whole list.
	URL string

	// Interval is how long a copy is used before the list is downloaded
	// again.
	Interval time.Duration

	// Format is how the list's file is written.
	Format Format

	// VPN says that the list holds servers of VPN services.
	VPN bool
}

// Listing says that a list contains an address.
type Listing struct {
	Name        string `json:"name"`
	Description string `json:"description"`

	// Updated is when routewatch last downloaded the list, or last heard from
	// its publisher that its copy was still current.
	Updated time.Time `json:"updated"`

	// VPN says that the list holds servers of VPN services. A lookup answer
	// reports it through is_vpn and vpn_providers.
	VPN bool `json:"-"`
}

// listCopy is a list's last good copy in memory.
type listCopy struct {
	addresses *netipx.IPSet
	updated   time.Time

	// validators identify the version of the list this copy holds.
	validators validators
}

// Params is what New needs.
type Params struct {
	// Dir is the directory that holds the copies on disk.
	Dir string

	// Lists are the lists to download and look addresses up in.
	Lists []List

	Logger *slog.Logger
}

// IPLists keeps a copy of each list and answers which lists contain an
// address. Start loads the copies from disk and starts downloading the lists.
type IPLists struct {
	dir    string
	lists  []List
	logger *slog.Logger

	// copies holds each list's last good copy, by list name. A list with no
	// good copy yet has none.
	mu     sync.RWMutex
	copies map[string]listCopy

	// stop ends the goroutine Start runs, and done is closed when it returns.
	stop context.CancelFunc
	done chan struct{}
}

// New returns an IPLists with no copies. Start loads them.
func New(params Params) *IPLists {
	return &IPLists{
		dir:    params.Dir,
		lists:  params.Lists,
		logger: params.Logger.With("component", "iplists"),
		copies: make(map[string]listCopy),
		done:   make(chan struct{}),
	}
}

// Lookup returns a Listing for each list whose copy contains addr, in the
// order of the lists given to New. It makes no outside request. When no list
// contains addr, it returns an empty list, not nil.
func (b *IPLists) Lookup(addr netip.Addr) []Listing {
	b.mu.RLock()
	defer b.mu.RUnlock()

	listings := []Listing{}

	for _, list := range b.lists {
		c, ok := b.copies[list.Name]
		if ok && c.addresses.Contains(addr.Unmap()) {
			listings = append(listings, Listing{
				Name:        list.Name,
				Description: list.Description,
				Updated:     c.updated,
				VPN:         list.VPN,
			})
		}
	}

	return listings
}

// ShortestInterval returns the shortest Interval of the lists. That is the
// soonest a copy can change, and so how long a lookup answer stays current.
func (b *IPLists) ShortestInterval() time.Duration {
	var shortest time.Duration

	for i, list := range b.lists {
		if i == 0 || list.Interval < shortest {
			shortest = list.Interval
		}
	}

	return shortest
}

// updated returns when the named list's copy was last downloaded or found
// current, or the zero time when the list has no copy.
func (b *IPLists) updated(name string) time.Time {
	b.mu.RLock()
	defer b.mu.RUnlock()

	return b.copies[name].updated
}

// copyValidators returns the validators of the named list's copy. They are
// empty when the list has no copy.
func (b *IPLists) copyValidators(name string) validators {
	b.mu.RLock()
	defer b.mu.RUnlock()

	return b.copies[name].validators
}

// setCopy makes c the named list's copy.
func (b *IPLists) setCopy(name string, c listCopy) {
	b.mu.Lock()
	defer b.mu.Unlock()

	b.copies[name] = c
}

// setUpdated records that the named list's copy was found current at t.
func (b *IPLists) setUpdated(name string, t time.Time) {
	b.mu.Lock()
	defer b.mu.Unlock()

	c, ok := b.copies[name]
	if ok {
		c.updated = t
		b.copies[name] = c
	}
}