Vertex ai schema updates

.gitignore

@@ -13,6 +13,7 @@ _site
 .sass-cache
 .jekyll-metadata
 public/
+tests/public_test/
 node_modules/
 _gen/
 .hugo_build.lock

config/_default/params.yaml

@@ -166,9 +166,6 @@ ui:
   # Sidebar generation is slow otherwise
   sidebar_cache_limit: 100
 
-  # We have almost 200 attributes; don't truncate the sidebar to max 50 contents.
-  sidebar_menu_truncate:  0
-
   #  Set to true to disable breadcrumb navigation.
   breadcrumb_disable: false
 

config/testing/hugo.yaml

@@ -0,0 +1,50 @@
+# Hugo testing environment configuration
+#
+# Used exclusively when running the bibliography JSON-LD test suite:
+#
+#   hugo --environment testing --destination tests/public_test
+#
+# This environment mounts the test fixtures from tests/fixtures/bibliography/
+# alongside the real bibliography content, so the JSON-LD template is exercised
+# against controlled data without those pages ever appearing in a production build.
+#
+# The module.mounts block must re-declare all standard project-level mounts
+# because adding any mount replaces Hugo's defaults for the project.
+# Theme (Docsy) mounts defined within that module are unaffected.
+
+baseURL: "http://localhost/"
+
+publishDir: tests/public_test
+
+# Broken refs in unrelated content files must not block the test build.
+refLinksErrorLevel: WARNING
+
+# Explicit mounts (see module section below) require this to be re-stated
+# so that English content URLs do not gain an /en/ prefix.
+defaultContentLanguageInSubdir: false
+
+module:
+  mounts:
+    # ── Standard project mounts (preserve defaults) ──────────────────────────
+    # Mount content/en/ directly as the English language content root so that
+    # URLs are generated without an /en/ prefix (matching production behavior).
+    - source: content/en
+      target: content
+      lang: en
+    - source: static
+      target: static
+    - source: layouts
+      target: layouts
+    - source: data
+      target: data
+    - source: assets
+      target: assets
+    - source: i18n
+      target: i18n
+    - source: archetypes
+      target: archetypes
+    # ── Test fixtures ─────────────────────────────────────────────────────────
+    # Mount alongside the real bibliography content for the English language.
+    - source: tests/fixtures/bibliography
+      target: content/history/bibliography
+      lang: en

content/en/history/bibliography/_index.md

@@ -4,6 +4,7 @@ heading: Interlisp Bibliography
 type: bibliography
 cascade:
     type: bibliography
+    toc_hide: true
 weight: 5
 aliases:
  - /bibliography/

layouts/_partials/bibliography-date.html

@@ -0,0 +1,27 @@
+{{- /*
+  bibliography-date.html
+  Resolves a bibliography page's publication date.
+
+  The front-matter `date` param is a plain YYYY-MM-DD string produced by
+  bibSplit.pl. Hugo's built-in .Date can be a full datetime parsed from git
+  history; this partial prefers the explicit param when it is well-formed.
+
+  Accepts: page context (.)
+  Returns: dict
+    dateISO   – YYYY-MM-DD string; "0001-01-01" when no date is known
+    hasDate   – true when dateISO is not the zero value
+    dateLabel – .Params.readabledate when present, otherwise dateISO
+*/ -}}
+{{- $dateTime := .Date -}}
+{{- with .Params.date -}}
+  {{- $iso := trim . " " -}}
+  {{- if and (ne $iso "") (findRE `^\d{4}-\d{2}-\d{2}$` $iso) -}}
+    {{- $dateTime = time $iso -}}
+  {{- end -}}
+{{- end -}}
+{{- $dateISO := $dateTime.Format "2006-01-02" -}}
+{{- return dict
+  "dateISO"   $dateISO
+  "hasDate"   (ne $dateISO "0001-01-01")
+  "dateLabel" (or .Params.readabledate $dateISO)
+-}}

layouts/_partials/bibliography-json-ld.html

@@ -11,18 +11,13 @@
 */ -}}
 {{- if eq .Type "bibliography" -}}
 
+{{- /* ── Date (resolved once, used by the IsPage branch below) ───────────── */ -}}
+{{- $date := partial "bibliography-date.html" . -}}
+
 {{- if .IsPage -}}
 
