From 244beb25123c2bbb53900d4643446e85bd487c80 Mon Sep 17 00:00:00 2001
From: kennethrioja <59597207+kennethrioja@users.noreply.github.com>
Date: Tue, 29 Sep 2026 16:44:08 +0200
Subject: [PATCH] feat(epic-tutorials-ingestor): new heptraining ingestor and
 tests

---
 app/models/source_filter.rb                   | 184 +++++++++---------
 lib/ingestors/cds_videos_ingestor.rb          | 142 --------------
 lib/ingestors/github_ingestor.rb              |   5 +-
 .../heptraining/cds_videos_ingestor.rb        | 144 ++++++++++++++
 .../heptraining/epic_tutorials_ingestor.rb    |  89 +++++++++
 lib/ingestors/ingestor_factory.rb             |   7 +-
 .../heptraining/epictutorials/epic-page.md    |  35 ++++
 .../cds_videos_ingestor_test.rb               |   4 +-
 .../epic_tutorials_ingestor_test.rb           | 134 +++++++++++++
 9 files changed, 503 insertions(+), 241 deletions(-)
 delete mode 100644 lib/ingestors/cds_videos_ingestor.rb
 create mode 100644 lib/ingestors/heptraining/cds_videos_ingestor.rb
 create mode 100644 lib/ingestors/heptraining/epic_tutorials_ingestor.rb
 create mode 100644 test/fixtures/files/ingestion/heptraining/epictutorials/epic-page.md
 rename test/unit/ingestors/{ => heptraining}/cds_videos_ingestor_test.rb (97%)
 create mode 100644 test/unit/ingestors/heptraining/epic_tutorials_ingestor_test.rb

diff --git a/app/models/source_filter.rb b/app/models/source_filter.rb
index a36503494..93df3bb0a 100644
--- a/app/models/source_filter.rb
+++ b/app/models/source_filter.rb
@@ -18,100 +18,98 @@ def self.array_string_match(content_value, filter_value)
   end
 end
 
-
-FILTER_DEFINITIONS = {
-  'target_audience' => {
-    comparison: FilterComparisons.method(:array_string_match)
-  },
-
-  'keyword' => {
-    comparison: FilterComparisons.method(:array_string_match),
-    filter_property: 'keywords'
-  },
-
-  'title' => {
-    comparison: FilterComparisons.method(:string_match)
-  },
-
-  'title_contains' => {
-    comparison: FilterComparisons.method(:contains_string_match),
-    filter_property: 'title'
-  },
-
-  'description' => {
-    comparison: FilterComparisons.method(:string_match)
-  },
-
-  'description_contains' => {
-    comparison: FilterComparisons.method(:contains_string_match),
-    filter_property: 'description'
-  },
-
-  'url' => {
-    comparison: FilterComparisons.method(:string_match)
-  },
-
-  'url_prefix' => {
-    comparison: FilterComparisons.method(:prefix_string_match),
-    filter_property: 'url'
-  },
-
-  'doi' => {
-    comparison: FilterComparisons.method(:string_match)
-  },
-
-  'license' => {
-    comparison: FilterComparisons.method(:string_match),
-    filter_property: 'licence'
-  },
-
-  'difficulty_level' => {
-    comparison: FilterComparisons.method(:string_match)
-  },
-
-  'resource_type' => {
-    comparison: FilterComparisons.method(:array_string_match)
-  },
-
-  'prerequisites_contains' => {
-    comparison: FilterComparisons.method(:contains_string_match),
-    filter_property: 'prerequisites'
-  },
-
-  'learning_objectives_contains' => {
-    comparison: FilterComparisons.method(:contains_string_match),
-    filter_property: 'learning_objectives'
-  },
-
-  'subtitle' => {
-    comparison: FilterComparisons.method(:string_match)
-  },
-
-  'subtitle_contains' => {
-    comparison: FilterComparisons.method(:contains_string_match),
-    filter_property: 'subtitle'
-  },
-
-  'city' => {
-    comparison: FilterComparisons.method(:string_match)
-  },
-
-  'country' => {
-    comparison: FilterComparisons.method(:string_match)
-  },
-
-  'event_type' => {
-    comparison: FilterComparisons.method(:array_string_match),
-    filter_property: 'event_types'
-  },
-
-  'timezone' => {
-    comparison: FilterComparisons.method(:string_match)
-  }
-}.freeze
-
-
 class SourceFilter < ApplicationRecord
+  FILTER_DEFINITIONS = {
+    'target_audience' => {
+      comparison: FilterComparisons.method(:array_string_match)
+    },
+
+    'keyword' => {
+      comparison: FilterComparisons.method(:array_string_match),
+      filter_property: 'keywords'
+    },
+
+    'title' => {
