feat(data-index): wire machine-index flags; fold ietf into configs.yml

.github/workflows/data-deploy.yml

@@ -359,30 +359,42 @@ jobs:
           TITLE: ${{ steps.branding.outputs.title }}
           FAVICON: ${{ steps.branding.outputs.favicon }}
           DESCRIPTION: ${{ steps.branding.outputs.description }}
+          PUBID_FLAVOR: ${{ steps.branding.outputs.pubid_flavor }}
+          PUBLISH_DATA: ${{ steps.branding.outputs.publish_data }}
         run: |
+          EXTRA=()
+          [ -n "$PUBID_FLAVOR" ] && EXTRA+=(--pubid-flavor "$PUBID_FLAVOR")
+          [ "$PUBLISH_DATA" = "true" ] && EXTRA+=(--publish-data)
           relaton index "${{ inputs.data-dir }}" \
             --output _site \
             --title "$TITLE" \
             --favicon "$FAVICON" \
             --description "$DESCRIPTION" \
-            --base-url "https://raw.githubusercontent.com/${GITHUB_REPOSITORY}/${GITHUB_REF_NAME}"
+            --base-url "https://raw.githubusercontent.com/${GITHUB_REPOSITORY}/${GITHUB_REF_NAME}" \
+            "${EXTRA[@]}"
 
       - name: Build index (git source)
         if: inputs.source == 'git'
         # BUNDLE_GEMFILE is exported to GITHUB_ENV in the build step above.
         # TITLE/FAVICON/DESCRIPTION travel by env for the same reason as the gem
-        # step.
+        # step. PUBID_FLAVOR/PUBLISH_DATA come from configs.yml via branding.
         env:
           TITLE: ${{ steps.branding.outputs.title }}
           FAVICON: ${{ steps.branding.outputs.favicon }}
           DESCRIPTION: ${{ steps.branding.outputs.description }}
+          PUBID_FLAVOR: ${{ steps.branding.outputs.pubid_flavor }}
+          PUBLISH_DATA: ${{ steps.branding.outputs.publish_data }}
         run: |
+          EXTRA=()
+          [ -n "$PUBID_FLAVOR" ] && EXTRA+=(--pubid-flavor "$PUBID_FLAVOR")
+          [ "$PUBLISH_DATA" = "true" ] && EXTRA+=(--publish-data)
           bundle exec relaton index "${{ github.workspace }}/${{ inputs.data-dir }}" \
             --output "${{ github.workspace }}/_site" \
             --title "$TITLE" \
             --favicon "$FAVICON" \
             --description "$DESCRIPTION" \
-            --base-url "https://raw.githubusercontent.com/${GITHUB_REPOSITORY}/${GITHUB_REF_NAME}"
+            --base-url "https://raw.githubusercontent.com/${GITHUB_REPOSITORY}/${GITHUB_REF_NAME}" \
+            "${EXTRA[@]}"
 
       # Both gated on the deploy job's own publish gate, so a run that cannot
       # publish does no Pages work: no API call to configure Pages, no artifact

data-index/configs.yml

@@ -88,6 +88,20 @@ repos:
     description: >-
       Combined bibliographic index of ITU-R and ITU-T publications in Relaton
       format.
+  # Combined IETF corpus for Relaton v3 (parsed from ietf-tools'
+  # relaton-data-{rfcs,ids,rfcsubseries}). publish_data puts the corpus
+  # on the Pages site so clients fetch documents from the same origin
+  # as the machine index; the data is fully derived, so it need not
+  # live in git long-term.
+  - repo: ietf
+    display: IETF
+    source: index-v1.yaml
+    branch: main
+    pubid_class: Pubid::Ietf::Identifier
+    publish_data: true
+    description: >-
+      Combined bibliographic index of IETF RFCs, Internet-Drafts and
+      BCP/STD/FYI series in Relaton format.
   - { repo: jcgm,         display: JCGM,          source: index-v1.yaml, branch: main, pubid_class: Pubid::Jcgm::Identifier }
   - { repo: jis,          display: JIS,           source: index-v2.yaml, branch: v2,   pubid_class: Pubid::Jis::Identifier }
   - { repo: nist,         display: NIST,          source: index-v2.yaml, branch: v2,   pubid_class: Pubid::Nist::Identifier }