-{{- /* ── Date: mirror the logic in single.html ──────────────────────────── */ -}}
-{{- $dateTime := .Date -}}
-{{- with .Params.date -}}
-  {{- $iso := trim . " " -}}
-  {{- if and (ne $iso "") (findRE `^\d{4}-\d{2}-\d{2}$` $iso) -}}
-    {{- $dateTime = time $iso -}}
-  {{- end -}}
-{{- end -}}
-{{- $dateISO := $dateTime.Format "2006-01-02" -}}
-{{- $hasDate  := ne $dateISO "0001-01-01" -}}
+{{- $dateISO := $date.dateISO -}}
+{{- $hasDate := $date.hasDate -}}
 
 {{- /* ── Map item_type → Schema.org @type ──────────────────────────────── */ -}}
 {{- $itemType   := .Params.item_type | default "document" -}}
@@ -91,11 +86,36 @@
 {{- with .Params.url_source -}}{{- $sameAs = append (trim . " ") $sameAs -}}{{- end -}}
 {{- with .Params.zotero_url -}}{{- $sameAs = append (trim . " ") $sameAs -}}{{- end -}}
 
+{{- /* ── CS Concepts: about[] + keywords[] ────────────────────────────
+     Reads the `concepts:` list from front matter (list of concept IDs).
+     Looks each ID up in data/bibliography/concepts.json to get the name.
+     Emits schema:about (array of DefinedTerm) and schema:keywords (string).
+*/ -}}
+{{- $conceptData   := site.Data.bibliography.concepts -}}
+{{- $conceptIds    := .Params.concepts -}}
+{{- $aboutObjs     := slice -}}
+{{- $keywordNames  := slice -}}
+{{- if reflect.IsSlice $conceptIds -}}
+  {{- range $conceptIds -}}
+    {{- $id      := trim . " " -}}
+    {{- $concept := index $conceptData $id -}}
+    {{- if $concept -}}
+      {{- $aboutObjs    = append (dict
+            "@type"          "DefinedTerm"
+            "@id"            (printf "https://interlisp.org/concepts/#%s" $id)
+            "name"           $concept.name
+            "inDefinedTermSet" "https://interlisp.org/data/cs-concepts.jsonld"
+          ) $aboutObjs -}}
+      {{- $keywordNames = append $concept.name $keywordNames -}}
+    {{- end -}}
+  {{- end -}}
+{{- end -}}
+
 {{- /* ── Base JSON-LD object (properties common to all types) ─────────── */ -}}
 {{- $ld := dict
   "@context"   "https://schema.org"
   "@type"      $schemaType
-  "name"       .Title
+  "name"       (.Title | strings.TrimRight "\n ")
   "url"        .Permalink
   "inLanguage" "en-US"
 -}}
@@ -124,6 +144,14 @@
   {{- $ld = merge $ld (dict "sameAs" $sameAs) -}}
 {{- end -}}
 
+{{- if gt (len $aboutObjs) 0 -}}
+  {{- $ld = merge $ld (dict "about" $aboutObjs) -}}
+{{- end -}}
+
+{{- if gt (len $keywordNames) 0 -}}
+  {{- $ld = merge $ld (dict "keywords" (delimit $keywordNames ", ")) -}}
+{{- end -}}
+
 {{- /* ── Patent: additionalType + structured identifiers ──────────────── */ -}}
 {{- if eq $itemType "patent" -}}
   {{- $ld = merge $ld (dict "additionalType" "Patent") -}}
@@ -140,10 +168,10 @@
   {{- end -}}
 
   {{- with .Params.assignee -}}
-    {{- $ld = merge $ld (dict "funder" (dict "@type" "Organization" "name" .)) -}}
+    {{- $ld = merge $ld (dict "copyrightHolder" (dict "@type" "Organization" "name" .)) -}}
   {{- end -}}
   {{- with .Params.issuing_authority -}}
-    {{- $ld = merge $ld (dict "countryOfOrigin" (dict "@type" "Country" "name" .)) -}}
+    {{- $ld = merge $ld (dict "validIn" (dict "@type" "DefinedRegion" "name" .)) -}}
   {{- end -}}
 {{- end -}}
 
