deploy: ca4c8f7691

generate.py

@@ -26,42 +26,45 @@ def slugify(text: str) -> str:
 def parse_readme(path: str) -> list[dict]:
     """Parse README.md and return a list of project entries (no API data)."""
     entries = []
-    current_language = ""
     current_category = ""
 
     re_h2 = re.compile(r"^## (.+)$")
-    re_h3 = re.compile(r"^### (.+)$")
     re_entry = re.compile(r"^\s*- \[(.+?)\]\((.+?)\) - (.+)$")
     re_github = re.compile(r"\[GitHub\]\((https://github\.com/[\w-]+/[-\w\.]+)\)")
-
-    skip_sections = {"Languages"}
-
-    # Strip markdown badge images before parsing
     re_badge = re.compile(r"\s*!\[[^\]]*\]\([^)]*\)\s*")
+    re_langs = re.compile(r'^((?:`[^`]+`\s*)+)-\s*(.*)$')
+
+    skip_sections = {"Contents"}
 
     with open(path, "r", encoding="utf-8") as f:
         for line in f:
             line = re_badge.sub(" ", line).rstrip("\n")
 
             m = re_h2.match(line)
-            if m:
-                current_language = m.group(1).strip()
-                current_category = ""
-                continue
-
-            m = re_h3.match(line)
             if m:
                 current_category = m.group(1).strip()
                 continue
 
-            if current_language in skip_sections:
+            if current_category in skip_sections:
                 continue
 
             m = re_entry.match(line)
             if m:
                 name = m.group(1).strip()
                 url = m.group(2).strip()
-                desc = m.group(3).strip()
+                raw_desc = m.group(3).strip()
+
+                # Extract inline language tags
+                m_lang = re_langs.match(raw_desc)
+                if m_lang:
+                    lang_str = m_lang.group(1)
+                    desc = m_lang.group(2)
+                    languages = re.findall(r'`([^`]+)`', lang_str)
+                else:
+                    desc = raw_desc
+                    languages = []
+
+                primary_language = languages[0] if languages else ""
 
                 github_url = ""
                 gh_match = re_github.search(desc)
@@ -81,15 +84,15 @@ def parse_readme(path: str) -> list[dict]:
 
                 is_cran = "cran.r-project.org" in url
                 is_pypi = "pypi.org" in url or "pypi.python.org" in url
-                is_commercial = current_language == "Commercial & Proprietary Services"
+                is_commercial = current_category == "Commercial & Proprietary Services"
-                category = current_category or current_language
+                section_slug = slugify(current_category)
-                section_slug = slugify(category)
 
                 entries.append(
                     {
                         "project": name,
-                        "language": current_language,
+                        "language": primary_language,
-                        "category": category,
+                        "languages": ",".join(languages),
+                        "category": current_category,
                         "section_slug": section_slug,
                         "url": url,
                         "description": desc,
@@ -121,6 +124,8 @@ def load_csv(path: str) -> list[dict]:
             # Extract github_url and repo from CSV data
             repo = row.get("repo", "")
             row["github_url"] = f"https://github.com/{repo}" if repo else ""
+            # Ensure languages column exists
+            row["languages"] = row.get("languages", row.get("language", ""))
             # Clean description: strip [GitHub](url) if present
             desc = row.get("description", "")
             desc = re.sub(
@@ -148,25 +153,28 @@ def build_tags_html(e: dict) -> str:
     esc = html.escape
     tags = []
 
-    # Language tag
+    # Language tags (from inline backtick tags)
-    lang = e.get("language", "")
+    languages_str = e.get("languages", e.get("language", ""))
-    if lang and lang != "Commercial & Proprietary Services" and lang != "Related Lists":
+    languages = [l.strip() for l in languages_str.split(",") if l.strip()]
-        lang_slug = slugify(lang)
+    skip_langs = {"Commercial & Proprietary Services", "Related Lists",
-        tags.append(
+                  "Reproducing Works, Training & Books", "Cross-Language Frameworks"}
-            f'<button class="tag tag-lang" data-filter-type="language" '
+    for lang in languages:
-            f'data-filter-value="{esc(lang)}">{esc(lang_slug)}</button>'
+        if lang and lang not in skip_langs:
-        )
+            tags.append(
+                f'<button class="tag tag-lang" data-filter-type="language" '
+                f'data-filter-value="{esc(lang)}">{esc(lang.lower())}</button>'
+            )
 
-    # Section tag
+    # Category tag
-    section_slug = e.get("section_slug", "")
     category = e.get("category", "")
-    if section_slug and section_slug != slugify(lang):
+    section_slug = e.get("section_slug", "")
+    if section_slug:
         tags.append(
             f'<button class="tag tag-section" data-filter-type="category" '
             f'data-filter-value="{esc(category)}">{esc(section_slug)}</button>'
         )
 
-    # Source tags
+    # Source tags (unchanged)
     if e.get("github"):
         tags.append(
             '<button class="tag tag-source tag-github" '
@@ -191,16 +199,99 @@ def build_tags_html(e: dict) -> str:
     return "\n          ".join(tags)
 
