source_monitor 0.9.0 → 0.9.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 37c1b9f849296d336eef1ced8584d8cad21caadb8c67606332ebd0f5db8b6fea
-  data.tar.gz: 36b8646b5f89a6b2b4317b9c914268b9ab399cd7b8cb4cb3aa9ee38809d7fb85
+  metadata.gz: c3dd7577c86e15ec9926a631998d423b1d2fd1bc18cbdfc83e8d7dc57b6be365
+  data.tar.gz: 65fc2870418c04d3741a98404558ffdd3e8f5a901294681446f337b662dd50f2
 SHA512:
-  metadata.gz: d05d79d697e3d2889e0c4e48f8559601c8f43787d94db7d70e517badd606e2ced0252015b3d95bb3721b1acd3ef0bc1096c280c704c602f2a16269160322ef02
-  data.tar.gz: 607355cdf142b9fd7587004c570ece825ac30e1f40864b39fef934e347cf13c22ff09bda06b0f5bf8dd6e1984b3bcc4644d3667e22890c0d6d9bfe5fa28fcf09
+  metadata.gz: 115775737ef8f40ea9323932d58e941fccb9b6903371cbdab80d62bcdfbf31d85f44c5eacbcc7b536489483972a2b02e7e547454715dae9af8b19083dce62a62
+  data.tar.gz: 2a285b946a069420c28a1588f580f721f0ea23da6b5c002a0dfb8d149c338c120291e4ad8e77609b65f59ae55bfadec7db6b85c49f92d2097616588d9425c363

data/.claude/skills/sm-domain-model/SKILL.md

@@ -155,7 +155,7 @@ Items use soft delete via `deleted_at` column (NOT default_scope):
 | `url` | presence |
 
 ### Content Delegation
-`scraped_html` and `scraped_content` delegate to `ItemContent`. Setting these values auto-creates/destroys the ItemContent association.
+`scraped_html` and `scraped_content` delegate to `ItemContent`. Setting these values auto-creates the ItemContent association. `ensure_feed_content_record` also creates ItemContent for feed word count tracking. ItemContent is only auto-destroyed when both scraped fields are blank AND the item has no feed content.
 