+      comparison: FilterComparisons.method(:string_match)
+    },
+
+    'title_contains' => {
+      comparison: FilterComparisons.method(:contains_string_match),
+      filter_property: 'title'
+    },
+
+    'description' => {
+      comparison: FilterComparisons.method(:string_match)
+    },
+
+    'description_contains' => {
+      comparison: FilterComparisons.method(:contains_string_match),
+      filter_property: 'description'
+    },
+
+    'url' => {
+      comparison: FilterComparisons.method(:string_match)
+    },
+
+    'url_prefix' => {
+      comparison: FilterComparisons.method(:prefix_string_match),
+      filter_property: 'url'
+    },
+
+    'doi' => {
+      comparison: FilterComparisons.method(:string_match)
+    },
+
+    'license' => {
+      comparison: FilterComparisons.method(:string_match),
+      filter_property: 'licence'
+    },
+
+    'difficulty_level' => {
+      comparison: FilterComparisons.method(:string_match)
+    },
+
+    'resource_type' => {
+      comparison: FilterComparisons.method(:array_string_match)
+    },
+
+    'prerequisites_contains' => {
+      comparison: FilterComparisons.method(:contains_string_match),
+      filter_property: 'prerequisites'
+    },
+
+    'learning_objectives_contains' => {
+      comparison: FilterComparisons.method(:contains_string_match),
+      filter_property: 'learning_objectives'
+    },
+
+    'subtitle' => {
+      comparison: FilterComparisons.method(:string_match)
+    },
+
+    'subtitle_contains' => {
+      comparison: FilterComparisons.method(:contains_string_match),
+      filter_property: 'subtitle'
+    },
+
+    'city' => {
+      comparison: FilterComparisons.method(:string_match)
+    },
+
+    'country' => {
+      comparison: FilterComparisons.method(:string_match)
+    },
+
+    'event_type' => {
+      comparison: FilterComparisons.method(:array_string_match),
+      filter_property: 'event_types'
+    },
+
+    'timezone' => {
+      comparison: FilterComparisons.method(:string_match)
+    }
+  }.freeze
+
   belongs_to :source
 
   auto_strip_attributes :value
diff --git a/lib/ingestors/cds_videos_ingestor.rb b/lib/ingestors/cds_videos_ingestor.rb
deleted file mode 100644
index 6376a1d34..000000000
--- a/lib/ingestors/cds_videos_ingestor.rb
+++ /dev/null
@@ -1,142 +0,0 @@
-# frozen_string_literal: true
-require 'json'
-
-module Ingestors
-  class CdsVideosIngestor < Ingestor # rubocop:disable Style/Documentation
-    CDS_VIDEOS_RECORD_URL = 'https://videos.cern.ch/record/'
-
-    def self.config
-      {
-        key: 'cds videos',
-        title: 'CDS videos record or search',
-        category: :materials,
-        user_agent: 'TeSS CDS Videos ingestor'
-      }
-    end
-
-    # Reads from single CDS record URL or search query URL
-    # For a search query, we need to change fields: page to 1 and size to 100
-    # Then read all pages while running `to_material()`
-    # Else for a single material, go direct with `to_material()`
-    def read(source_url)
-      api_url = to_api(source_url)
-
-      if source_url.include?('search')
-        api_url_page_updated = update_url_field_value(api_url, 'page', 1)
-        api_url_page_size_updated = update_url_field_value(api_url_page_updated, 'size', 100)
-        data = JSON.parse(open_url(api_url_page_size_updated).read)
-        add_records_material(data)
-      else
-        data = JSON.parse(open_url(api_url).read)
-        add_material to_material(data)
-      end
-    rescue StandardError => e
-      Rails.logger.error("#{e.class}: read() failed, #{e.message}")
-    end
-
-    private
-
-    def to_api(url)
-      uri = URI(url)
-      parts = uri.path.split('/') # 'example.com/foo/bar' will have path == '/foo/bar', so three parts
-
-      # FROM '/search?{query}'
-      if parts[1] == 'search' && parts.size == 2
-        # TO '/api/records/{query}'
-        "https://#{uri.host}/api/records?#{uri.query}"
-      # FROM '/record/{recid}'
-      elsif parts[1] == 'record' && parts.size == 3
-        # TO 'api/record/{recid}'
-        "https://#{uri.host}/api/#{parts[1]}/#{parts[2]}"