@@ -160,21 +188,21 @@
 {{- /* ── Conference paper ─────────────────────────────────────────────── */ -}}
 {{- if eq $itemType "paper-conference" -}}
   {{- with .Params.proceedings_title -}}
-    {{- $ld = merge $ld (dict "isPartOf" (dict "@type" "Periodical" "name" .)) -}}
+    {{- $ld = merge $ld (dict "isPartOf" (dict "@type" "Book" "name" .)) -}}
   {{- end -}}
   {{- with .Params.publisher -}}
     {{- $ld = merge $ld (dict "publisher" (dict "@type" "Organization" "name" .)) -}}
   {{- end -}}
+  {{- with .Params.place -}}
+    {{- $ld = merge $ld (dict "locationCreated" (dict "@type" "Place" "name" .)) -}}
+  {{- end -}}
 {{- end -}}
 
 {{- /* ── Book ─────────────────────────────────────────────────────────── */ -}}
 {{- if eq $itemType "book" -}}
   {{- with .Params.publisher -}}
     {{- $ld = merge $ld (dict "publisher" (dict "@type" "Organization" "name" .)) -}}
   {{- end -}}
-  {{- with .Params.place -}}
-    {{- $ld = merge $ld (dict "locationCreated" .) -}}
-  {{- end -}}
 {{- end -}}
 
 {{- /* ── Chapter ──────────────────────────────────────────────────────── */ -}}
@@ -194,10 +222,10 @@
   {{- with .Params.publisher -}}
     {{- $ld = merge $ld (dict "publisher" (dict "@type" "Organization" "name" .)) -}}
   {{- end -}}
-  {{- with .Params.reportType -}}
+  {{- with .Params.report_type -}}
     {{- $ld = merge $ld (dict "additionalType" .) -}}
   {{- end -}}
-  {{- with .Params.reportNumber -}}
+  {{- with .Params.report_number -}}
     {{- $ld = merge $ld (dict "identifier" (dict "@type" "PropertyValue" "propertyID" "report-number" "value" .)) -}}
   {{- end -}}
 {{- end -}}
@@ -243,15 +271,12 @@
   {{- end -}}
 {{- end -}}
 
-<script type="application/ld+json">
-{{- $ld | jsonify (dict "indent" "  ") | safeJS -}}
-</script>
+{{- printf "<script type=\"application/ld+json\">\n%s\n</script>" ($ld | jsonify (dict "indent" "  ")) | safeHTML -}}
 
 {{- else if .IsSection -}}
 
 {{- /* ── COLLECTION PAGE (bibliography index) ──────────────────────────── */ -}}
 {{- $pages := .RegularPages -}}
-{{- $pages  = sort $pages "Date" "desc" -}}
 {{- $pages  = sort $pages "Title" "asc" -}}
 
 {{- $itemList := slice -}}
@@ -281,9 +306,7 @@
   )
 -}}
 
-<script type="application/ld+json">
-{{- $ld | jsonify (dict "indent" "  ") | safeJS -}}
-</script>
+{{- printf "<script type=\"application/ld+json\">\n%s\n</script>" ($ld | jsonify (dict "indent" "  ")) | safeHTML -}}
 
 {{- end -}}
 

layouts/bibliography/single.html

@@ -30,18 +30,10 @@ <h1>{{ .Title }}</h1>
   </p>
 {{- end -}}
 <p>
-  {{- $dateTime := .Date -}}
-  {{- with .Params.date -}}
-    {{- $isoDate := trim . " " -}}
-    {{- if and (ne $isoDate "") (findRE `^\d{4}-\d{2}-\d{2}` $isoDate) -}}
-      {{- $dateTime = time $isoDate -}}
-    {{- end -}}
-  {{- end -}}
-  {{- $dateISO := $dateTime.Format "2006-01-02" -}}
-  {{- $dateLabel := or .Params.readabledate $dateISO -}}
+  {{- $date := partial "bibliography-date.html" . -}}
   {{- /* Don't display bogus date */ -}}
-  {{- if ne $dateISO "0001-01-01" -}}
-    <time datetime="{{ $dateISO }}">{{ $dateLabel }}</time>
+  {{- if $date.hasDate -}}
+    <time datetime="{{ $date.dateISO }}">{{ $date.dateLabel }}</time>
   {{- end -}}
 </p>
 <p>

scripts/bibSplit.pl

@@ -58,10 +58,12 @@ sub sanitize_text {
 
   my $type = $obj->{type} // '';
 