data-index/generated/ietf_config.yml

@@ -0,0 +1,11 @@
+title: IETF Index
+description: >-
+  Combined bibliographic index of IETF RFCs, Internet-Drafts and BCP/STD/FYI series in Relaton format.
+paginate: 100
+jekyll-index:
+  favicon: 'https://www.relaton.org/favicon.ico'
+  source: 'index-v1.yaml'
+  baseurl: 'https://raw.githubusercontent.com/relaton/relaton-data-ietf/main/'
+  add_type_to_reference: true
+  pubid_class: 'Pubid::Ietf::Identifier'
+  pubid_require: 'pubid'

lib/data_index_config.rb

@@ -67,6 +67,12 @@ def branding(repo, title: nil, favicon: nil, description: nil)
       "title" => present(title) || (found ? entry_title(found) : derived_title(repo)),
       "favicon" => present(favicon) || (found ? entry_favicon(found) : ""),
       "description" => present(description) || (found ? entry_description(found) : ""),
+      # Machine-index flags for `relaton index` (relaton/relaton#113).
+      # Derived from the existing pubid_class row so no new configs.yml
+      # key is required for structured corpora; publish_data is the one
+      # explicit opt-in (only fully-derived corpora want it).
+      "pubid_flavor" => found ? pubid_flavor(found) : "",
+      "publish_data" => found && found["publish_data"] ? "true" : "false",
     }
   end
 
@@ -187,4 +193,14 @@ def pubid_class(entry)
 
     value.strip.sub(/\A::/, "")
   end
+
+  # "Pubid::Iso::Identifier" -> "iso". The short flavor name is what
+  # `relaton index --pubid-flavor` takes.
+  def pubid_flavor(entry)
+    klass = pubid_class(entry)
+    return "" unless klass
+
+    m = klass.match(/\APubid::(\w+)::/)
+    m ? m[1].downcase : ""
+  end
 end

spec/cimas_data_pages_spec.rb

@@ -77,10 +77,9 @@
     # has no configs.yml row would deploy the theme with no per-repo _config.yml.
     # Excludes are the deliberate non-index repos (see data-pages-rollout hand-off).
     known = configs.repos.map { |e| "relaton-data-#{e['repo']}" }
-    # ietf gets deploy.yml but is deliberately not a Pages index (no document
-    # index published); every other data-group repo is covered by configs.yml,
-    # including the already-live ids/oasis/w3c now folded in.
-    excluded = %w[relaton-data-ietf]
+    # Every data-group repo that gets deploy.yml is covered by configs.yml
+    # (ietf was excluded until its combined-corpus rollout landed).
+    excluded = %w[]
     deploys_pages =
       data_group.select do |name|
         files = repositories.fetch(name, {}).fetch("files", nil) || {}
@@ -93,9 +92,8 @@
   end
 
   it "syncs deploy.yml and check-index.yml together, or neither" do
-    # Not folded into the per-repo examples above: those iterate configs.yml,
-    # which deliberately has no relaton-data-ietf row (it gets deploy.yml but
-    # publishes no document index). A repo that merges data with no PR-time
+    # Not folded into the per-repo examples above: those iterate configs.yml.
+    # A repo that merges data with no PR-time
     # build is exactly the gap this file exists to make loud, whether or not it
     # has a page — so drive this one off cimas.yml instead.
     #

