Closes #30 Introduces the "challenge" field in bot rule definitions: ```json { "name": "generic-bot-catchall", "user_agent_regex": "(?i:bot|crawler)", "action": "CHALLENGE", "challenge": { "difficulty": 16, "report_as": 4, "algorithm": "slow" } } ``` This makes Anubis return a challenge page for every user agent with "bot" or "crawler" in it (case-insensitively) with difficulty 16 using the old "slow" algorithm but reporting in the client as difficulty 4. This is useful when you want to make certain clients in particular suffer. Additional validation and testing logic has been added to make sure that users do not define "impossible" challenge settings. If no algorithm is specified, Anubis defaults to the "fast" algorithm. Signed-off-by: Xe Iaso <me@xeiaso.net>
151 lines
3.8 KiB
Go
151 lines
3.8 KiB
Go
package config
|
|
|
|
import (
|
|
"errors"
|
|
"fmt"
|
|
"regexp"
|
|
)
|
|
|
|
type Rule string
|
|
|
|
const (
|
|
RuleUnknown Rule = ""
|
|
RuleAllow Rule = "ALLOW"
|
|
RuleDeny Rule = "DENY"
|
|
RuleChallenge Rule = "CHALLENGE"
|
|
)
|
|
|
|
type Algorithm string
|
|
|
|
const (
|
|
AlgorithmUnknown Algorithm = ""
|
|
AlgorithmFast Algorithm = "fast"
|
|
AlgorithmSlow Algorithm = "slow"
|
|
)
|
|
|
|
type Bot struct {
|
|
Name string `json:"name"`
|
|
UserAgentRegex *string `json:"user_agent_regex"`
|
|
PathRegex *string `json:"path_regex"`
|
|
Action Rule `json:"action"`
|
|
Challenge *ChallengeRules `json:"challenge,omitempty"`
|
|
}
|
|
|
|
var (
|
|
ErrNoBotRulesDefined = errors.New("config: must define at least one (1) bot rule")
|
|
ErrBotMustHaveName = errors.New("config.Bot: must set name")
|
|
ErrBotMustHaveUserAgentOrPath = errors.New("config.Bot: must set either user_agent_regex, path_regex")
|
|
ErrBotMustHaveUserAgentOrPathNotBoth = errors.New("config.Bot: must set either user_agent_regex, path_regex, and not both")
|
|
ErrUnknownAction = errors.New("config.Bot: unknown action")
|
|
ErrInvalidUserAgentRegex = errors.New("config.Bot: invalid user agent regex")
|
|
ErrInvalidPathRegex = errors.New("config.Bot: invalid path regex")
|
|
)
|
|
|
|
func (b Bot) Valid() error {
|
|
var errs []error
|
|
|
|
if b.Name == "" {
|
|
errs = append(errs, ErrBotMustHaveName)
|
|
}
|
|
|
|
if b.UserAgentRegex == nil && b.PathRegex == nil {
|
|
errs = append(errs, ErrBotMustHaveUserAgentOrPath)
|
|
}
|
|
|
|
if b.UserAgentRegex != nil && b.PathRegex != nil {
|
|
errs = append(errs, ErrBotMustHaveUserAgentOrPathNotBoth)
|
|
}
|
|
|
|
if b.UserAgentRegex != nil {
|
|
if _, err := regexp.Compile(*b.UserAgentRegex); err != nil {
|
|
errs = append(errs, ErrInvalidUserAgentRegex, err)
|
|
}
|
|
}
|
|
|
|
if b.PathRegex != nil {
|
|
if _, err := regexp.Compile(*b.PathRegex); err != nil {
|
|
errs = append(errs, ErrInvalidPathRegex, err)
|
|
}
|
|
}
|
|
|
|
switch b.Action {
|
|
case RuleAllow, RuleChallenge, RuleDeny:
|
|
// okay
|
|
default:
|
|
errs = append(errs, fmt.Errorf("%w: %q", ErrUnknownAction, b.Action))
|
|
}
|
|
|
|
if b.Action == RuleChallenge && b.Challenge != nil {
|
|
if err := b.Challenge.Valid(); err != nil {
|
|
errs = append(errs, err)
|
|
}
|
|
}
|
|
|
|
if len(errs) != 0 {
|
|
return fmt.Errorf("config: bot entry for %q is not valid:\n%w", b.Name, errors.Join(errs...))
|
|
}
|
|
|
|
return nil
|
|
}
|
|
|
|
type ChallengeRules struct {
|
|
Difficulty int `json:"difficulty"`
|
|
ReportAs int `json:"report_as"`
|
|
Algorithm Algorithm `json:"algorithm"`
|
|
}
|
|
|
|
var (
|
|
ErrChallengeRuleHasWrongAlgorithm = errors.New("config.Bot.ChallengeRules: algorithm is invalid")
|
|
ErrChallengeDifficultyTooLow = errors.New("config.Bot.ChallengeRules: difficulty is too low (must be >= 1)")
|
|
ErrChallengeDifficultyTooHigh = errors.New("config.Bot.ChallengeRules: difficulty is too high (must be <= 64)")
|
|
)
|
|
|
|
func (cr ChallengeRules) Valid() error {
|
|
var errs []error
|
|
|
|
if cr.Difficulty < 1 {
|
|
errs = append(errs, fmt.Errorf("%w, got: %d", ErrChallengeDifficultyTooLow, cr.Difficulty))
|
|
}
|
|
|
|
if cr.Difficulty > 64 {
|
|
errs = append(errs, fmt.Errorf("%w, got: %d", ErrChallengeDifficultyTooHigh, cr.Difficulty))
|
|
}
|
|
|
|
switch cr.Algorithm {
|
|
case AlgorithmFast, AlgorithmSlow, AlgorithmUnknown:
|
|
// do nothing, it's all good
|
|
default:
|
|
errs = append(errs, fmt.Errorf("%w: %q", ErrChallengeRuleHasWrongAlgorithm, cr.Algorithm))
|
|
}
|
|
|
|
if len(errs) != 0 {
|
|
return fmt.Errorf("config: challenge rules entry is not valid:\n%w", errors.Join(errs...))
|
|
}
|
|
|
|
return nil
|
|
}
|
|
|
|
type Config struct {
|
|
Bots []Bot `json:"bots"`
|
|
DNSBL bool `json:"dnsbl"`
|
|
}
|
|
|
|
func (c Config) Valid() error {
|
|
var errs []error
|
|
|
|
if len(c.Bots) == 0 {
|
|
errs = append(errs, ErrNoBotRulesDefined)
|
|
}
|
|
|
|
for _, b := range c.Bots {
|
|
if err := b.Valid(); err != nil {
|
|
errs = append(errs, err)
|
|
}
|
|
}
|
|
|
|
if len(errs) != 0 {
|
|
return fmt.Errorf("config is not valid:\n%w", errors.Join(errs...))
|
|
}
|
|
|
|
return nil
|
|
}
|