artists: change how artist urls are normalized.

Change how artist URLs are normalized in artist entries. Don't try to secretly
convert image URLs to profile URLs in artist entries. For example, if someone puts a
Pixiv image URL in an artist entry, don't secretly try to fetch the source and
convert it into a profile URL in the `normalized_url` field.

We did this because years ago, it was standard practice to put image URLs in artist
entries. Pixiv image URLs used to contain the artist's username, so we used to put
image URLs in artist entries for artist finding purposes. But Pixiv changed it so
that image URLs no longer contained the username, so we dealt with it by adding a
`normalized_url` column to artist_urls and secretly converting image URLs to profile
URLs in this field. But this is no longer necessary because now we don't normally put
image URLs in artist entries in the first place.

Now the `profile_url` method in `Source::URL` is used to normalize URLs in artist
entries. This lets us parse various profile URL formats and normalize them into a
single canonical form.

This also removes the `normalize_for_artist_finder` method from source strategies.
Instead the `profile_url` method is used for artist finding purposes. So the profile
URL returned by the source strategy needs to be the same as the URL in the artist
entry in order for artist finding to work.

app/logical/sources/strategies/base.rb

@@ -97,7 +97,8 @@ module Sources
         [artist_name, tag_name].compact.uniq
       end
 
-      # A link to the artist's profile page on the site.
+      # A link to the artist's profile page on the site. This will be used for
+      # artist finding purposes, so it needs to match the URL in the artist entry.
       def profile_url
         nil
       end
@@ -137,12 +138,6 @@ module Sources
       end
       memoize :http_downloader
 
-      # The url to use for artist finding purposes. This will be stored in the
-      # artist entry. Normally this will be the profile url.
-      def normalize_for_artist_finder
-        profile_url.presence || url
-      end
-
       # Given a post/image url, this is the normalized url that will be displayed in a post's page in its stead.
       # This function should never make any network call, even indirectly. Return nil to never normalize.
       def normalize_for_source
@@ -150,7 +145,7 @@ module Sources
       end
 
       def artists
-        ArtistFinder.find_artists(normalize_for_artist_finder.to_s)
+        ArtistFinder.find_artists(profile_url.to_s)
       end
 
       # A new artist entry with suggested defaults for when the artist doesn't
@@ -234,7 +229,6 @@ module Sources
           :image_urls => image_urls,
           :page_url => page_url,
           :canonical_url => canonical_url,
-          :normalized_for_artist_finder_url => normalize_for_artist_finder,
           :tags => tags,
           :normalized_tags => normalized_tags,
           :translated_tags => translated_tags,

app/logical/sources/strategies/nico_seiga.rb

@@ -40,10 +40,7 @@ module Sources
       end
 
       def profile_url
-        user_id = api_client&.user_id
-        return if user_id.blank? # artists can be anonymous
-
-        "https://seiga.nicovideo.jp/user/illust/#{api_client.user_id}"
+        "https://seiga.nicovideo.jp/user/illust/#{api_client.user_id}" if api_client.user_id.present?
       end
 
       def artist_name

app/logical/sources/strategies/pixiv.rb

@@ -62,12 +62,10 @@ module Sources
       end
 
       def profile_url
-        if parsed_url.profile_url.present?
-          parsed_url.profile_url
-        elsif api_illust[:userId].present?
+        if api_illust[:userId].present?
           "https://www.pixiv.net/users/#{api_illust[:userId]}"
-        else
-          nil
+        elsif parsed_url.profile_url.present?
+          parsed_url.profile_url
         end
       end
 

app/logical/sources/strategies/twitter.rb

@@ -93,10 +93,6 @@ module Sources::Strategies
       api_response[:full_text].to_s
     end
 
-    def normalize_for_artist_finder
-      profile_url.try(:downcase).presence || url
-    end
-
     def normalize_for_source
       if tag_name_from_url.present? && status_id.present?
         "https://twitter.com/#{tag_name_from_url}/status/#{status_id}"

app/models/artist.rb

@@ -242,7 +242,8 @@ class Artist < ApplicationRecord
       elsif query.include?("*")
         where(id: ArtistURL.where_like(:url, query).select(:artist_id))
       elsif query =~ %r{\Ahttps?://}i
-        ArtistFinder.find_artists(query)
+        url = Sources::Strategies.find(query).profile_url || query
+        ArtistFinder.find_artists(url)
       else
         where(id: ArtistURL.where_like(:url, "*#{query}*").select(:artist_id))
       end

app/models/artist_url.rb

@@ -19,27 +19,16 @@ class ArtistURL < ApplicationRecord
   end
 
   def self.normalize_normalized_url(url)
-    if url.nil?
-      nil
-    else
-      url = url.sub(%r{^https://}, "http://")
-      url = url.sub(%r{^http://blog-imgs-\d+\.fc2}, "http://blog.fc2")
-      url = url.sub(%r{^http://blog-imgs-\d+-\w+\.fc2}, "http://blog.fc2")
-      url = url.sub(%r{^http://blog\d*\.fc2\.com/(?:\w/){,3}(\w+)}, "http://\\1.blog.fc2.com")
-      url = url.sub(%r{^http://pictures.hentai-foundry.com//}, "http://pictures.hentai-foundry.com/")
+    return nil if url.nil?
 
-      # the strategy won't always work for twitter because it looks for a status
-      url = url.downcase if url =~ %r{^https?://(?:mobile\.)?twitter\.com}i
+    url = Source::URL.parse(url)&.profile_url || url
+    url = url.sub(%r{^https://}, "http://")
+    url = url.sub(%r{^http://blog-imgs-\d+\.fc2}, "http://blog.fc2")
+    url = url.sub(%r{^http://blog-imgs-\d+-\w+\.fc2}, "http://blog.fc2")
+    url = url.sub(%r{^http://blog\d*\.fc2\.com/(?:\w/){,3}(\w+)}, "http://\\1.blog.fc2.com")
 
-      url = Sources::Strategies.find(url).normalize_for_artist_finder
-
-      # XXX the Pixiv strategy should implement normalize_for_artist_finder and return the correct url directly.
-      url = url.sub(%r{\Ahttps?://www\.pixiv\.net/(?:en/)?users/(\d+)\z}i, 'https://www.pixiv.net/member.php?id=\1')
-
-      url = url.gsub(%r{/+\Z}, "")
-      url = url.gsub(%r{^https://}, "http://")
-      url + "/"
-    end
+    url = url.gsub(%r{/+\Z}, "")
+    url + "/"
   end
 
   def self.search(params = {})
@@ -67,7 +56,8 @@ class ArtistURL < ApplicationRecord
     elsif url.include?("*")
       where_ilike(attr, url)
     else
-      where(attr => normalize_normalized_url(url))
+      profile_url = Sources::Strategies.find(url).profile_url || url
+      where(attr => normalize_normalized_url(profile_url))
     end
   end