-      end
-    end
-
-    def update_url_field_value(url, field, value)
-      uri = URI.parse(url)
-      params = URI.decode_www_form(uri.query || '').to_h
-      params[field] = value.to_s
-      uri.query = URI.encode_www_form(params)
-      uri.to_s
-    end
-
-    def add_records_material(initial_data)
-      data = initial_data
-
-      while data
-        hits = data.dig('hits', 'hits') || []
-        hits.each { |hit| add_material to_material(hit) }
-
-        next_url = data.dig('links', 'next')
-        break unless next_url
-
-        response = open_url(next_url)&.read
-        data = response ? JSON.parse(response) : nil
-      end
-    end
-
-    # Sets material hash keys and values and add them to material
-    def to_material(data)
-      metadata = (data['metadata'] || {}).transform_keys { |k| k == '_cds' ? 'cds' : k }
-
-      material = OpenStruct.new
-      material.title = metadata.dig('title', 'title').to_s.titleize
-      material.url = "#{CDS_VIDEOS_RECORD_URL}#{data['id']}"
-      material.description = get_description(metadata)
-      material.keywords = Array(metadata['keywords']).first(10).map { |k| k['name'] }.compact
-      material.licence = metadata.dig('copyright', 'holder') == 'CERN' ? 'other-at' : 'notspecified'
-      material.status = 'Active'
-      material.contact = get_contact(metadata)
-      material.version = Array(metadata['report_number']).first
-      material.date_created = metadata['date']
-      material.date_published = metadata['publication_date']
-      material.authors = get_authors(metadata)
-      material.contributors = get_contributors(metadata)
-      type = metadata['type']
-      category = metadata['category']
-      resource_type = [type, category].compact.map { |v| v.to_s.titleize }.join(' – ')
-      material.resource_type = resource_type.present? ? [resource_type] : []
-      material
-    end
-
-    def get_description(metadata)
-      description = metadata['description'].split('<br>')[0] + "\n\n"
-      description = description&.<< "Video duration: #{metadata['duration']}\n\n" if metadata['duration']
-      description = description + metadata['additional_descriptions']&.map { |k| k['description'] }&.join("\n\n") + "\n\n" || '' if metadata['additional_descriptions']
-      description = description&.<< "Related identifier:\n- Is part of: #{metadata['alternate_identifiers'][0]['value']} (URL)\n\n" if metadata['alternate_identifiers']&.any?
-      description = description&.<< "Copyright: [#{metadata.dig('copyright', 'holder')}](#{metadata.dig('copyright', 'url')}) (#{metadata.dig('copyright', 'year')})" if metadata.dig('copyright', 'holder')
-      description
-    end
-
-    def get_authors(metadata)
-      metadata['contributors']
-            &.select { |c| c['role'] == 'Creator' }
-            &.reject { |c| c['name'].downcase == 'cern' }
-            &.map { |c| c['name']&.gsub(',', '')&.titleize } || ''
-    end
-
-    def get_contributors(metadata)
-      metadata['contributors']
-            &.reject { |c| c['role'] == 'Creator' || c['role'] == 'ContactPerson' }
-            &.reject { |c| c['name'].downcase == 'cern' }
-            &.map { |c| c['name']&.gsub(',', '')&.titleize } || ''
-    end
-
-    def get_contact(metadata)
-      contributors = metadata['contributors'] || []
-
-      # 1. Check for ContactPerson name
-      contact_person = contributors.find { |c| c['role'] == 'ContactPerson' }
-      contact_name = contact_person&.[]('name')&.gsub(',', '')&.titleize
-
-      # 2. Check for Creator email
-      creator = contributors.find { |c| c['role'] == 'Creator' }
-      creator_email = creator&.[]('email')&.gsub(',', '')&.titleize
-
-      # 3. Check for any other contributor email
-      other_contributor = contributors.find { |c| !%w[ContactPerson Creator].include?(c['role']) }
-      other_email = other_contributor&.[]('email')
-
-      contact_name.presence || creator_email.presence || other_email || ''
-    end
-  end
-end
diff --git a/lib/ingestors/github_ingestor.rb b/lib/ingestors/github_ingestor.rb
