feat: iplist2rule utility command (#1373)

* feat: iplist2rule utility command

Assisted-By: GLM 4.7 via Claude Code
Signed-off-by: Xe Iaso <me@xeiaso.net>

* docs: update CHANGELOG

Signed-off-by: Xe Iaso <me@xeiaso.net>

* chore: fix spelling

Signed-off-by: Xe Iaso <me@xeiaso.net>

* chore: fix spelling again

Signed-off-by: Xe Iaso <me@xeiaso.net>

* feat(iplist2rule): add comment describing how rule was generated

Signed-off-by: Xe Iaso <me@xeiaso.net>

* docs: add iplist2rule docs

Signed-off-by: Xe Iaso <me@xeiaso.net>

* chore: fix spelling

Signed-off-by: Xe Iaso <me@xeiaso.net>

---------

Signed-off-by: Xe Iaso <me@xeiaso.net>

.github/actions/spelling/allow.txt

@@ -18,3 +18,8 @@ clampip
 pseudoprofound
 reimagining
 iocaine
+admins
+fout
+iplist
+NArg
+blocklists

docs/docs/CHANGELOG.md

@@ -11,6 +11,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+- Add iplist2rule tool that lets admins turn an IP address blocklist into an Anubis ruleset.
 - Add Polish locale ([#1292](https://github.com/TecharoHQ/anubis/pull/1309))
 
 <!-- This changes the project to: -->

docs/docs/admin/iplist2rule.mdx

@@ -0,0 +1,50 @@
+---
+title: iplist2rule CLI tool
+---
+
+The `iplist2rule` tool converts IP blocklists into Anubis challenge policies. It reads common IP block list formats and generates the appropriate Anubis policy file for IP address filtering.
+
+## Installation
+
+Install directly with Go
+
+```bash
+go install github.com/TecharoHQ/anubis/utils/cmd/iplist2rule@latest
+```
+
+## Usage
+
+Basic conversion from URL:
+
+```bash
+iplist2rule https://raw.githubusercontent.com/7c/torfilter/refs/heads/main/lists/txt/torfilter-1m-flat.txt filter-tor.yaml
+```
+
+Explicitly allow every IP address on a list:
+
+```bash
+iplist2rule --action ALLOW https://raw.githubusercontent.com/7c/torfilter/refs/heads/main/lists/txt/torfilter-1m-flat.txt filter-tor.yaml
+```
+
+Add weight to requests matching IP addresses on a list:
+
+```bash
+iplist2rule --action WEIGH --weight 20 https://raw.githubusercontent.com/7c/torfilter/refs/heads/main/lists/txt/torfilter-1m-flat.txt filter-tor.yaml
+```
+
+## Options
+
+| Flag          | Description                                                                                      | Default                           |
+| :------------ | :----------------------------------------------------------------------------------------------- | :-------------------------------- |
+| `--action`    | The Anubis action to take for the IP address in question, must be in ALL CAPS.                   | `DENY` (forbids traffic)          |
+| `--rule-name` | The name for the generated Anubis rule, should be in kebab-case.                                 | (not set, inferred from filename) |
+| `--weight`    | When `--action=WEIGH`, how many weight points should be added or removed from matching requests? | 0 (not set)                       |
+
+## Using the Generated Policy
+
+Save the output and import it in your main policy file:
+
+```yaml
+bots:
+  - import: "./filter-tor.yaml"
+```

docs/docs/admin/robots2policy.mdx

@@ -12,6 +12,7 @@ Install directly with Go:
 ```bash
 go install github.com/TecharoHQ/anubis/cmd/robots2policy@latest
 ```
+
 ## Usage
 
 Basic conversion from URL:
@@ -35,8 +36,8 @@ robots2policy -input robots.txt -action DENY -format json
 ## Options
 
 | Flag                  | Description                                                        | Default             |
-|-----------------------|--------------------------------------------------------------------|---------------------|
+| --------------------- | ------------------------------------------------------------------ | ------------------- |
-| `-input`              | robots.txt file path or URL (use `-` for stdin)                    | *required*          |
+| `-input`              | robots.txt file path or URL (use `-` for stdin)                    | _required_          |
 | `-output`             | Output file (use `-` for stdout)                                   | stdout              |
 | `-format`             | Output format: `yaml` or `json`                                    | `yaml`              |
 | `-action`             | Action for disallowed paths: `ALLOW`, `DENY`, `CHALLENGE`, `WEIGH` | `CHALLENGE`         |
@@ -47,6 +48,7 @@ robots2policy -input robots.txt -action DENY -format json
 ## Example
 
 Input robots.txt:
+
 ```txt
 User-agent: *
 Disallow: /admin/
@@ -57,6 +59,7 @@ Disallow: /
 ```
 
 Generated policy:
+
 ```yaml
 - name: robots-txt-policy-disallow-1
   action: CHALLENGE
@@ -77,8 +80,8 @@ Generated policy:
 Save the output and import it in your main policy file:
 
