migration: rehash -> re-normalize #81

calculating hash using old unnormalized URLs will most likely produce
the same old invalid hash, this commit normalizes URLs first and then
calculate new hash, updating old URLs as well.

1 files changed, 14 insertions, 8 deletions

diff --git a/src/weepinbell/migration.clj b/src/weepinbell/migration.clj
index 701ed8f..544f5d6 100644
--- a/src/weepinbell/migration.clj
+++ b/src/weepinbell/migration.clj
@@ -6,6 +6,7 @@
             [weepinbell.storage.edn-storage :as edns]

             [weepinbell.storage.spec]

             [weepinbell.metadata.microformats :refer [parse-microformats]]

+            [weepinbell.utils.url :refer [normalize]]

             [weepinbell.utils.digest :refer [digest]]

             [clojure.java.io :as io]

             [fast-edn.core :as edn]))

@@ -19,14 +20,19 @@
       (assoc :jf2 (parse-microformats (:microformats wm)))

       (dissoc :microformats)))

 

-(defn rehash

+(defn re-normalize

   "Given a Webmention object, recalculate its hash and return a new map."

   [wm]

   {:pre [(map? wm) (contains? wm :webmention)]}

-  (assoc wm :webmention

-         (assoc (:webmention wm) :id

-                (digest (str (get-in wm [:webmention :source])

-                             (get-in wm [:webmention :target]))))))

+  (let [{:keys [source target]} (:webmention wm)

+        normal-source (normalize source)

+        normal-target (normalize target)

+        newhash (digest (str normal-source normal-target))]

+    (assoc wm :webmention

+           (-> (:webmention wm)

+               (assoc :source normal-source)

+               (assoc :target normal-target)

+               (assoc :id newhash)))))

 

 (defn edn->h2

   "Given an EDN file and a SQLite DB path, migrate data from that

@@ -42,12 +48,12 @@
       (fn [wms]

         (doseq [wm wms]

           (let [id (get-in wm [:webmention :id])]

-            (println "Appending webmention" id "to database")

             (try

               (let [wm (if (contains? wm :microformats)

                          (mf->jf2 wm) wm)

-                    wm (rehash wm)]

-                (h2/insert-webmention ds wm))

+                    wm (re-normalize wm)]

+                (h2/insert-webmention ds wm)

+                (println id "->" (get-in wm [:webmention :id])))

               (catch Exception e

                 (println "Something unexpected happened.")

                 (println (.getMessage e))))))))