index 6cc65eafc..77f29bc75 100644
--- a/lib/ingestors/github_ingestor.rb
+++ b/lib/ingestors/github_ingestor.rb
@@ -93,7 +93,10 @@ def github_api_from_io(uri, parts)
     # ttl: time-to-live in seconds (default 7 days)
     def cache_fetch(key, url)
       Rails.cache.fetch(key, expires_in: TTL, skip_nil: true) do
-        JSON.parse(open_url(url).read)
+        response = open_url(url)
+        next nil unless response
+
+        JSON.parse(response.read)
       end
     end
 
diff --git a/lib/ingestors/heptraining/cds_videos_ingestor.rb b/lib/ingestors/heptraining/cds_videos_ingestor.rb
new file mode 100644
index 000000000..a4f145c79
--- /dev/null
+++ b/lib/ingestors/heptraining/cds_videos_ingestor.rb
@@ -0,0 +1,144 @@
+# frozen_string_literal: true
+require 'json'
+
+module Ingestors
+  module Heptraining
+    class CdsVideosIngestor < Ingestor # rubocop:disable Style/Documentation
+      CDS_VIDEOS_RECORD_URL = 'https://videos.cern.ch/record/'
+
+      def self.config
+        {
+          key: 'cds videos',
+          title: 'CDS videos record or search',
+          category: :materials,
+          user_agent: 'TeSS CDS Videos ingestor'
+        }
+      end
+
+      # Reads from single CDS record URL or search query URL
+      # For a search query, we need to change fields: page to 1 and size to 100
+      # Then read all pages while running `to_material()`
+      # Else for a single material, go direct with `to_material()`
+      def read(source_url)
+        api_url = to_api(source_url)
+
+        if source_url.include?('search')
+          api_url_page_updated = update_url_field_value(api_url, 'page', 1)
+          api_url_page_size_updated = update_url_field_value(api_url_page_updated, 'size', 100)
+          data = JSON.parse(open_url(api_url_page_size_updated).read)
+          add_records_material(data)
+        else
+          data = JSON.parse(open_url(api_url).read)
+          add_material to_material(data)
+        end
+      rescue StandardError => e
+        Rails.logger.error("#{e.class}: read() failed, #{e.message}")
+      end
+
+      private
+
+      def to_api(url)
+        uri = URI(url)
+        parts = uri.path.split('/') # 'example.com/foo/bar' will have path == '/foo/bar', so three parts
+
+        # FROM '/search?{query}'
+        if parts[1] == 'search' && parts.size == 2
+          # TO '/api/records/{query}'
+          "https://#{uri.host}/api/records?#{uri.query}"
+        # FROM '/record/{recid}'
+        elsif parts[1] == 'record' && parts.size == 3
+          # TO 'api/record/{recid}'
+          "https://#{uri.host}/api/#{parts[1]}/#{parts[2]}"
+        end
+      end
+
+      def update_url_field_value(url, field, value)
+        uri = URI.parse(url)
+        params = URI.decode_www_form(uri.query || '').to_h
+        params[field] = value.to_s
+        uri.query = URI.encode_www_form(params)
+        uri.to_s
+      end
+
+      def add_records_material(initial_data)
+        data = initial_data
+
+        while data
+          hits = data.dig('hits', 'hits') || []
+          hits.each { |hit| add_material to_material(hit) }
+
+          next_url = data.dig('links', 'next')
+          break unless next_url
+
+          response = open_url(next_url)&.read
+          data = response ? JSON.parse(response) : nil
+        end
+      end
+
+      # Sets material hash keys and values and add them to material
+      def to_material(data)
+        metadata = (data['metadata'] || {}).transform_keys { |k| k == '_cds' ? 'cds' : k }
+
+        material = OpenStruct.new
+        material.title = metadata.dig('title', 'title').to_s.titleize
+        material.url = "#{CDS_VIDEOS_RECORD_URL}#{data['id']}"
+        material.description = get_description(metadata)
+        material.keywords = Array(metadata['keywords']).first(10).map { |k| k['name'] }.compact
+        material.licence = metadata.dig('copyright', 'holder') == 'CERN' ? 'other-at' : 'notspecified'
+        material.status = 'Active'
+        material.contact = get_contact(metadata)
+        material.version = Array(metadata['report_number']).first
