routewatch/internal/iplist/parse.go

package iplist

import (
	"bufio"
	"encoding/json"
	"errors"
	"fmt"
	"io"
	"net"
	"net/netip"
	"strings"

	"go4.org/netipx"
)

const (
	// commentPrefix starts a comment line in a list file.
	commentPrefix = "#"

	// networkSeparator separates the address and the mask length of a
	// network, as in 192.0.2.0/24.
	networkSeparator = "/"

	// dshieldFieldSeparator separates the fields of a DShield line.
	dshieldFieldSeparator = "\t"

	// spamhausMetadataType is the type of the line that ends a Spamhaus
	// file. That line holds the file's metadata and no network.
	spamhausMetadataType = "metadata"
)

var (
	errUnknownFormat = errors.New("unknown list format")
	errNoNetwork     = errors.New("no network on the line")
	errBadRange      = errors.New("first and last address make no range")
	errNoAddresses   = errors.New("no relay addresses in the document")
)

// parse reads a list file written in format and returns the addresses it
// holds. Anything it cannot read fails the whole file, so a file that is not
// the list, such as an error page, never replaces a good copy.
func parse(r io.Reader, format Format) (*netipx.IPSet, error) {
	switch format {
	case FormatLines:
		return parseLines(r, addAddressOrNetwork)
	case FormatSpamhausJSON:
		return parseLines(r, addSpamhausNetwork)
	case FormatDShield:
		return parseLines(r, addDShieldNetwork)
	case FormatOnionooJSON:
		return parseOnionoo(r)
	default:
		return nil, errUnknownFormat
	}
}

// parseLines reads a list file line by line, skipping blank lines and
// comments, and calls addLine with each other line.
func parseLines(
	r io.Reader, addLine func(*netipx.IPSetBuilder, string) error,
) (*netipx.IPSet, error) {
	var builder netipx.IPSetBuilder

	scanner := bufio.NewScanner(r)

	for lineNumber := 1; scanner.Scan(); lineNumber++ {
		line := strings.TrimSpace(scanner.Text())
		if line == "" || strings.HasPrefix(line, commentPrefix) {
			continue
		}

		err := addLine(&builder, line)
		if err != nil {
			return nil, fmt.Errorf("line %d: %w", lineNumber, err)
		}
	}

	err := scanner.Err()
	if err != nil {
		return nil, err
	}

	return builder.IPSet()
}

// addAddressOrNetwork adds an address, such as 192.0.2.1, or a network, such
// as 192.0.2.0/24, to builder.
func addAddressOrNetwork(builder *netipx.IPSetBuilder, text string) error {
	if strings.Contains(text, networkSeparator) {
		network, err := netip.ParsePrefix(text)
		if err != nil {
			return err
		}

		builder.AddPrefix(network)

		return nil
	}

	addr, err := netip.ParseAddr(text)
	if err != nil {
		return err
	}

	builder.Add(addr)

	return nil
}

// addSpamhausNetwork adds the network on a line of a Spamhaus file to
// builder. The metadata line adds nothing.
func addSpamhausNetwork(builder *netipx.IPSetBuilder, line string) error {
	var entry struct {
		CIDR string `json:"cidr"`
		Type string `json:"type"`
	}

	err := json.Unmarshal([]byte(line), &entry)
	if err != nil {
		return err
	}

	if entry.Type == spamhausMetadataType {
		return nil
	}

	network, err := netip.ParsePrefix(entry.CIDR)
	if err != nil {
		return err
	}

	builder.AddPrefix(network)

	return nil
}

// addDShieldNetwork adds the network on a line of a DShield file to builder.
// The line's first two fields are the network's first and last address.
func addDShieldNetwork(builder *netipx.IPSetBuilder, line string) error {
	firstField, rest, found := strings.Cut(line, dshieldFieldSeparator)
	if !found {
		return errNoNetwork
	}

	lastField, _, _ := strings.Cut(rest, dshieldFieldSeparator)

	first, err := netip.ParseAddr(firstField)
	if err != nil {
		return err
	}

	last, err := netip.ParseAddr(lastField)
	if err != nil {
		return err
	}

	network := netipx.IPRangeFrom(first, last)
	if !network.IsValid() {
		return errBadRange
	}

	builder.AddRange(network)

	return nil
}

// onionooDetails is the part of an Onionoo details document that holds the
// relays' addresses.
//
//nolint:tagliatelle // Onionoo's own field names
type onionooDetails struct {
	Relays []struct {
		ExitAddresses []string `json:"exit_addresses"`
		ORAddresses   []string `json:"or_addresses"`
	} `json:"relays"`
}

// parseOnionoo returns every address in the exit_addresses and or_addresses
// fields of the relays in an Onionoo details document. A document with no
// addresses fails, because the Tor network always has relays.
func parseOnionoo(r io.Reader) (*netipx.IPSet, error) {
	data, err := io.ReadAll(r)
	if err != nil {
		return nil, err
	}

	var details onionooDetails

	err = json.Unmarshal(data, &details)
	if err != nil {
		return nil, err
	}

	var builder netipx.IPSetBuilder

	for _, relay := range details.Relays {
		for _, text := range relay.ExitAddresses {
			err = addAddress(&builder, text)
			if err != nil {
				return nil, err
			}
		}

		for _, text := range relay.ORAddresses {
			err = addAddressWithPort(&builder, text)
			if err != nil {
				return nil, err
			}
		}
	}

	addresses, err := builder.IPSet()
	if err != nil {
		return nil, err
	}

	if len(addresses.Ranges()) == 0 {
		return nil, errNoAddresses
	}

	return addresses, nil
}

// addAddress adds an address, such as 192.0.2.1, to builder.
func addAddress(builder *netipx.IPSetBuilder, text string) error {
	addr, err := netip.ParseAddr(text)
	if err != nil {
		return err
	}

	builder.Add(addr)

	return nil
}

// addAddressWithPort adds the address of text, such as 192.0.2.1:443 or
// [2001:db8::1]:443, to builder. Onionoo allows a list of ports after the
// address, so the part after the address is not read.
func addAddressWithPort(builder *netipx.IPSetBuilder, text string) error {
	host, _, err := net.SplitHostPort(text)
	if err != nil {
		return err
	}

	return addAddress(builder, host)
}