data: add some examples of expression-based rules

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

data/apps/git-client.yaml

@@ -0,0 +1,7 @@
+- name: allow-git-clients
+  action: ALLOW
+  expression:
+    and:
+    - userAgent.startsWith("git/") || userAgent.contains("libgit") || userAgent.startsWith("go-git") || userAgent.startsWith("JGit/") || userAgent.startsWith("JGit-")
+    - >
+      "Git-Protocol" in headers && headers["Git-Protocol"] == "version=2"

data/clients/go-get.yaml

@@ -0,0 +1,7 @@
+- name: go-get
+  action: ALLOW
+  expression:
+    and:
+    - userAgent.startsWith("Go-http-client/")
+    - '"go-get" in query'
+    - query["go-get"] == "1"

data/common/allow-api-like.yaml

@@ -0,0 +1,6 @@
+- name: allow-api-routes
+  action: ALLOW
+  expression:
+    and:
+    - '!(method == "HEAD" || method == "GET")'
+    - path.startsWith("/api/")

data/common/keep-internet-working.yaml

@@ -8,3 +8,6 @@
 - name: robots-txt
   path_regex: ^/robots.txt$
   action: ALLOW
+- name: sitemap
+  path_regex: ^/sitemap.xml$
+  action: ALLOW

data/common/rfc-violations.yaml

@@ -0,0 +1,3 @@
+- name: no-user-agent-string
+  expression: userAgent == ""
+  action: DENY

data/embed.go

@@ -3,6 +3,6 @@ package data
 import "embed"
 
 var (
-	//go:embed botPolicies.yaml botPolicies.json apps bots common crawlers
+	//go:embed botPolicies.yaml botPolicies.json apps bots clients common crawlers
 	BotPolicies embed.FS
 )