 ```yaml
-import:
+bots:
-  - path: "./robots-policy.yaml"
+  - import: "./robots-policy.yaml"
 ```
 
 The tool handles wildcard patterns, user-agent specific rules, and blacklisted bots automatically.

utils/cmd/iplist2rule/blocklist.go

@@ -0,0 +1,57 @@
+package main
+
+import (
+	"bufio"
+	"fmt"
+	"io"
+	"net/http"
+	"net/netip"
+	"strings"
+)
+
+// FetchBlocklist reads the blocklist over HTTP and returns every non-commented
+// line parsed as an IP address in CIDR notation. IPv4 addresses are returned as
+// /32, IPv6 addresses as /128.
+//
+// This function was generated with GLM 4.7.
+func FetchBlocklist(url string) ([]string, error) {
+	resp, err := http.Get(url)
+	if err != nil {
+		return nil, err
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode != http.StatusOK {
+		return nil, fmt.Errorf("HTTP request failed with status: %s", resp.Status)
+	}
+
+	var lines []string
+	scanner := bufio.NewScanner(resp.Body)
+	for scanner.Scan() {
+		line := scanner.Text()
+		// Skip empty lines and comments (lines starting with #)
+		if line == "" || strings.HasPrefix(line, "#") {
+			continue
+		}
+
+		addr, err := netip.ParseAddr(line)
+		if err != nil {
+			// Skip lines that aren't valid IP addresses
+			continue
+		}
+
+		var cidr string
+		if addr.Is4() {
+			cidr = fmt.Sprintf("%s/32", addr.String())
+		} else {
+			cidr = fmt.Sprintf("%s/128", addr.String())
+		}
+		lines = append(lines, cidr)
+	}
+
+	if err := scanner.Err(); err != nil && err != io.EOF {
+		return nil, err
+	}
+
+	return lines, nil
+}

utils/cmd/iplist2rule/main.go

@@ -0,0 +1,103 @@
+package main
+
+import (
+	"flag"
+	"fmt"
+	"log"
+	"os"
+	"path/filepath"
+	"strings"
+	"time"
+
+	"github.com/TecharoHQ/anubis/lib/config"
+	"github.com/facebookgo/flagenv"
+	"sigs.k8s.io/yaml"
+)
+
+type Rule struct {
+	Name       string         `yaml:"name" json:"name"`
+	Action     config.Rule    `yaml:"action" json:"action"`
+	RemoteAddr []string       `json:"remote_addresses,omitempty" yaml:"remote_addresses,omitempty"`
+	Weight     *config.Weight `json:"weight,omitempty" yaml:"weight,omitempty"`
+}
+
+func init() {
+	flag.Usage = func() {
+		fmt.Printf(`Usage of %[1]s:
+
+	%[1]s [flags] <blocklist-url> <filename>
+
+Grabs the contents of the blocklist, converts it to an Anubis ruleset, and writes it to filename.
+
+Flags:
+`, filepath.Base(os.Args[0]))
+
+		flag.PrintDefaults()
+	}
+}
+
+var (
+	action         = flag.String("action", "DENY", "Anubis action to take (ALLOW / DENY / WEIGH)")
+	manualRuleName = flag.String("rule-name", "", "If set, prefer this name over inferring from filename")
+	weight         = flag.Int("weight", 0, "If set to any number, add/subtract this many weight points when --action=WEIGH")
+)
+
+func main() {
+	flagenv.Parse()
+	flag.Parse()
+
+	if flag.NArg() != 2 {
+		flag.Usage()
+		os.Exit(2)
+	}
+
+	blocklistURL := flag.Arg(0)
+	foutName := flag.Arg(1)
+	ruleName := strings.TrimSuffix(foutName, filepath.Ext(foutName))
+
+	if *manualRuleName != "" {
+		ruleName = *manualRuleName
+	}
+
+	ruleAction := config.Rule(*action)
+	if err := ruleAction.Valid(); err != nil {
+		log.Fatalf("--action=%q is invalid: %v", *action, err)
+	}
+
+	result := &Rule{
+		Name:   ruleName,
+		Action: ruleAction,
+	}
+
+	if *weight != 0 {
+		if ruleAction != config.RuleWeigh {
+			log.Fatalf("used --weight=%d but --action=%s", *weight, *action)
+		}
+
+		result.Weight = &config.Weight{
+			Adjust: *weight,
+		}
+	}
+
+	ips, err := FetchBlocklist(blocklistURL)
+	if err != nil {
+		log.Fatalf("can't fetch blocklist %s: %v", blocklistURL, err)
+	}
+
+	result.RemoteAddr = ips
+
+	fout, err := os.Create(foutName)
+	if err != nil {
+		log.Fatalf("can't create output file %q: %v", foutName, err)
+	}
+	defer fout.Close()
+
+	fmt.Fprintf(fout, "# Generated by %s on %s from %s\n\n", filepath.Base(os.Args[0]), time.Now().Format(time.RFC3339), blocklistURL)
+
+	data, err := yaml.Marshal([]*Rule{result})
+	if err != nil {
+		log.Fatalf("can't marshal yaml")
+	}
+
+	fout.Write(data)
+}