+        material.date_created = metadata['date']
+        material.date_published = metadata['publication_date']
+        material.authors = get_authors(metadata)
+        material.contributors = get_contributors(metadata)
+        type = metadata['type']
+        category = metadata['category']
+        resource_type = [type, category].compact.map { |v| v.to_s.titleize }.join(' – ')
+        material.resource_type = resource_type.present? ? [resource_type] : []
+        material
+      end
+
+      def get_description(metadata)
+        description = metadata['description'].split('<br>')[0] + "\n\n"
+        description = description&.<< "Video duration: #{metadata['duration']}\n\n" if metadata['duration']
+        description = description + metadata['additional_descriptions']&.map { |k| k['description'] }&.join("\n\n") + "\n\n" || '' if metadata['additional_descriptions']
+        description = description&.<< "Related identifier:\n- Is part of: #{metadata['alternate_identifiers'][0]['value']} (URL)\n\n" if metadata['alternate_identifiers']&.any?
+        description = description&.<< "Copyright: [#{metadata.dig('copyright', 'holder')}](#{metadata.dig('copyright', 'url')}) (#{metadata.dig('copyright', 'year')})" if metadata.dig('copyright', 'holder')
+        description
+      end
+
+      def get_authors(metadata)
+        metadata['contributors']
+              &.select { |c| c['role'] == 'Creator' }
+              &.reject { |c| c['name'].downcase == 'cern' }
+              &.map { |c| c['name']&.gsub(',', '')&.titleize } || ''
+      end
+
+      def get_contributors(metadata)
+        metadata['contributors']
+              &.reject { |c| c['role'] == 'Creator' || c['role'] == 'ContactPerson' }
+              &.reject { |c| c['name'].downcase == 'cern' }
+              &.map { |c| c['name']&.gsub(',', '')&.titleize } || ''
+      end
+
+      def get_contact(metadata)
+        contributors = metadata['contributors'] || []
+
+        # 1. Check for ContactPerson name
+        contact_person = contributors.find { |c| c['role'] == 'ContactPerson' }
+        contact_name = contact_person&.[]('name')&.gsub(',', '')&.titleize
+
+        # 2. Check for Creator email
+        creator = contributors.find { |c| c['role'] == 'Creator' }
+        creator_email = creator&.[]('email')&.gsub(',', '')&.titleize
+
+        # 3. Check for any other contributor email
+        other_contributor = contributors.find { |c| !%w[ContactPerson Creator].include?(c['role']) }
+        other_email = other_contributor&.[]('email')
+
+        contact_name.presence || creator_email.presence || other_email || ''
+      end
+    end
+  end
+end
diff --git a/lib/ingestors/heptraining/epic_tutorials_ingestor.rb b/lib/ingestors/heptraining/epic_tutorials_ingestor.rb
new file mode 100644
index 000000000..1476ef3db
--- /dev/null
+++ b/lib/ingestors/heptraining/epic_tutorials_ingestor.rb
@@ -0,0 +1,89 @@
+# frozen_string_literal: true
+
+require 'yaml'
+
+module Ingestors
+  module Heptraining
+    class EpicTutorialsIngestor < Ingestor
+      def self.config
+        {
+          key: 'epic_tutorials',
+          title: 'ePIC Tutorials',
+          category: :materials,
+          user_agent: 'TeSS ePIC Tutorials ingestor'
+        }
+      end
+
+      def read(url)
+        @verbose = false
+        response = open_url(url, raise: true)
+        return unless response
+
+        process_frontmatter(response.read)
+      rescue StandardError => e
+        Rails.logger.error("#{e.class}: read() failed, #{e.message}")
+      end
+
+      private
+
+      def process_frontmatter(content)
+        yaml_match = content.match(/\A---\s*\n(.*?)\n?---\s*/m)
+        raise 'No YAML frontmatter found' unless yaml_match
+        
+        data = YAML.safe_load(yaml_match[1], permitted_classes: [Date, Time])
+        tutorials = data['tutorials'] || []
+
+        tutorials.each do |tutorial|
+          process_tutorial(tutorial)
+        end
+      end
+
+      def process_tutorial(tutorial)
+        url = tutorial['url']
+        return if url.blank?