-  # Titles can have colons and other special characters.  Place YAML keyword on one line
-  # and follow it with the title indented on subsequent line
+  # Titles can have colons and other special characters.  Use a YAML double-quoted scalar
+  # so the decoded value has no trailing newline (the literal-block `|` style would add one).
   my $itemTitle = sanitize_text($obj->{title} // '');
-  my $title = $itemTitle eq '' ? "title: ''" : "title: |\n  $itemTitle\n";
+  (my $escapedTitle = $itemTitle) =~ s/\\/\\\\/g;
+  $escapedTitle =~ s/"/\\"/g;
+  my $title = $itemTitle eq '' ? "title: ''" : "title: \"$escapedTitle\"";
 
   # Abstracts can be multi-line and  contain multiple paragraphs.  Place YAML keyword on
   # one line and follow it with the abstract indented on subsequent lines.
@@ -78,25 +80,25 @@ sub sanitize_text {
   my $itemAuthors = '';
   if (ref($obj->{authorsFormatted}) eq 'ARRAY' && @{$obj->{authorsFormatted}}) {
     $itemAuthors = "\n";
-    for my $a (@{$obj->{authorsFormatted}}) {
+    for my $author (@{$obj->{authorsFormatted}}) {
       # The encode_json is where extended unicode chars get corrupted, e.g., "Emanuelson, Pär"
       # There may be other things that now don't work!!
       # my $quoted = encode_json($a // '');
       # sanitize_text seems to handle them correctly
-      my $san = sanitize_text($a // '');
-      $itemAuthors .= "  - \"$san\"\n";
+      my $san_author = sanitize_text($author // '');
+      $itemAuthors .= "  - \"$san_author\"\n";
     }
     $itemAuthors =~ s/\n$//u;  # strip trailing newline
   }
 
   my $itemEditors = '';
   if (ref($obj->{editorsFormatted}) eq 'ARRAY' && @{$obj->{editorsFormatted}}) {
     $itemEditors = "\n";
-    for my $a (@{$obj->{editorsFormatted}}) {
+    for my $editor (@{$obj->{editorsFormatted}}) {
       # as above...
-      # my $quoted = encode_json($a // '');
-      my $san = sanitize_text($a // '');
-      $itemEditors .= "  - \"$san\"\n";
+      # my $quoted = encode_json($editor // '');
+      my $san_editor = sanitize_text($editor // '');
+      $itemEditors .= "  - \"$san_editor\"\n";
     }
     $itemEditors =~ s/\n$//u;  # strip trailing newline
   }
@@ -185,6 +187,7 @@ sub sanitize_text {
 
 $extraFields
 tags:
+concepts:
 url_source: $urlSource
 zotero_url: "https://www.zotero.org/groups/2914042/items/$key"
 

tests/fixtures/bibliography/ZTEST-BLOG.md

@@ -0,0 +1,20 @@
+---
+title: "Test Blog Post"
+date: 2021-08-20
+readabledate: 2021-08-20
+type: bibliography
+item_type: post-weblog
+authors:
+  - "Blogger, Test"
+editors:
+abstract: |
+  A test abstract for a blog post used by automated test fixtures.
+
+blog_title: "Test Tech Blog"
+
+tags:
+url_source: "https://example.com/blog/post"
+zotero_url: "https://www.zotero.org/groups/test/items/ZTESTBLG"
+
+lastmod: 2023-08-01T00:00:00Z
+---

tests/fixtures/bibliography/ZTEST-BOOK.md

@@ -0,0 +1,20 @@
+---
+title: "Test Book Title"
+date: 1995-01-01
+readabledate: 1995
+type: bibliography
+item_type: book
+authors:
+  - "Author, Test"
+editors:
+abstract: |
+  A test abstract for a book used by automated test fixtures.
+
+publisher: "Test Publisher"
+
+tags:
+url_source: "https://example.com/book"
+zotero_url: "https://www.zotero.org/groups/test/items/ZTESTBOOK"
+
+lastmod: 2022-01-01T00:00:00Z
+---