feat: make smolnet usable by a site that is not randogoth.com

Three changes, each found by pointing it at zonetoast, which files by tag
rather than category and writes its links by hand.

A single-bucket taxonomy is dropped. Pelican gives every uncategorised article
its DEFAULT_CATEGORY, so a tag-filed site still has one category holding
everything, and offering "misc, 14" as the only way in is worse than offering
nothing at all. Below SMOLNET_MIN_SECTIONS the whole section index goes.
randogoth.com still gets its six areas.

Links written against the HTML build are rewritten. {filename} is the portable
form, but content predating that knowledge hardcodes the output URL instead,
and zonetoast is full of ](/go-west.html). A capsule has no .html and the
daemon resolves a name carrying an extension literally, so all seventeen of
them 404'd. They now map onto the flat capsule slug, /pages/glossary.html
included, and a target matching no document is reported rather than silently
rewritten into a second broken link.

The line under an article title is a setting. Date and category is the right
default, but a site whose category is always `misc` has something better to
say: zonetoast carries `era`, which is what it is actually organised around,
so its articles read "17 May 2026 · 1996".

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

plugins/smolnet.py

@@ -17,7 +17,9 @@ setting, and every setting has a default, so a site can switch it on with just
     SMOLNET_OUTPUT        'smolnet'   directory under OUTPUT_PATH
     SMOLNET_SECTION_DIR   'section'   subdirectory holding one index per category
     SMOLNET_LATEST        15          entries on the front page; 0 drops the section
+    SMOLNET_META   [date, category]   fields for the line under an article title
     SMOLNET_SECTION_ORDER {}          category name -> sort key, else alphabetical
+    SMOLNET_MIN_SECTIONS  2           below this, the section index is dropped
     SMOLNET_LABELS        {}          override any heading, see LABELS
     SMOLNET_ASSETS        None        directories to copy; defaults to STATIC_PATHS
     SMOLNET_SIDECAR       '.itsybitsy.toml'
@@ -67,6 +69,13 @@ META_CONT = re.compile(r"^\s+\S")
 # Pelican's internal link syntax. Left alone these reach the capsule verbatim.
 INTERNAL = re.compile(r"\{(filename|static|attach)\}([^)\s]+)")
 
+# Links written against the HTML build, e.g. ](/go-west.html). Pelican's
+# {filename} form is the portable one, but plenty of content predates knowing
+# that and hardcodes the output URL instead. A capsule has no .html, and the
+# daemon resolves a name carrying an extension literally, so these 404 unless
+# they are rewritten.
+HARDCODED = re.compile(r"\]\(\s*(/[^)\s]*?\.html)([^)]*)\)")
+
 SUMMARY_MARKER = "<!-- PELICAN_END_SUMMARY -->"
 
 # Markdown image syntax, for dropping the ones whose host is gone. Matched on
@@ -137,6 +146,26 @@ def rewrite_internal(text, by_source, warn):
     return INTERNAL.sub(sub, text)
 
 
+def rewrite_html_links(text, slugs, warn):
+    """Point links written against the HTML build at the capsule instead.
+
+    `/pages/glossary.html` and `/go-west.html` both become `/<slug>`, since the
+    capsule is flat. A target whose slug is not among the documents built is
+    reported and left alone rather than silently rewritten into a second broken
+    link.
+    """
+
+    def sub(match):
+        target, rest = match.group(1), match.group(2)
+        slug = os.path.basename(target)[: -len(".html")]
+        if slug in slugs:
+            return "](/%s%s)" % (slug, rest)
+        warn("smolnet: link to %s matches no document", target)
+        return match.group(0)
+
+    return HARDCODED.sub(sub, text)
+
+
 def reveal_rot13(text, attr):
     """Replace a block of HTML carrying a rot13 address with the address itself.
 
@@ -237,8 +266,10 @@ class CapsuleGenerator(Generator):
         # Map source basename -> slug, so {filename} can be resolved. Built from
         # everything published, pages included, since an article may link one.
         by_source = {}
+        slugs = set()
         for doc in articles + pages:
             by_source[os.path.basename(doc.source_path)] = doc.slug
+            slugs.add(doc.slug)
 
         os.makedirs(out, exist_ok=True)
         root_titles = {}
@@ -247,6 +278,7 @@ class CapsuleGenerator(Generator):
             body = strip_metadata(self._read(doc))
             body = body.replace(SUMMARY_MARKER, "")
             body = rewrite_internal(body, by_source, self._warn)
+            body = rewrite_html_links(body, slugs, self._warn)
             body = reveal_rot13(body, rot_attr)
             body = drop_dead_images(body, dead_hosts)
             # Blank lines, not newlines: a heading and the line under it are
@@ -261,12 +293,21 @@ class CapsuleGenerator(Generator):
                 fh.write(text)
             root_titles[name] = doc.title
 
+        # Which metadata goes under the title. Default is date and category,
+        # but a site that files by tag has no useful category and may well have
+        # a field that means more: zonetoast carries `era`, which is the point
+        # of the site in a way that Pelican's default `misc` is not.
+        meta_fields = s.get("SMOLNET_META", ["date", "category"])
         for article in articles:
             bits = []
-            if getattr(article, "date", None):
+            for field in meta_fields:
-                bits.append(article.date.strftime("%d %b %Y"))
+                value = getattr(article, field, None)
-            if getattr(article, "category", None):
+                if not value:
-                bits.append(str(article.category))
+                    continue
+                if field == "date":
+                    bits.append(value.strftime("%d %b %Y"))
+                else:
+                    bits.append(str(value))
             emit(article, " · ".join(bits))
         for page in pages:
             emit(page, "")
@@ -276,6 +317,12 @@ class CapsuleGenerator(Generator):
             self.context.get("categories", []),
             key=lambda pair: (order.get(str(pair[0]), 99), str(pair[0])),
         )
+        # A site that files by tag rather than category still has one category,
+        # Pelican's DEFAULT_CATEGORY, holding everything. Offering "misc, 14" as
+        # the only way in is worse than offering nothing, so one bucket is not a
+        # taxonomy and the whole section index goes.
+        if len(sections) < s.get("SMOLNET_MIN_SECTIONS", 2):
+            sections = []
         if sections:
             os.makedirs(os.path.join(out, section_dir), exist_ok=True)
             section_titles = {}