+
+        materials, events = fetch_from_other_ingestor(url)
+
+        # Build external resources list from YAML
+        ext_resources = (tutorial['resources'] || []).map do |res|
+          next if res['url'].blank?
+
+          kind = res['kind'].present? ? res['kind'].capitalize : nil
+          title = res['label'].present? ? "#{kind} #{res['label']}" : kind
+          { title: title, url: res['url'] }
+        end.compact
+
+        # Attach external resources to returned materials
+        (materials + events).each do |material|
+          material.external_resources ||= []
+          material.external_resources.concat(ext_resources)
+        end
+
+        @materials.concat(materials)
+        @events.concat(events)
+      end
+
+      def fetch_from_other_ingestor(url)
+        ingestor = if github_url?(url)
+                      Ingestors::GithubIngestor.new
+                    elsif indico_url?(url)
+                      Ingestors::IndicoIngestor.new
+                    end
+
+        return [[], []] unless ingestor
+
+        ingestor.read(url)
+        [ingestor.materials, ingestor.events]
+      end
+
+      def github_url?(url)
+        uri = URI.parse(url)
+        uri.host&.downcase == 'github.com' || uri.host&.downcase&.end_with?('.github.io')
+      end
+
+      def indico_url?(url)
+        url.include?('indico')
+      end
+    end
+  end
+end
\ No newline at end of file
diff --git a/lib/ingestors/ingestor_factory.rb b/lib/ingestors/ingestor_factory.rb
index d4c2d3fac..97e8c9cdb 100644
--- a/lib/ingestors/ingestor_factory.rb
+++ b/lib/ingestors/ingestor_factory.rb
@@ -15,8 +15,7 @@ def self.ingestors
         Ingestors::GithubIngestor,
         Ingestors::EventRSSIngestor,
         Ingestors::MaterialRSSIngestor,
-        Ingestors::YoutubeIngestor,
-        Ingestors::CdsVideosIngestor
+        Ingestors::YoutubeIngestor
       ] + taxila_ingestors + llm_ingestors + heptraining_ingestors
     end
 
@@ -57,7 +56,9 @@ def self.llm_ingestors
 
     def self.heptraining_ingestors
       [
-        Ingestors::Heptraining::GrayScottIngestor
+        Ingestors::Heptraining::GrayScottIngestor,
+        Ingestors::Heptraining::CdsVideosIngestor,
+        Ingestors::Heptraining::EpicTutorialsIngestor
       ]
     end
 
diff --git a/test/fixtures/files/ingestion/heptraining/epictutorials/epic-page.md b/test/fixtures/files/ingestion/heptraining/epictutorials/epic-page.md
new file mode 100644
index 000000000..56aabb26f
--- /dev/null
+++ b/test/fixtures/files/ingestion/heptraining/epictutorials/epic-page.md
@@ -0,0 +1,35 @@
+---
+title: ePIC Tutorials
+description: Tutorials for ePIC environment setup, analysis, simulation, reconstruction, file access, and benchmarks.
