From bb94fb41b198b78566d0ab8400d31ccb3e5bc142 Mon Sep 17 00:00:00 2001
From: Edward Loveall <edward@edwardloveall.com>
Date: Mon, 11 Oct 2021 11:56:28 -0400
Subject: [PATCH] Support medium's redirectUrl query param

When a post has a gi= query param, Medium makes a global_identifier
"query". This redirects via a 307 temporary redirect to a url that
looks like this:

https://medium.com/m/global-identity?redirectUrl=https%3A%2F%2Fexample.c
om%2Fmy-post-000000000000

Previously, scribe looked for the Medium post id in the url's path, not
it's query params since query params can include other garbage like
medium_utm (not related to medium.com). Now it looks first for the post
id in the path, then looks to the redirectUrl as a fallback.
---
 spec/requests/articles/show_spec.cr |  6 ++++++
 src/actions/articles/show.cr        | 22 ++++++++++++++++++----
 2 files changed, 24 insertions(+), 4 deletions(-)

diff --git a/spec/requests/articles/show_spec.cr b/spec/requests/articles/show_spec.cr
index 56ad415..0a2fadc 100644
--- a/spec/requests/articles/show_spec.cr
+++ b/spec/requests/articles/show_spec.cr
@@ -68,4 +68,10 @@ describe Articles::Show do
 
     TestClient.last_post_id.should eq("777777abcdef")
   end
+
+  it "parses the post id for global identity redirects" do
+    HttpClient.get("/m/global-identity?redirectUrl=https%3A%2F%2Fexample.com%2Fmy-post-888888abcdef")
+
+    TestClient.last_post_id.should eq("888888abcdef")
+  end
 end
diff --git a/src/actions/articles/show.cr b/src/actions/articles/show.cr
index 8bf9fa7..98cde52 100644
--- a/src/actions/articles/show.cr
+++ b/src/actions/articles/show.cr
@@ -2,10 +2,10 @@ require "json"
 
 class Articles::Show < BrowserAction
   fallback do
-    maybe_post_id = post_id(context.request.path)
-    case maybe_post_id
+    post_id = maybe_post_id(context.request)
+    case post_id
     in Monads::Just
-      response = client_class.post_data(maybe_post_id.value!)
+      response = client_class.post_data(post_id.value!)
       page = PageConverter.new.convert(response.data)
       html ShowPage, page: page
     in Monads::Nothing, Monads::Maybe
@@ -17,13 +17,27 @@ class Articles::Show < BrowserAction
     end
   end
 
-  def post_id(request_path : String)
+  def maybe_post_id(request : HTTP::Request)
+    from_params = post_id_from_params(request.query_params)
+    from_path = post_id_from_path(request.path)
+    from_path.or(from_params)
+  end
+
+  def post_id_from_path(request_path : String)
     Monads::Try(Regex::MatchData)
       .new(->{ request_path.match(/([0-9a-f]+)$/i) })
       .to_maybe
       .fmap(->(matches : Regex::MatchData) { matches[1] })
   end
 
+  def post_id_from_params(params : URI::Params)
+    maybe_uri = Monads::Try(String)
+      .new(->{ params["redirectUrl"] })
+      .to_maybe
+      .fmap(->(url : String) { URI.parse(url) })
+      .bind(->(uri : URI) { post_id_from_path(uri.path) })
+  end
+
   def client_class
     if Lucky::Env.use_local?
       LocalClient