Merge branch 'feature/intro-pick-links'

website/build.py

@@ -39,6 +39,30 @@ SPONSORSHIP_DESCRIPTION = "Sponsorship for awesome-python: tiers, audience, and
 
 BUNDLED_PREFIX_RE = re.compile(r"^\(part of ")
 
+# Category intros name projects as their docs do, README entries by their PyPI name
+PICK_ALIASES = {
+    "Airflow": "apache-airflow",
+    "Beautiful Soup": "beautifulsoup4",
+    "Cacheops": "django-cacheops",
+    "Chroma": "chromadb",
+    "Coverage.py": "coverage",
+    "Faiss": "faiss-cpu",
+    "gRPC": "grpcio",
+    "Grappelli": "django-grappelli",
+    "Hydra": "hydra-core",
+    "Ibis": "ibis-framework",
+    "Material for MkDocs": "mkdocs-material",
+    "OpenCV": "opencv-python",
+    "Playwright": "playwright-python",
+    "PyAV": "av",
+    "python-oracledb": "oracledb",
+    "Sherlock": "sherlock-project",
+    "Silk": "django-silk",
+    "Surprise": "scikit-surprise",
+    "Unfold": "django-unfold",
+    "Vega-Altair": "altair",
+}
+
 SOURCE_TYPE_DOMAINS = {
     "docs.python.org": BUILTIN_FILTER,
     "gitlab.com": "GitLab",
@@ -253,7 +277,52 @@ def subcategory_meta_description(name: str, parent_name: str, entry_names: Seque
     return f"The {name} picks in Awesome Python's {parent_name} list: {names}."
 
 
-def load_category_intro(path: Path) -> tuple[str, str, str, str]:
+def entry_name_key(name: str) -> str:
+    return re.sub(r"[^a-z0-9]", "", name.lower())
+
+
+def link_pick_names(pick: str, slugs_by_key: dict[str, str]) -> str:
+    """Link entry names in a "How to choose" pick to their rows, preferring the longest match.
+
+    Names match ignoring case and punctuation, so the README's PyPI-style
+    "django-ninja" matches the intro's "Django Ninja".
+    """
+    words = list(re.finditer(r"`[^`]*`|[^\s,]+", pick))
+    parts, pos, i = [], 0, 0
+    while i < len(words):
+        for j in range(min(len(words), i + 4), i, -1):
+            start, end = words[i].start(), words[j - 1].end()
+            span = pick[start:end]
+            slug = slugs_by_key.get(entry_name_key(span))
+            # Code spans and dangling punctuation like "The Algorithms -" stay outside links
+            if slug and span[0].isalnum() and span[-1].isalnum() and "," not in span and "`" not in span:
+                parts.append(f"{pick[pos:start]}[{span}](#entry-{slug})")
+                pos, i = end, j
+                break
+        else:
+            i += 1
+    return "".join(parts) + pick[pos:]
+
+
+def link_intro_picks(text: str, entry_names: Sequence[str]) -> str:
+    """Link the picks in an intro's "How to choose:" list to their rows in the table below."""
+    head, marker, rest = text.partition("\nHow to choose:\n\n")
+    if not marker:
+        return text
+    slugs_by_key = {entry_name_key(name): slugify(name) for name in entry_names}
+    for alias, name in PICK_ALIASES.items():
+        if entry_name_key(name) in slugs_by_key:
+            slugs_by_key[entry_name_key(alias)] = slugs_by_key[entry_name_key(name)]
+    lines = rest.split("\n")
+    for i, line in enumerate(lines):
+        if not line.startswith("- "):
+            break
+        situation, _, pick = line.rpartition(": ")
+        lines[i] = f"{situation}: {link_pick_names(pick, slugs_by_key)}"
+    return head + marker + "\n".join(lines)
+
+
+def load_category_intro(path: Path, entry_names: Sequence[str] = ()) -> tuple[str, str, str, str]:
     """Render a category intro file to HTML, split at the end of its "How to choose:" list.
 
     Returns the part shown above the table, the guide shown below it, and the
@@ -264,10 +333,10 @@ def load_category_intro(path: Path) -> tuple[str, str, str, str]:
     if not path.exists():
         return "", "", "", ""
     md = MarkdownIt("commonmark")
-    tokens = md.parse(path.read_text(encoding="utf-8"))
+    tokens = md.parse(link_intro_picks(path.read_text(encoding="utf-8"), entry_names))
     for token in tokens:
         for child in token.children or []:
-            if child.type == "link_open":
+            if child.type == "link_open" and not str(child.attrGet("href")).startswith("#"):
                 child.attrSet("target", "_blank")
                 child.attrSet("rel", "noopener")
     lead = next(node for node in SyntaxTreeNode(tokens).children if node.type == "paragraph")
@@ -731,6 +800,7 @@ def build(repo_root: Path) -> None:
         trim_blocks=True,
         lstrip_blocks=True,
     )
+    env.filters["slugify"] = slugify
     site_dir = website / "output"
     if site_dir.exists():
         shutil.rmtree(site_dir)
@@ -776,7 +846,10 @@ def build(repo_root: Path) -> None:
         page_dir.mkdir(parents=True, exist_ok=True)
         parent_name = parent_category["name"] if parent_category else None
         category_title = category_meta_title(category["name"], parent_name)
-        intro_html, guide_html, intro_lead, _ = load_category_intro(website / "data" / "category_intros" / f"{current_path.removeprefix('/categories/').strip('/')}.md")
+        page_entries = [entry for group in entry_groups for entry in group["entries"]] if entry_groups else entries
+        intro_html, guide_html, intro_lead, _ = load_category_intro(
+            website / "data" / "category_intros" / f"{current_path.removeprefix('/categories/').strip('/')}.md", [e["name"] for e in page_entries]
+        )
         if intro_lead:
             category_description = intro_lead
         elif parent_name:
@@ -787,7 +860,6 @@ def build(repo_root: Path) -> None:
         if parent_category:
             breadcrumbs.append((parent_category["name"], category_public_url(parent_category)))
         breadcrumbs.append((category["name"], category_url))
-        page_entries = [entry for group in entry_groups for entry in group["entries"]] if entry_groups else entries
         category_json_ld = json.dumps(
             build_category_json_ld(category_title.removesuffix(" - Awesome Python"), category_url, category_description, page_entries, breadcrumbs),
             ensure_ascii=False,

website/static/main.js

@@ -367,12 +367,25 @@ sortHeaders.forEach(function (th) {
   });
 });
 