+name: tutorials
+layout: default
+tutorials:
+
+  - title: "Setting up an environment"
+    url: "https://github.com/hsf-training/cpluspluscourse"
+    summary: "How to get eic-shell and what it is<br> Usage of github"
+    image: "/assets/images/tutorials/tutorial-eicshell.png"
+    resources:
+      - label: "1"
+        url: "https://www.youtube.com/watch?v=Y0Mg24XLomY"
+        kind: "youtube"
+      - label: "2"
+        url: "https://www.youtube.com/watch?v=5HmzFnYW4W4"
+        kind: "youtube"
+
+  - title: "Reconstruction framework"
+    url: "https://github.com/hsf-training/cpluspluscourse"
+    summary: "eicrecon in a nutshell. <br> JANA2 framework , Plugins, Factories, and Algorithms"
+    image: "/assets/images/tutorials/tutorial-jana2.png"
+
+  - title: "Getting started with physics analysis"
+    url: "https://indico.bnl.gov/event/27123"
+    summary: "Understanding EPIC detector regions <br>Quality assurance plots for physics <br>Acceptance and efficiency<br>Beam effects and afterburner<br>Full-chain analysis"
+    image: "/assets/images/tutorials/tutorial-physics-analysis.png"
+    resources:
+      - url: "https://youtu.be/goONxXudL-s"
+        kind: "youtube"
+---
+
+<div>
+</div>
\ No newline at end of file
diff --git a/test/unit/ingestors/cds_videos_ingestor_test.rb b/test/unit/ingestors/heptraining/cds_videos_ingestor_test.rb
similarity index 97%
rename from test/unit/ingestors/cds_videos_ingestor_test.rb
rename to test/unit/ingestors/heptraining/cds_videos_ingestor_test.rb
index a428948ae..0f275202f 100644
--- a/test/unit/ingestors/cds_videos_ingestor_test.rb
+++ b/test/unit/ingestors/heptraining/cds_videos_ingestor_test.rb
@@ -4,14 +4,14 @@
 
 class CdsVideosIngestorTest < ActiveSupport::TestCase
   setup do
-    @ingestor = Ingestors::CdsVideosIngestor.new
+    @ingestor = Ingestors::Heptraining::CdsVideosIngestor.new
 
     # API record
     webmock('https://videos.cern.ch/api/record/3023615', 'cdsvideos/cds.ingestor.json')
   end
 
   test 'returns expected ingestor config' do
-    config = Ingestors::CdsVideosIngestor.config
+    config = Ingestors::Heptraining::CdsVideosIngestor.config
     assert_equal 'cds videos', config[:key]
     assert_equal :materials, config[:category]
   end
diff --git a/test/unit/ingestors/heptraining/epic_tutorials_ingestor_test.rb b/test/unit/ingestors/heptraining/epic_tutorials_ingestor_test.rb
new file mode 100644
index 000000000..246d4842e
--- /dev/null
+++ b/test/unit/ingestors/heptraining/epic_tutorials_ingestor_test.rb
@@ -0,0 +1,134 @@
+# frozen_string_literal: true
+
+require 'test_helper'
+
+class EpicTutorialsIngestorTest < ActiveSupport::TestCase
+  setup do
+    @ingestor = Ingestors::Heptraining::EpicTutorialsIngestor.new
+    @user = users(:regular_user)
+    @content_provider = content_providers(:portal_provider)
+
+    webmock('https://raw.githubusercontent.com/eic/tutorials/main/tutorials.md', 'heptraining/epictutorials/epic-page.md')
+    # Github
+    webmock('https://github.com/hsf-training/cpluspluscourse', 'github/mock.html')
+    webmock('https://api.github.com/repos/hsf-training/cpluspluscourse', 'github/api-github-com.json')
+    webmock('https://api.github.com/repos/hsf-training/cpluspluscourse/contributors', 'github/contributors.json')
+    webmock('https://api.github.com/repos/hsf-training/cpluspluscourse/contents/README.md', 'github/readme.json')
+    webmock('https://api.github.com/repos/hsf-training/cpluspluscourse/releases', 'github/releases.json')
+
+    # Indico
+    webmock('https://indico.bnl.gov/event/27123', 'indico/indico.html')
+    webmock('https://indico.bnl.gov/event/27123/event.ics', 'indico/event.ics')
+  end
+
+  test 'config' do
+    config = Ingestors::Heptraining::EpicTutorialsIngestor.config
+
+    assert_equal 'epic_tutorials', config[:key]
+    assert_equal 'ePIC Tutorials', config[:title]
+    assert_equal :materials, config[:category]
+    assert_equal 'TeSS ePIC Tutorials ingestor', config[:user_agent]
+  end
+
+  test 'github_url?' do
+    assert @ingestor.send(:github_url?, 'https://github.com/eic/tutorial-setting-up-environment')
+    assert @ingestor.send(:github_url?, 'https://eic.github.io/tutorial-setting-up-environment')
+    refute @ingestor.send(:github_url?, 'https://indico.bnl.gov/event/27123/')
+    refute @ingestor.send(:github_url?, 'not_a_valid_url')
+  end
+
+  test 'indico_url?' do
+    assert @ingestor.send(:indico_url?, 'https://indico.bnl.gov/event/27123/')
+    assert @ingestor.send(:indico_url?, 'https://indico.cern.ch/event/12345/')
+    refute @ingestor.send(:indico_url?, 'https://eic.github.io/scavenger-hunt')
+  end
+
+  test 'should read epic tutorials source and attach external resources' do
+    # Stub delegation to sub-ingestors
+    @ingestor.read('https://raw.githubusercontent.com/eic/tutorials/main/tutorials.md')
+    @ingestor.write(@user, @content_provider)
+
+    assert_equal 2, @ingestor.materials.count
+    assert_equal 1, @ingestor.events.count
+
+    evt = @ingestor.events.detect { |e| e.title == '14th HEP C++ Course and Hands-on Training - The Essentials' }
+    assert evt.persisted?