 
+def build_tag_cloud(entries: list[dict]) -> str:
+    """Build a tag cloud of popular languages and categories."""
+    from collections import Counter
+
+    # Count language frequencies
+    lang_counts = Counter()
+    for e in entries:
+        langs = [l.strip() for l in e.get("languages", e.get("language", "")).split(",") if l.strip()]
+        lang_counts.update(langs)
+
+    # Remove non-language sections
+    skip = {"Commercial & Proprietary Services", "Related Lists", "Reproducing Works, Training & Books", "Cross-Language Frameworks"}
+    for s in skip:
+        lang_counts.pop(s, None)
+
+    # Count category frequencies
+    cat_counts = Counter(e.get("category", "") for e in entries if e.get("category"))
+
+    # Get top items
+    top_langs = lang_counts.most_common(8)  # Top 8 languages
+    top_cats = cat_counts.most_common(6)    # Top 6 categories
+
+    if not top_langs and not top_cats:
+        return ""
+
+    # Combine and sort by frequency
+    all_items = []
+    for lang, count in top_langs:
+        all_items.append(("language", lang, count))
+    for cat, count in top_cats:
+        all_items.append(("category", cat, count))
+
+    # Sort by count descending
+    all_items.sort(key=lambda x: x[2], reverse=True)
+
+    # Calculate size scale (1.0 to 1.6x)
+    if all_items:
+        min_count = min(item[2] for item in all_items)
+        max_count = max(item[2] for item in all_items)
+        count_range = max_count - min_count if max_count > min_count else 1
+    else:
+        min_count = max_count = count_range = 1
+
+    tags = []
+    esc = html.escape
+    for tag_type, value, count in all_items:
+        # Calculate font size: 1.0 to 1.6
+        size = 1.0 + ((count - min_count) / count_range * 0.6) if count_range > 0 else 1.0
+
+        if tag_type == "language":
+            tags.append(
+                f'<button class="tag tag-lang tag-cloud-item" '
+                f'data-filter-type="language" data-filter-value="{esc(value)}" '
+                f'style="font-size: {size:.2f}em;">{esc(value.lower())}</button>'
+            )
+        else:  # category
+            tags.append(
+                f'<button class="tag tag-section tag-cloud-item" '
+                f'data-filter-type="category" data-filter-value="{esc(value)}" '
+                f'style="font-size: {size:.2f}em;">{esc(value)}</button>'
+            )
+
+    if not tags:
+        return ""
+
+    return f"""        <div class="tag-cloud">
+          <div class="tag-cloud-label">Popular filters:</div>
+          <div class="tag-cloud-items">
+            {chr(10).join("            " + tag for tag in tags)}
+          </div>
+        </div>"""
+
+
 def generate_html(entries: list[dict]) -> str:
     """Generate the full HTML page from project entries."""
     languages = sorted(
         set(
-            e["language"]
+            lang.strip()
             for e in entries
-            if e.get("language") and e["language"] != "Languages"
+            for lang in e.get("languages", e.get("language", "")).split(",")
+            if lang.strip()
+            and lang.strip() not in {
+                "Commercial & Proprietary Services",
+                "Related Lists",
+                "Reproducing Works, Training & Books",
+                "Cross-Language Frameworks",
+            }
         )
     )
 
+    # Generate tag cloud
+    tag_cloud_html = build_tag_cloud(entries)
+
     # Build table rows
     rows = []
     for i, e in enumerate(entries, 1):
@@ -208,7 +299,6 @@ def generate_html(entries: list[dict]) -> str:
         name = esc(e["project"])
         url = esc(e["url"])
         desc = esc(e["description"])
-        language = esc(e.get("language", ""))
         category = esc(e.get("category", ""))
         github_url = esc(e.get("github_url", ""))
         repo = esc(e.get("repo", ""))
@@ -219,6 +309,11 @@ def generate_html(entries: list[dict]) -> str:
         is_pypi = e.get("pypi", False)
         is_commercial = e.get("commercial", False)
 
+        # Languages attribute (space-separated)
+        languages_attr = esc(" ".join(
+            l.strip() for l in e.get("languages", e.get("language", "")).split(",") if l.strip()
+        ))
+
         # Stars display
         stars_html = (
             f'<span class="stars" title="{stars:,} stars">'
@@ -250,7 +345,7 @@ def generate_html(entries: list[dict]) -> str:
         tags_html = build_tags_html(e)
 
         rows.append(
-            f"""      <tr class="row" data-language="{language}" data-category="{category}" data-sources="{sources_attr}" data-stars="{stars}">
+            f"""      <tr class="row" data-languages="{languages_attr}" data-category="{category}" data-sources="{sources_attr}" data-stars="{stars}">
         <td class="col-num">{i}</td>
         <td class="col-name">
           <a href="{url}" target="_blank" rel="noopener">{name}</a>
@@ -331,6 +426,8 @@ def generate_html(entries: list[dict]) -> str:
           </div>
         </div>
 
