Split up AI filtering files (#592)

* Split up AI filtering files

Create aggressive/moderate/permissive policies to allow administrators to choose their AI/LLM stance.

Aggressive policy matches existing default in Anubis.

Removes `Google-Extended` flag from `ai-robots-txt.yaml` as it doesn't exist in requests.

Rename `ai-robots-txt.yaml` to `ai-catchall.yaml` as the file is no longer a copy of the source repo/file.

* chore: spelling

* chore: fix embeds

* chore: fix data includes

* chore: fix file name typo

* chore: Ignore READMEs in configs

* chore(lib/policy/config): go tool goimports -w

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

---------

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

lib/policy/config/config_test.go

@@ -251,6 +251,7 @@ func TestImportStatement(t *testing.T) {
 		"bots",
 		"common",
 		"crawlers",
+		"meta",
 	} {
 		if err := fs.WalkDir(data.BotPolicies, folderName, func(path string, d fs.DirEntry, err error) error {
 			if err != nil {
@@ -259,6 +260,9 @@ func TestImportStatement(t *testing.T) {
 			if d.IsDir() {
 				return nil
 			}
+			if d.Name() == "README.md" {
+				return nil
+			}
 
 			tests = append(tests, testCase{
 				name:       "(data)/" + path,

lib/policy/config/testdata/bad/import_and_bot.json

@@ -1,7 +1,7 @@
 {
   "bots": [
     {
-      "import": "(data)/bots/ai-robots-txt.yaml",
+      "import": "(data)/bots/ai-catchall.yaml",
       "name": "generic-browser",
       "user_agent_regex": "Mozilla|Opera\n",
       "action": "CHALLENGE"

lib/policy/config/testdata/bad/import_and_bot.yaml

@@ -1,5 +1,5 @@
 bots:
-- import: (data)/bots/ai-robots-txt.yaml
+- import: (data)/bots/ai-catchall.yaml
   name: generic-browser
   user_agent_regex: >
     Mozilla|Opera