From 4bb609fffc45aaf303e00f339cf635c4b529abf0 Mon Sep 17 00:00:00 2001
From: eltrac <hi@eltr.ac>
Date: Fri, 11 Sep 2026 17:04:36 +0800
Subject: refactor(receiver, webhook, utils): replace commons validator

used java.net to create a small validator that passes the test

refactor: rename validator to url, and move other url funcs here
---
 src/weepinbell/feed.clj                |  2 +-
 src/weepinbell/receiver.clj            |  2 +-
 src/weepinbell/retriever.clj           |  2 +-
 src/weepinbell/storage/edn_storage.clj |  2 +-
 src/weepinbell/utils.clj               | 18 ------------------
 src/weepinbell/utils/url.clj           | 26 ++++++++++++++++++++++++++
 src/weepinbell/webhook.clj             |  2 +-
 7 files changed, 31 insertions(+), 23 deletions(-)
 create mode 100644 src/weepinbell/utils/url.clj

(limited to 'src')

diff --git a/src/weepinbell/feed.clj b/src/weepinbell/feed.clj
index c28e0f9..7f1963d 100644
--- a/src/weepinbell/feed.clj
+++ b/src/weepinbell/feed.clj
@@ -1,6 +1,6 @@
 (ns weepinbell.feed
   (:require [clj-rss.core :as rss]
-            [weepinbell.utils :refer [get-domain]]
+            [weepinbell.utils.url :refer [get-domain]]
             [weepinbell.utils.digest :refer [md5-hash]])
   (:import [java.time Instant]))
 
diff --git a/src/weepinbell/receiver.clj b/src/weepinbell/receiver.clj
index 21433ee..bf4bce7 100644
--- a/src/weepinbell/receiver.clj
+++ b/src/weepinbell/receiver.clj
@@ -2,7 +2,7 @@
   "Receiver receives Webmention request (a source and a target); verify the request; return error message if any; push Webmention into queue of processor."
   (:require [clojure.string :as string]
             [clojure.core.async :refer [put!]]
-            [weepinbell.utils :refer [valid-http-url? get-domain]]
+            [weepinbell.utils.url :refer [get-domain valid-http-url?]]
             [weepinbell.utils.digest :refer [md5-hash]]))
 
 ;; utilities
diff --git a/src/weepinbell/retriever.clj b/src/weepinbell/retriever.clj
index ce9fcfd..1bcd959 100644
--- a/src/weepinbell/retriever.clj
+++ b/src/weepinbell/retriever.clj
@@ -1,5 +1,5 @@
 (ns weepinbell.retriever
-  (:require [weepinbell.utils :refer [get-domain]]
+  (:require [weepinbell.utils.url :refer [get-domain]]
             [weepinbell.microformats-wrapper :as mf-wrapper]))
 
 (def default-page-size 12)
diff --git a/src/weepinbell/storage/edn_storage.clj b/src/weepinbell/storage/edn_storage.clj
index 436d2be..ca2d9b7 100644
--- a/src/weepinbell/storage/edn_storage.clj
+++ b/src/weepinbell/storage/edn_storage.clj
@@ -1,6 +1,6 @@
 (ns weepinbell.storage.edn-storage
   (:require [clojure.edn :as edn]
-            [weepinbell.utils :refer [get-domain get-target get-path]]
+            [weepinbell.utils.url :refer [get-domain get-target get-path]]
             [clojure.java.io :as io]
             [clojure.string :refer [join]]))
 
diff --git a/src/weepinbell/utils.clj b/src/weepinbell/utils.clj
index 78068ef..9c279b7 100644
--- a/src/weepinbell/utils.clj
+++ b/src/weepinbell/utils.clj
@@ -1,28 +1,10 @@
 (ns weepinbell.utils
-  (:import [org.apache.commons.validator.routines UrlValidator]
-           [java.net URI])
   (:require [org.httpkit.client :as hk]
             [clojure.string :as string]
             [clojure.walk :as walk]
             [clojure.java.io :as io]
             [taoensso.timbre :as timbre]))
 
-(defn get-domain [url]
-  (when (some? url)
-    (-> url URI/create .getHost)))
-
-(defn get-path [url]
-  (when (some? url)
-    (-> url URI/create .getPath)))
-
-(defn get-target [wm]
-  (get-in wm [:webmention :target]))
-
-(defn valid-http-url? [url]
-  (let [schemes (into-array String ["http" "https"])
-        validator (UrlValidator. schemes)]
-    (.isValid validator url)))
-
 (defn javamap->map [map]
   (->> (seq map) (into {}) walk/keywordize-keys))
 
diff --git a/src/weepinbell/utils/url.clj b/src/weepinbell/utils/url.clj
new file mode 100644
index 0000000..1e47b82
--- /dev/null
+++ b/src/weepinbell/utils/url.clj
@@ -0,0 +1,26 @@
+(ns weepinbell.utils.url
+  (:import [java.net URL URI MalformedURLException URISyntaxException IDN])
+  (:require [clojure.string :as string]))
+
+(defn valid-http-url? [url-string]
+  (try 
+    (let [url (URL. url-string)
+          uri (.toURI url)
+          scheme (.getScheme uri)
+          host (. IDN toASCII (-> url .getHost (string/replace "www." "")))]
+      (and (string/includes? host ".") ;; do not accept localhost and other non-TLD names
+           (or (= scheme "http") (= scheme "https"))))
+    (catch MalformedURLException _ false)
+    (catch URISyntaxException _ false)))
+
+(defn get-domain [url]
+  (when (some? url)
+    (-> url URI/create .getHost)))
+
+(defn get-path [url]
+  (when (some? url)
+    (-> url URI/create .getPath)))
+
+(defn get-target [wm]
+  (get-in wm [:webmention :target]))
+
diff --git a/src/weepinbell/webhook.clj b/src/weepinbell/webhook.clj
index 0090243..58583b0 100644
--- a/src/weepinbell/webhook.clj
+++ b/src/weepinbell/webhook.clj
@@ -1,7 +1,7 @@
 (ns weepinbell.webhook
   (:require [org.httpkit.client :as hk]
             [taoensso.timbre :as timbre]
-            [weepinbell.utils :refer [valid-http-url?]]))
+            [weepinbell.utils.url :refer [valid-http-url?]]))
 
 (defn trigger
   "Send requests to a list of webhooks."
-- 
cgit v1.2.3