Merge branch 'index-author'

Every list of articles now reads "Author · Feed · Publication · N min":
the signed-in issue page, the public issue page, the RSS feed and the
EPUB's In This Issue page. `author_label` drops an author that is empty
or only repeats the feed's title, as a dozen personal blogs do. Article
pages keep their own byline.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VXYGBPoHZSDSfE5WcJ9bvj

Cargo.lock

@@ -905,6 +905,7 @@ dependencies = [
  "lettre",
  "libc",
  "password-auth",
+ "percent-encoding",
  "rand 0.10.2",
  "reqwest",
  "resvg",

Cargo.toml

@@ -23,6 +23,7 @@ jiff = { version = "0.2.35", features = ["serde"] }
 lettre = { version = "0.11", default-features = false, features = ["builder", "smtp-transport", "tokio1", "tokio1-rustls-tls", "hostname"] }
 libc = "0.2.189"
 password-auth = "1.0.0"
+percent-encoding = "2.3.2"
 rand = "0.10.2"
 reqwest = { version = "0.13.4", default-features = false, features = [
     "rustls",

src/dedupe.rs

@@ -6,6 +6,7 @@
 use std::collections::HashMap;
 
 use jiff::Timestamp;
+use percent_encoding::percent_decode_str;
 use url::Url;
 
 use crate::types::{Article, Entry, ExtractMethod, SourceKind, SourceRef};
@@ -109,6 +110,16 @@ fn is_tracking_param(key: &str) -> bool {
 /// The real destination behind a known redirector, if any (§3.2).
 fn redirect_target(url: &Url) -> Option<String> {
     let host = url.host_str()?.to_ascii_lowercase();
+    if matches!(host.as_str(), "scour.ing" | "www.scour.ing")
+        && let Some(encoded) = url.path().strip_prefix("/r/rss/")
+    {
+        let target = percent_decode_str(encoded).decode_utf8().ok()?.into_owned();
+        let target_url = Url::parse(&target).ok()?;
+        if matches!(target_url.scheme(), "http" | "https") && target_url.host_str().is_some() {
+            return Some(target);
+        }
+        return None;
+    }
     let is_google_news = host == "news.google.com" || host.ends_with(".news.google.com");
     let is_google_redirect = host == "news.url.google.com"
         || ((host == "www.google.com" || host == "google.com") && url.path() == "/url");
@@ -490,6 +501,21 @@ mod tests {
                 "https://www.google.com/url?q=https://example.com/real&sa=D",
                 Some("https://example.com/real"),
             ),
+            // Scour RSS redirectors encode the real URL in the path
+            (
+                "https://scour.ing/r/rss/https%3A%2F%2Frmzlb.github.io%2Fnotifyd%2Farticles%2Fpostgres-queue-what-skip-locked-does-not-give-you.html",
+                Some(
+                    "https://rmzlb.github.io/notifyd/articles/postgres-queue-what-skip-locked-does-not-give-you.html",
+                ),
+            ),
+            (
+                "https://www.scour.ing/r/rss/https%3A%2F%2Fexample.com%2Fpost%3Fid%3D7%26utm_source%3Dscour%26utm_medium%3Drss",
+                Some("https://example.com/post?id=7"),
+            ),
+            (
+                "https://scour.ing/@tyler/interests/Kernel%20Development",
+                Some("https://scour.ing/@tyler/interests/Kernel%20Development"),
+            ),
             // non-http schemes and junk
             ("mailto:tyler@hallada.net", None),
             ("ftp://example.com/file", None),

src/epub/chapters.rs

@@ -370,6 +370,14 @@ fn source_line(article: &Article) -> String {
     }
 }
 
+/// The index's meta lead: the author, when known, ahead of [`source_line`].
+fn index_source_line(article: &Article) -> String {
+    match article.author_label() {
+        Some(author) => format!("{author} · {}", source_line(article)),
+        None => source_line(article),
+    }
+}
+
 /// "In This Issue": per section, each article's title, source, reading time and
 /// summary, linked to its chapter (§3.10).
 pub fn render_in_this_issue(issue: &Issue) -> Result<Chapter, EpubError> {
@@ -382,7 +390,7 @@ pub fn render_in_this_issue(issue: &Issue) -> Result<Chapter, EpubError> {
             .map(|pick| IndexEntry {
                 href: article_href(pick),
                 title: pick.article.title.clone(),
-                source: source_line(&pick.article),
+                source: index_source_line(&pick.article),
                 reading_minutes: pick.article.reading_minutes(),
                 summary: summary_for(issue, pick).unwrap_or_default().to_string(),
                 why: pick.why.clone(),
@@ -891,14 +899,16 @@ mod tests {
         let mut issue = issue();
         issue.lineup.picks[0].article.publication = Some("Example Journal".into());
         issue.lineup.picks[1].article.publication = Some("Example Feed".into());
+        issue.lineup.picks[1].article.author = Some("example feed".into());
 