 ## LogEntry Delegated Type
 

data/.claude/skills/sm-domain-model/reference/model-graph.md

@@ -30,8 +30,8 @@
      v         v
   ItemContent  ScrapeLog
   ===========  (also belongs_to :source)
-  Scraped
-  content
+  Feed + scraped
+  word counts
 ```
 
 ## Association Details
@@ -43,10 +43,11 @@
 - Counter cache: `items_count` on Source (tracks active items)
 
 ### Item -> ItemContent
-- `has_one :item_content` -- Lazy-created when scraped content is assigned
+- `has_one :item_content` -- Created when item has feed content (via `ensure_feed_content_record`) or when scraped content is assigned
 - `dependent: :destroy, autosave: true`
 - `touch: true` on the belongs_to side
-- Content is auto-destroyed when both `scraped_html` and `scraped_content` become blank
+- Stores `feed_word_count` (from `item.content`) and `scraped_word_count` (from `scraped_content`)
+- Content is auto-destroyed only when both scraped fields are blank AND item has no feed content
 
 ### Source -> FetchLog
 - `has_many :fetch_logs, dependent: :destroy`

data/CHANGELOG.md

@@ -15,6 +15,14 @@ All notable changes to this project are documented below. The format follows [Ke
 
 - No unreleased changes yet.
 
+## [0.9.1] - 2026-02-22
+
+### Fixed
+
+- **Feed word counts now always computed.** Items fetched from feeds but never scraped now get an `ItemContent` record with `feed_word_count` automatically. Previously, only scraped items had `ItemContent`, so the `backfill_word_counts` rake task found nothing for feed-only items.
+- **Backfill task creates missing ItemContent records.** `source_monitor:backfill_word_counts` now has a two-phase approach: first creates `ItemContent` for items with feed content but no record, then recomputes all word counts.
+- **ItemContent preserved when item has feed content.** Clearing scraped fields no longer destroys the `ItemContent` record if the item still has feed content (which provides `feed_word_count`).
+
 ## [0.9.0] - 2026-02-22
 
 ### Added

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    source_monitor (0.9.0)
+    source_monitor (0.9.1)
       cssbundling-rails (~> 1.4)
       faraday (~> 2.9)
       faraday-follow_redirects (~> 0.4)

data/VERSION

@@ -1 +1 @@
-0.9.0
+0.9.1

data/app/assets/builds/source_monitor/application.css

@@ -671,10 +671,6 @@ video {
   top: 50%;
 }
 
-.fm-admin .top-4 {
-  top: 1rem;
-}
-
 .fm-admin .top-16 {
   top: 4rem;
 }
@@ -701,6 +697,14 @@ video {
   margin-bottom: 0.25rem;
 }
 
+.fm-admin .mb-1 {
+  margin-bottom: 0.25rem;
+}
+
+.fm-admin .ml-0\.5 {
+  margin-left: 0.125rem;
+}
+
 .fm-admin .ml-2 {
   margin-left: 0.5rem;
 }
@@ -745,14 +749,6 @@ video {
   margin-top: 1.5rem;
 }
 
-.fm-admin .mb-1 {
-  margin-bottom: 0.25rem;
-}
-
-.fm-admin .ml-0\.5 {
-  margin-left: 0.125rem;
-}
-
 .fm-admin .block {
   display: block;
 }
@@ -861,10 +857,6 @@ video {
   width: 20rem;
 }
 
-.fm-admin .w-full {
-  width: 100%;
-}
-
 .fm-admin .w-\[15\%\] {
   width: 15%;
 }
@@ -881,14 +873,18 @@ video {
   width: 45%;
 }
 
-.fm-admin .min-w-full {
-  min-width: 100%;
+.fm-admin .w-full {
+  width: 100%;
 }
 
 .fm-admin .min-w-\[12rem\] {
   min-width: 12rem;
 }
 
+.fm-admin .min-w-full {
+  min-width: 100%;
+}
+
 .fm-admin .max-w-2xl {
   max-width: 42rem;
 }
@@ -1599,6 +1595,10 @@ video {
   line-height: 1rem;
 }
 
+.fm-admin .font-bold {
+  font-weight: 700;
+}
+
 .fm-admin .font-medium {
   font-weight: 500;
 }
@@ -1611,10 +1611,6 @@ video {
   font-weight: 600;
 }
 
-.fm-admin .font-bold {
-  font-weight: 700;
-}
-
 .fm-admin .uppercase {
   text-transform: uppercase;
 }
@@ -1938,6 +1934,11 @@ video {
   color: rgb(37 99 235 / var(--tw-text-opacity, 1));
 }
 
+.fm-admin .hover\:text-blue-700:hover {
+  --tw-text-opacity: 1;
+  color: rgb(29 78 216 / var(--tw-text-opacity, 1));
+}
+
 .fm-admin .hover\:text-rose-500:hover {
   --tw-text-opacity: 1;
   color: rgb(244 63 94 / var(--tw-text-opacity, 1));
@@ -1963,11 +1964,6 @@ video {
   color: rgb(255 255 255 / var(--tw-text-opacity, 1));
 }
 
-.fm-admin .hover\:text-blue-700:hover {
-  --tw-text-opacity: 1;
-  color: rgb(29 78 216 / var(--tw-text-opacity, 1));
-}
-
 .fm-admin .hover\:underline:hover {
   text-decoration-line: underline;
 }
@@ -2071,10 +2067,6 @@ video {
     width: auto;
   }
 
-  .fm-admin .sm\:min-w-\[16rem\] {
-    min-width: 16rem;
-  }
-
   .fm-admin .sm\:grid-cols-2 {
     grid-template-columns: repeat(2, minmax(0, 1fr));
   }

data/app/models/source_monitor/item.rb

@@ -33,6 +33,15 @@ module SourceMonitor
 
     SourceMonitor::ModelExtensions.register(self, :item)
 
+    # Creates an ItemContent record for feed word count computation when one doesn't exist.
+    # The before_save callback on ItemContent will compute feed_word_count from item.content.
+    def ensure_feed_content_record
+      return if item_content.present?
+      return if content.blank?
+
+      create_item_content!
+    end
+
     class << self
       def ransackable_attributes(_auth_object = nil)
         %w[title summary url published_at created_at scrape_status]
@@ -91,6 +100,7 @@ module SourceMonitor
     def cleanup_item_content_if_blank
       return unless item_content
       return if item_content.scraped_html.present? || item_content.scraped_content.present?
+      return if content.present?
 
       if item_content.persisted?
         item_content.mark_for_destruction

data/lib/source_monitor/items/item_creator.rb

@@ -120,6 +120,7 @@ module SourceMonitor
         new_item = source.items.new
         apply_attributes(new_item, attributes)
         new_item.save!
+        new_item.ensure_feed_content_record
         Result.new(item: new_item, status: :created)
       rescue ActiveRecord::RecordNotUnique
         handle_concurrent_duplicate(attributes, raw_guid_present:)

data/lib/source_monitor/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SourceMonitor
-  VERSION = "0.9.0"
+  VERSION = "0.9.1"
 end

data/lib/tasks/source_monitor_tasks.rake

@@ -3,6 +3,20 @@
 namespace :source_monitor do
   desc "Backfill word counts for existing item_content records."
   task backfill_word_counts: :environment do
+    # Phase 1: Create ItemContent for items with feed content but no ItemContent
+    items_needing_content = SourceMonitor::Item
+      .where.not(content: [ nil, "" ])
+      .where.missing(:item_content)
+
+    created = 0
+    items_needing_content.find_each do |item|
+      item.ensure_feed_content_record
+      created += 1
+      puts "Created #{created} missing ItemContent records..." if (created % 100).zero?
+    end
+    puts "Created #{created} ItemContent records for feed-only items." if created > 0
+
+    # Phase 2: Recompute word counts for all existing ItemContent
     total = SourceMonitor::ItemContent.count
     processed = 0
 
@@ -12,7 +26,7 @@ namespace :source_monitor do
       puts "Processed #{processed}/#{total} records..." if (processed % 100).zero?
     end
 
-    puts "Done. Backfilled word counts for #{processed} records."
+    puts "Done. Backfilled word counts for #{processed} records (#{created} newly created)."
   end
 
   namespace :cleanup do

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: source_monitor
 version: !ruby/object:Gem::Version
-  version: 0.9.0
+  version: 0.9.1
 platform: ruby
 authors:
 - dchuk