+{tag_cloud_html}
+
         <div class="filter-bar" id="filter-bar" style="display:none">
           <span class="filter-label">Filtered by:</span>
           <span class="filter-value" id="filter-value"></span>

static/main.js

@@ -73,7 +73,7 @@
         " " +
         (expand ? expand.textContent : "")
       ).toLowerCase();
-      const language = row.dataset.language || "";
+      const languages = (row.dataset.languages || "").split(" ");
       const category = row.dataset.category || "";
       const sources = row.dataset.sources || "";
 
@@ -86,7 +86,7 @@
       if (show && activeFilter.value) {
         const ft = activeFilter.type;
         const fv = activeFilter.value;
-        if (ft === "language" && language !== fv) show = false;
+        if (ft === "language" && !languages.includes(fv)) show = false;
         if (ft === "category" && category !== fv) show = false;
         if (ft === "source" && !sources.split(" ").includes(fv)) show = false;
       }
@@ -128,8 +128,8 @@
     applyFilters();
   });
 
-  // ===== Tag Click =====
+  // ===== Tag Click Handler =====
-  tableBody.addEventListener("click", (e) => {
+  function handleTagClick(e) {
     const tag = e.target.closest(".tag");
     if (tag) {
       e.stopPropagation();
@@ -145,7 +145,16 @@
       applyFilters();
       return;
     }
-  });
+  }
+
+  // Listen for tag clicks on table rows
+  tableBody.addEventListener("click", handleTagClick);
+
+  // Listen for tag clicks on tag cloud (outside table)
+  const tagCloud = $(".tag-cloud");
+  if (tagCloud) {
+    tagCloud.addEventListener("click", handleTagClick);
+  }
 
   // ===== Row Expand =====
   tableBody.addEventListener("click", (e) => {

static/style.css

@@ -363,6 +363,36 @@ button {
   pointer-events: none;
 }
 
+/* ===== Tag Cloud ===== */
+.tag-cloud {
+  padding: 1rem 0 0.5rem 0;
+  margin-bottom: 1rem;
+}
+
+.tag-cloud-label {
+  font-size: 0.75rem;
+  font-weight: 600;
+  text-transform: uppercase;
+  letter-spacing: 0.05em;
+  color: var(--ink-tertiary);
+  margin-bottom: 0.5rem;
+}
+
+.tag-cloud-items {
+  display: flex;
+  flex-wrap: wrap;
+  gap: 0.5rem;
+  align-items: center;
+}
+
+.tag-cloud-item {
+  transition: transform var(--transition), opacity var(--transition);
+}
+
+.tag-cloud-item:hover {
+  transform: scale(1.08);
+}
+
 .filter-controls select {
   padding: 0.625rem 2rem 0.625rem 0.875rem;
   font-family: var(--font);
@@ -703,6 +733,23 @@ button {
   border-color: rgba(252, 211, 77, 0.25);
 }
 
+/* Language-specific tag colors */
+.tag-lang[data-filter-value="Python"] { background: #306998; color: #FFD43B; border: 1px solid rgba(48, 105, 152, 0.3); }
+.tag-lang[data-filter-value="R"] { background: #276DC3; color: #fff; border: 1px solid rgba(39, 109, 195, 0.3); }
+.tag-lang[data-filter-value="Julia"] { background: #9558B2; color: #fff; border: 1px solid rgba(149, 88, 178, 0.3); }
+.tag-lang[data-filter-value="JavaScript"] { background: #F7DF1E; color: #000; border: 1px solid rgba(247, 223, 30, 0.3); }
+.tag-lang[data-filter-value="Rust"] { background: #CE412B; color: #fff; border: 1px solid rgba(206, 65, 43, 0.3); }
+.tag-lang[data-filter-value="C++"] { background: #00599C; color: #fff; border: 1px solid rgba(0, 89, 156, 0.3); }
+.tag-lang[data-filter-value="C#"] { background: #68217A; color: #fff; border: 1px solid rgba(104, 33, 122, 0.3); }
+.tag-lang[data-filter-value="Java"] { background: #ED8B00; color: #fff; border: 1px solid rgba(237, 139, 0, 0.3); }
+.tag-lang[data-filter-value="Golang"] { background: #00ADD8; color: #fff; border: 1px solid rgba(0, 173, 216, 0.3); }
+.tag-lang[data-filter-value="Haskell"] { background: #5D4F85; color: #fff; border: 1px solid rgba(93, 79, 133, 0.3); }
+.tag-lang[data-filter-value="Scala"] { background: #DC322F; color: #fff; border: 1px solid rgba(220, 50, 47, 0.3); }
+.tag-lang[data-filter-value="Ruby"] { background: #CC342D; color: #fff; border: 1px solid rgba(204, 52, 45, 0.3); }
+.tag-lang[data-filter-value="Matlab"] { background: #E16737; color: #fff; border: 1px solid rgba(225, 103, 55, 0.3); }
+.tag-lang[data-filter-value="Elixir/Erlang"] { background: #4B275F; color: #fff; border: 1px solid rgba(75, 39, 95, 0.3); }
+.tag-lang[data-filter-value="PHP"] { background: #777BB4; color: #fff; border: 1px solid rgba(119, 123, 180, 0.3); }
+
 /* ===== Results ===== */
 .no-results {
   text-align: center;