         let index = render_in_this_issue(&issue).unwrap();
         assert!(
             index
                 .xhtml
-                .contains("Example Feed · Example Journal &#183; 6 min read")
+                .contains("A. Writer · Example Feed · Example Journal &#183; 6 min read")
         );
         assert!(!index.xhtml.contains("Example Feed · Example Feed"));
+        assert!(!index.xhtml.contains("example feed · Example Feed"));
 
         let article = render_article(
             &issue,

src/types.rs

@@ -160,13 +160,27 @@ impl Article {
         let publication = self
             .publication
             .clone()
-            .or_else(|| domain(&self.canonical_url))?;
+            // Covers rows stored before Scour wrappers were unwrapped.
+            .or_else(|| {
+                domain(
+                    crate::dedupe::canonical_url(&self.canonical_url)
+                        .as_deref()
+                        .unwrap_or(&self.canonical_url),
+                )
+            })?;
         (!publication
             .trim()
             .eq_ignore_ascii_case(self.feed_title.trim()))
         .then_some(publication)
     }
 
+    /// The trimmed author, unless empty or identical to the feed name.
+    pub fn author_label(&self) -> Option<String> {
+        let author = self.author.as_deref()?.trim();
+        (!author.is_empty() && !author.eq_ignore_ascii_case(self.feed_title.trim()))
+            .then(|| author.to_string())
+    }
+
     /// Stable EPUB chapter id used by TOC and rating links (implementation notes §12).
     pub fn chapter_id(&self) -> String {
         format!("art-{}", self.best_entry_id)
@@ -914,6 +928,14 @@ mod tests {
         assert_eq!(article.publication_label().as_deref(), Some("example.com"));
     }
 
+    #[test]
+    fn publication_label_unwraps_stored_scour_urls() {
+        let mut article = publication_article();
+        article.canonical_url =
+            "https://scour.ing/r/rss/https%3A%2F%2Fwww.example.com%2Fpost".into();
+        assert_eq!(article.publication_label().as_deref(), Some("example.com"));
+    }
+
     #[test]
     fn publication_label_omits_a_publication_matching_the_feed() {
         let mut article = publication_article();
@@ -929,6 +951,19 @@ mod tests {
         assert_eq!(article.publication_label(), None);
     }
 
+    #[test]
+    fn author_label_trims_and_omits_empty_or_matching_authors() {
+        let mut article = publication_article();
+        article.author = Some("  Jane Doe  ".into());
+        assert_eq!(article.author_label().as_deref(), Some("Jane Doe"));
+
+        article.author = Some("  ".into());
+        assert_eq!(article.author_label(), None);
+
+        article.author = Some("  a FEED ".into());
+        assert_eq!(article.author_label(), None);
+    }
+
     #[test]
     fn composite_social_score_matches_spec_formula() {
         let refs = vec![

src/web/issue.rs

@@ -876,6 +876,7 @@ struct FullEntry {
     title: String,
     href: String,
     dashboard_href: String,
+    author: Option<String>,
     source: Source,
     reading_minutes: i64,
     is_lead: bool,
@@ -1021,6 +1022,7 @@ pub async fn render_full(
                     title: pick.article.title.clone(),
                     href: article_href(date, pick.article.id),
                     dashboard_href: format!("/dashboard/articles/{}", pick.article.id),
+                    author: pick.article.author_label(),
                     source: Source::new(&pick.article, &config, is_admin),
                     reading_minutes: pick.article.reading_minutes(),
                     is_lead: pick.is_lead,
@@ -1946,6 +1948,13 @@ mod tests {
     #[tokio::test]
     async fn signed_in_full_issue_article_world_and_behind_render_private_content() {
         let (_dir, db, source) = seeded_issue(true).await;
+        let matching_author = &source.lineup.picks[1].article;
+        sqlx::query("UPDATE articles SET author = ? WHERE id = ?")
+            .bind(format!(" {} ", matching_author.feed_title.to_lowercase()))
+            .bind(matching_author.id)
+            .execute(db.pool())
+            .await
+            .unwrap();
         crate::web::users::add(&db, "reader", "correct horse battery", false)
             .await
             .unwrap();
@@ -1993,6 +2002,8 @@ mod tests {
         assert!(issue.contains("A short abstract for the second piece"));
         assert!(issue.contains("Why it"));
         assert!(issue.contains("Interests: Filesystems, Rust"));
+        assert!(issue.contains("A. Writer · Example Feed"));
+        assert!(!issue.contains("example feed · Example Feed"));
         assert!(issue.contains("World Briefing"));
         assert!(issue.contains("Behind the paper"));
         assert!(!issue.contains("Was this a good pick?"));