spec/data_index_config_spec.rb

@@ -135,17 +135,18 @@ def jekyll_index(repo)
   end
 
   describe "configs.yml data" do
-    it "covers exactly the 30 repos with no duplicates" do
+    it "covers exactly the 31 repos with no duplicates" do
       repos = config.repos.map { |e| e["repo"] }
-      expect(repos.size).to eq(30)
-      expect(repos.uniq.size).to eq(30)
+      expect(repos.size).to eq(31)
+      expect(repos.uniq.size).to eq(31)
       expect(repos).to include("iso", "ieee", "jis", "adobe", "easc", "gost", "jcgm", "oiml", "iala")
       expect(repos).to include("ids", "oasis", "w3c") # already-live, folded in
+      expect(repos).to include("ietf") # combined v3 corpus
       # Both ITU rows: `itu` is the combined ITU-R + ITU-T corpus, `itu-r` the
       # ITU-R-only repo the relaton gem still consumes. Neither is a typo for
       # the other, and dropping either silently 404s a site.
       expect(repos).to include("itu", "itu-r")
-      expect(repos).not_to include("sdo", "ietf", "misc")
+      expect(repos).not_to include("sdo", "misc")
     end
 
     it "gives every entry the required fields" do

spec/index_branding_spec.rb

@@ -8,7 +8,7 @@
 #
 # The load-bearing invariants here are the fallbacks: the workflow passes all
 # three flags unconditionally, and Cimas syncs deploy.yml into one repo
-# (relaton-data-ietf) that configs.yml deliberately does not cover.
+# (any future data-group repo) that configs.yml does not yet cover.
 require "English" # $CHILD_STATUS
 require "shellwords"
 
@@ -80,9 +80,11 @@
         title: "Custom", favicon: "custom.ico", description: "Custom desc",
       )
 
-      expect(branding).to eq(
+      expect(branding).to include(
         "title" => "Custom", "favicon" => "custom.ico", "description" => "Custom desc",
       )
+      expect(branding["pubid_flavor"]).to eq("iso")
+      expect(branding["publish_data"]).to eq("false")
     end
 
     it "treats an explicit blank override as unset" do
@@ -97,11 +99,18 @@
     end
 
     it "falls back to the derived title and no branding for a repo configs.yml omits" do
-      # relaton-data-ietf gets deploy.yml from Cimas but publishes no document
-      # index, so it has no configs.yml row (see cimas_data_pages_spec.rb).
-      # Its result must match what the retired shell derivation produced.
-      expect(config.branding("relaton/relaton-data-ietf"))
-        .to eq("title" => "IETF Index", "favicon" => "", "description" => "")
+      # A data-group repo that has not yet been folded into configs.yml must
+      # still resolve without raising (the deploy step always runs branding).
+      expect(config.branding("relaton/relaton-data-nope"))
+        .to include("title" => "NOPE Index", "favicon" => "", "description" => "",
+                    "pubid_flavor" => "", "publish_data" => "false")
+    end
+
+    it "resolves ietf with publish_data and the ietf pubid flavor" do
+      branding = config.branding("relaton/relaton-data-ietf")
+      expect(branding["title"]).to eq("IETF Index")
+      expect(branding["pubid_flavor"]).to eq("ietf")
+      expect(branding["publish_data"]).to eq("true")
     end
 
     it "does not raise for an unknown repo, unlike #entry" do
@@ -162,17 +171,28 @@
       out = `#{bin.shellescape} relaton/relaton-data-w3c 2>/dev/null`
 
       expect($CHILD_STATUS).to be_success
-      expect(parse.call(out)).to eq(
+      expect(parse.call(out)).to include(
         config.branding("relaton/relaton-data-w3c"),
       )
     end
 
     it "resolves a repo configs.yml does not cover" do
+      out = `#{bin.shellescape} relaton/relaton-data-nope 2>/dev/null`
+
+      expect($CHILD_STATUS).to be_success
+      expect(parse.call(out)).to include(
+        "title" => "NOPE Index", "favicon" => "", "description" => "",
+        "pubid_flavor" => "", "publish_data" => "false",
+      )
+    end
+
+    it "emits ietf's pubid_flavor and publish_data" do
       out = `#{bin.shellescape} relaton/relaton-data-ietf 2>/dev/null`
 
       expect($CHILD_STATUS).to be_success
-      expect(parse.call(out))
-        .to eq("title" => "IETF Index", "favicon" => "", "description" => "")
+      parsed = parse.call(out)
+      expect(parsed.fetch("pubid_flavor")).to eq("ietf")
+      expect(parsed.fetch("publish_data")).to eq("true")
     end
 
     it "applies the flags the workflow always passes, blanks included" do