From b4ce4ec975b4d81c0c8348e8444653140a80df38 Mon Sep 17 00:00:00 2001
From: Daniel Uber <djuber@gmail.com>
Date: Fri, 11 Jun 2021 12:51:51 -0500
Subject: [PATCH] 15 minute fix: Shorten long titles from feed items if needed
 (#13961)

* Shorten long titles from feed items if needed

Fixes #13959

When the title is too long to create a valid article, put a shortened
title in the generated article markdown.

Added unit tests to cover the default case and the shortening case

* Fix Struct initialization

Rubocop suggested struct over openstruct because of performance, but
Struct.new creates a "class" with a positional initializer, while
Openstruct's new takes a hash like keyword set and builds an object
from those directly.

I mistakenly reused the openstruct syntax after the conversion. This
changes the feed and item to use Struct's initializer.

* Use String#truncate in place of custom trimming

`separator` enables a natural break (preventing space between last
character and ellipsis), and omission text "..." is the default behavior.

* Use verifying doubles in test, use method access to members in code

The instance_double for Feedjira::Parser::RSSEntry
necessitated changing hash key access to reader method access for the
data members (title, categories, summary, description).
---
 .../feeds/assemble_article_markdown.rb        | 12 +++--
 .../feeds/assemble_article_markdown_spec.rb   | 50 +++++++++++++++++++
 2 files changed, 58 insertions(+), 4 deletions(-)
 create mode 100644 spec/services/feeds/assemble_article_markdown_spec.rb

diff --git a/app/services/feeds/assemble_article_markdown.rb b/app/services/feeds/assemble_article_markdown.rb
index 51bab88aa..c183dbbac 100644
--- a/app/services/feeds/assemble_article_markdown.rb
+++ b/app/services/feeds/assemble_article_markdown.rb
@@ -6,8 +6,8 @@ module Feeds
 
     def initialize(item, user, feed, feed_source_url)
       @item = item
-      @title = item[:title].strip
-      @categories = item[:categories] || []
+      @title = item.title.strip
+      @categories = item.categories || []
       @user = user
       @feed = feed
       @feed_source_url = feed_source_url
@@ -16,7 +16,7 @@ module Feeds
     def call
       body = <<~HEREDOC
         ---
-        title: #{@title}
+        title: #{processed_title}
         published: false
         date: #{@item.published}
         tags: #{get_tags}
@@ -31,6 +31,10 @@ module Feeds
 
     private
 
+    def processed_title
+      @title.truncate(128, omission: "...", separator: " ")
+    end
+
     def get_tags
       @categories.first(4).map do |tag|
         tag.delete(" ").gsub(/[^[:alnum:]]/i, "")[0..19]
@@ -54,7 +58,7 @@ module Feeds
     end
 
     def get_content
-      @item[:content] || @item[:summary] || @item[:description]
+      @item.content || @item.summary || @item.description
     end
 
     def thorough_parsing(content, feed_url)
diff --git a/spec/services/feeds/assemble_article_markdown_spec.rb b/spec/services/feeds/assemble_article_markdown_spec.rb
new file mode 100644
index 000000000..af44fcacf
--- /dev/null
+++ b/spec/services/feeds/assemble_article_markdown_spec.rb
@@ -0,0 +1,50 @@
+require "rails_helper"
+
+RSpec.describe Feeds::AssembleArticleMarkdown, type: :service do
+  let(:user) { create(:user, feed_mark_canonical: true) }
+  let(:feed_source_url) { "https://feed.source/url" }
+  let(:feed) { instance_double("Feedjira::Parser::RSS", url: "https://feed.source/") }
+  let(:title) { "A title" }
+  let(:content) { "Some content that came in with the item, should be the body" }
+
+  let(:item) do
+    instance_double(
+      "Feedjira::Parser::RSSEntry",
+      title: title,
+      categories: %w[tag1 tag2 tag3 tag4 tag5],
+      published: "2020-12-20",
+      content: content,
+    )
+  end
+
+  let(:feeds_assemble_article_markdown) { described_class.new(item, user, feed, feed_source_url) }
+
+  it "creates markdown head matter" do
+    body = feeds_assemble_article_markdown.call
+
+    expect(body).to include("title: A title")
+    expect(body).to include("date: 2020-12-20")
+  end
+
+  it "includes the content from the feed" do
+    body = feeds_assemble_article_markdown.call
+
+    expect(body).to include(content)
+  end
+
+  context "when item has a long title" do
+    let(:title) { "Words " * 25 }
+
+    it "limits the title to 128 characters by truncation" do
+      body = feeds_assemble_article_markdown.call
+
+      title_line = body.lines.detect { |line| line.starts_with?("title:") }
+      shortened_title = title_line.split(":").second.strip
+      # we expect 21 "Words" plus an ellipsis, total of 128 characters
+      expected_title = "Words Words Words Words Words Words Words Words Words Words Words Words Words Words Words Words Words Words Words Words Words..." # rubocop:disable Layout/LineLength
+
+      expect(shortened_title.size).to eq(128)
+      expect(shortened_title).to eq(expected_title)
+    end
+  end
+end