docs: glossary infra (#34231)

* feat: glossary infra

* fix static analysis error

* fix ruff linter error.

* updates docs.yaml to use ubuntu-24.04

* code review fixes

docs/css/tooltip.css

@@ -0,0 +1,44 @@
+[data-tooltip] {
+  position: relative;
+  display: inline-block;
+  border-bottom: 1px dotted black;
+}
+
+[data-tooltip] .tooltip-content {
+  width: max-content;
+  max-width: 25em;
+  position: absolute;
+  top: 100%;
+  left: 50%;
+  transform: translateX(-50%);
+  background-color: white;
+  color: #404040;
+  box-shadow: 0 4px 14px 0 rgba(0,0,0,.2), 0 0 0 1px rgba(0,0,0,.05);
+  padding: 10px;
+  font: 14px/1.5 Lato, proxima-nova, Helvetica Neue, Arial, sans-serif;
+  text-decoration: none;
+  opacity: 0;
+  visibility: hidden;
+  transition: opacity 0.1s, visibility 0s;
+  z-index: 1000;
+  pointer-events: none; /* Prevent accidental interaction */
+}
+
+[data-tooltip]:hover .tooltip-content {
+  opacity: 1;
+  visibility: visible;
+  pointer-events: auto; /* Allow interaction when visible */
+}
+
+.tooltip-content .tooltip-glossary-link {
+  display: inline-block;
+  margin-top: 8px;
+  font-size: 12px;
+  color: #007bff;
+  text-decoration: none;
+}
+
+.tooltip-content .tooltip-glossary-link:hover {
+  color: #0056b3;
+  text-decoration: underline;
+}

docs/hooks/glossary.py

@@ -0,0 +1,68 @@
+import re
+import tomllib
+
+def load_glossary(file_path="docs/glossary.toml"):
+  with open(file_path, "rb") as f:
+    glossary_data = tomllib.load(f)
+  return glossary_data.get("glossary", {})
+
+def generate_anchor_id(name):
+  return name.replace(" ", "-").replace("_", "-").lower()
+
+def format_markdown_term(name, definition):
+  anchor_id = generate_anchor_id(name)
+  markdown = f"* [**{name.replace('_', ' ').title()}**](#{anchor_id})"
+  if definition.get("abbreviation"):
+    markdown += f" *({definition['abbreviation']})*"
+  if definition.get("description"):
+    markdown += f": {definition['description']}\n"
+  return markdown
+
+def glossary_markdown(vocabulary):
+  markdown = ""
+  for category, terms in vocabulary.items():
+    markdown += f"## {category.replace('_', ' ').title()}\n\n"
+    for name, definition in terms.items():
+      markdown += format_markdown_term(name, definition)
+  return markdown
+
+def format_tooltip_html(term_key, definition, html):
+  display_term = term_key.replace("_", " ").title()
+  clean_description = re.sub(r"\[(.+)]\(.+\)", r"\1", definition["description"])
+  glossary_link = (
+    f"<a href='/concepts/glossary#{term_key}' class='tooltip-glossary-link' title='View in glossary'>Glossary🔗</a>"
+  )
+  return re.sub(
+    re.escape(display_term),
+    lambda
+    match: f"<span data-tooltip>{match.group(0)}<span class='tooltip-content'>{clean_description} {glossary_link}</span></span>",
+    html,
+    flags=re.IGNORECASE,
+  )
+
+def apply_tooltip(_term_key, _definition, pattern, html):
+  return re.sub(
+    pattern,
+    lambda match: format_tooltip_html(_term_key, _definition, match.group(0)),
+    html,
+    flags=re.IGNORECASE,
+  )
+
+def tooltip_html(vocabulary, html):
+  for _category, terms in vocabulary.items():
+    for term_key, definition in terms.items():
+      if definition.get("description"):
+        pattern = rf"(?<!\w){re.escape(term_key.replace('_', ' ').title())}(?![^<]*<\/a>)(?!\([^)]*\))"
+        html = apply_tooltip(term_key, definition, pattern, html)
+  return html
+
+# Page Hooks
+def on_page_markdown(markdown, **kwargs):
+  glossary = load_glossary()
+  return markdown.replace("{{GLOSSARY_DEFINITIONS}}", glossary_markdown(glossary))
+
+def on_page_content(html, **kwargs):
+  if kwargs.get("page").title == "Glossary":
+    return html
+  glossary = load_glossary()
+  return tooltip_html(glossary, html)