+function openEntryRow(row) {
+  if (row.hidden && searchInput) {
+    searchInput.value = "";
+    applyFilters();
+  }
+  row.classList.add("open");
+  row.setAttribute("aria-expanded", "true");
+}
+
 // Group headings are hidden while sorted flat or filtered out by search, so a link to one must restore them first
 document.addEventListener("click", function (e) {
   const link = e.target.closest('a[href*="#"]');
   if (!link || link.pathname !== location.pathname) return;
-  const heading = document.getElementById(decodeURIComponent(link.hash.slice(1)));
-  const groupRow = heading ? heading.closest(".group-row") : null;
+  const target = document.getElementById(decodeURIComponent(link.hash.slice(1)));
+  if (target && target.matches("tr.row")) {
+    openEntryRow(target);
+    return;
+  }
+  const groupRow = target ? target.closest(".group-row") : null;
   if (!groupRow) return;
   if (activeSort.col !== "editorial") {
     activeSort = defaultSort;
@@ -385,6 +398,11 @@ document.addEventListener("click", function (e) {
   }
 });
 
+if (location.hash) {
+  const linkedRow = document.getElementById(decodeURIComponent(location.hash.slice(1)));
+  if (linkedRow && linkedRow.matches("tr.row")) openEntryRow(linkedRow);
+}
+
 if (searchInput) {
   let searchTimer;
   searchInput.addEventListener("input", function () {

website/static/style.css

@@ -837,6 +837,7 @@ kbd {
 
 .row {
   cursor: pointer;
+  scroll-margin-top: 4.5rem;
 }
 
 .group-row th {

website/templates/category.html

@@ -81,6 +81,7 @@
         {% set section_path = "/categories/" ~ parent_category.slug ~ "/" if parent_category else current_path %}
         <tr
           class="row"
+          {% if not group_categories %}id="entry-{{ entry.name | slugify }}"{% endif %}
           tabindex="0"
           aria-expanded="false"
           aria-controls="expand-{{ index }}"

website/tests/test_build.py

@@ -1100,7 +1100,7 @@ class TestBuild:
         parser.feed(category_html)
         assert parser.meta_by_name["description"] == "Use w1 for most apps."
         assert '<div class="category-intro"><p>Use <code>w1</code> for most apps.</p>' in category_html
-        assert "<li>Small apps: w1</li>" in category_html
+        assert '<li>Small apps: <a href="#entry-w1">w1</a></li>' in category_html
         assert '<a href="https://example.com/docs" target="_blank" rel="noopener">the docs</a>' in category_html
 
     def test_build_renders_category_guide_below_table(self, tmp_path):
@@ -1113,7 +1113,7 @@ class TestBuild:
 
         category_html = (tmp_path / "website" / "output" / "categories" / "widgets" / "index.html").read_text(encoding="utf-8")
         intro_html = category_html.split('<div class="category-intro">', 1)[1].split("</div>", 1)[0]
-        assert "<li>Small apps: w1</li>" in intro_html
+        assert '<li>Small apps: <a href="#entry-w1">w1</a></li>' in intro_html
         assert "Set up w1" not in intro_html
         guide_html = category_html.split('<section class="guide-band" id="guide">', 1)[1]
         assert "<h2>Widgets guide</h2>" in guide_html
@@ -1599,3 +1599,20 @@ class TestLoadCategoryIntro:
 
     def test_returns_empty_strings_without_intro_file(self, tmp_path):
         assert load_category_intro(tmp_path / "missing.md") == ("", "", "", "")
+
+    def test_links_picks_to_entry_rows(self, tmp_path):
+        path = tmp_path / "widgets.md"
+        path.write_text(
+            "Use w1.\n\nHow to choose:\n\n- Small apps: Django Ninja, or `uv tool` on uv\n- Big apps: Django\n- Old apps: The Algorithms - Python\n\nSee [w1](https://w1.example).\n", encoding="utf-8"
+        )
+        intro_html, guide_html, _, _ = load_category_intro(path, ["django-ninja", "Django", "uv", "TheAlgorithms"])
+        assert '<li>Small apps: <a href="#entry-django-ninja">Django Ninja</a>, or <code>uv tool</code> on <a href="#entry-uv">uv</a></li>' in intro_html
+        assert '<li>Big apps: <a href="#entry-django">Django</a></li>' in intro_html
+        assert '<li>Old apps: <a href="#entry-thealgorithms">The Algorithms</a> - Python</li>' in intro_html
+        assert '<a href="https://w1.example" target="_blank" rel="noopener">w1</a>' in guide_html
+
+    def test_links_pick_aliases_to_entry_rows(self, tmp_path):
+        path = tmp_path / "widgets.md"
+        path.write_text("Use w1.\n\nHow to choose:\n\n- Vision: OpenCV\n", encoding="utf-8")
+        intro_html, _, _, _ = load_category_intro(path, ["opencv-python"])
+        assert '<li>Vision: <a href="#entry-opencv-python">OpenCV</a></li>' in intro_html