+    assert_equal evt.url, 'https://indico.cern.ch/event/1617123/'
+    assert_equal evt.description, 'speakers and Zoom here, however it is not hybrid'
+    assert_equal 1, evt.external_resources.size
+    extres0 = evt.external_resources[0]
+    assert_equal 'Youtube', extres0.title
+    assert_equal 'https://youtu.be/goONxXudL-s', extres0.url
+
+
+    mat = @ingestor.materials.detect { |e| e.title == 'Cpluspluscourse' }
+    assert mat.persisted?
+    assert_equal mat.description, 'C++ Course Taught at CERN'
+    assert_equal 2, mat.external_resources.size
+    extres1 = mat.external_resources[0]
+    assert_equal 'Youtube 1', extres1.title
+    assert_equal 'https://www.youtube.com/watch?v=Y0Mg24XLomY', extres1.url
+    extres2 = mat.external_resources[1]
+    assert_equal 'Youtube 2', extres2.title
+    assert_equal 'https://www.youtube.com/watch?v=5HmzFnYW4W4', extres2.url
+  end
+
+  test 'fetch_from_other_ingestor delegates to GithubIngestor and IndicoIngestor' do
+    gh_url = 'https://eic.github.io/tutorial-setting-up-environment'
+    indico_url = 'https://indico.bnl.gov/event/27123/'
+    unknown_url = 'https://example.com/tutorial'
+
+    mock_gh_material = Material.new(title: 'GH Mat')
+    mock_indico_event = Event.new(title: 'Indico Evt')
+
+    # Test GitHub delegation
+    gh_mock = Minitest::Mock.new
+    gh_mock.expect(:read, true, [gh_url])
+    gh_mock.expect(:materials, [mock_gh_material])
+    gh_mock.expect(:events, [])
+
+    Ingestors::GithubIngestor.stub(:new, gh_mock) do
+      gh_res = @ingestor.send(:fetch_from_other_ingestor, gh_url)
+      assert_equal [mock_gh_material], gh_res[0]
+      assert_equal [], gh_res[1]
+    end
+    gh_mock.verify
+
+    # Test Indico delegation
+    indico_mock = Minitest::Mock.new
+    indico_mock.expect(:read, true, [indico_url])
+    indico_mock.expect(:materials, [])
+    indico_mock.expect(:events, [mock_indico_event])
+
+    Ingestors::IndicoIngestor.stub(:new, indico_mock) do
+      indico_res = @ingestor.send(:fetch_from_other_ingestor, indico_url)
+      assert_equal [], indico_res[0]
+      assert_equal [mock_indico_event], indico_res[1]
+    end
+    indico_mock.verify
+
+    # Test unknown URL
+    unknown_res = @ingestor.send(:fetch_from_other_ingestor, unknown_url)
+    assert_equal [[], []], unknown_res
+  end
+
+  test 'std errors when exception is raised during read' do
+    @ingestor.stub(:open_url, ->(*) { raise StandardError, 'connection error' }) do
+      mock_logger = Minitest::Mock.new
+      mock_logger.expect(:error, nil, ['StandardError: read() failed, connection error'])
+
+      Rails.stub(:logger, mock_logger) do
+        @ingestor.read('https://raw.githubusercontent.com/eic/tutorials/main/tutorials.md')
+      end
+
+      mock_logger.verify
+    end
+  end
+
+  private
+
+  def webmock(url, filename)
+    file = Rails.root.join('test', 'fixtures', 'files', 'ingestion', filename)
+    WebMock.stub_request(:get, url).to_return(status: 200, headers: {}, body: file.read)
+  end
+end
\ No newline at end of file