src/web/public.rs

@@ -114,7 +114,7 @@ impl From<&Issue> for PublicIssue {
                             PublicEntry {
                                 title: article.title.clone(),
                                 url: article.canonical_url.clone(),
-                                author: article.author.clone(),
+                                author: article.author_label(),
                                 source: article.feed_title.clone(),
                                 publication: article.publication_label(),
                                 reading_minutes: article.reading_minutes(),

src/web/templates/feed_entry.html

@@ -1 +1 @@
-{% for section in issue.sections %}<h2>{{ section.name }}</h2><ul>{% for entry in section.entries %}<li><a href="{{ entry.url }}">{{ entry.title }}</a> — {{ entry.source }}{% match entry.publication %}{% when Some with (publication) %} · {{ publication }}{% when None %}{% endmatch %}{% match entry.summary %}{% when Some with (summary) %}<p class="summary">{{ summary }}</p>{% when None %}{% endmatch %}{% match entry.why %}{% when Some with (why) %}<p class="why"><em>Why it's here: {{ why }}</em></p>{% when None %}{% endmatch %}{% if !entry.comment_links.is_empty() %} · {% for link in entry.comment_links %}<a href="{{ link.url }}">{{ link.label }}</a>{% endfor %}{% endif %}</li>{% endfor %}</ul>{% endfor %}
+{% for section in issue.sections %}<h2>{{ section.name }}</h2><ul>{% for entry in section.entries %}<li><a href="{{ entry.url }}">{{ entry.title }}</a> — {% match entry.author %}{% when Some with (author) %}{{ author }} · {% when None %}{% endmatch %}{{ entry.source }}{% match entry.publication %}{% when Some with (publication) %} · {{ publication }}{% when None %}{% endmatch %}{% match entry.summary %}{% when Some with (summary) %}<p class="summary">{{ summary }}</p>{% when None %}{% endmatch %}{% match entry.why %}{% when Some with (why) %}<p class="why"><em>Why it's here: {{ why }}</em></p>{% when None %}{% endmatch %}{% if !entry.comment_links.is_empty() %} · {% for link in entry.comment_links %}<a href="{{ link.url }}">{{ link.label }}</a>{% endfor %}{% endif %}</li>{% endfor %}</ul>{% endfor %}

src/web/templates/issue_full.html

@@ -5,7 +5,7 @@
   <section aria-labelledby="brief-heading" data-toc-entry="/issues/{{ date }}"><h1 id="brief-heading" class="reader-section-heading">The Brief</h1><div class="editorial prose-body mt-5 [&>p:first-child]:first-letter:float-left [&>p:first-child]:first-letter:mr-2 [&>p:first-child]:first-letter:mt-1 [&>p:first-child]:first-letter:font-serif [&>p:first-child]:first-letter:text-[4.6rem] [&>p:first-child]:first-letter:font-semibold [&>p:first-child]:first-letter:leading-[0.72]">{{ front_page_html|safe }}</div></section>
   {% if (page.is_admin() && read_href.is_some()) || downloads.is_some() %}<div class="my-8 flex flex-wrap gap-2 border-y border-rule py-4">{% if page.is_admin() %}{% match read_href %}{% when Some with (href) %}<a class="btn" href="{{ href }}" target="_blank" rel="noopener">Read in BookOrbit</a>{% when None %}{% endmatch %}{% endif %}{% match downloads %}{% when Some with (downloads) %}{% if downloads.others.is_empty() %}<a class="btn" href="{{ downloads.primary.href }}">Download {{ downloads.primary.label }}</a>{% else %}<div class="relative inline-flex"><a class="btn rounded-r-none" href="{{ downloads.primary.href }}">Download {{ downloads.primary.label }}</a><details class="-ml-px"><summary class="btn list-none rounded-l-none px-2 [&::-webkit-details-marker]:hidden" aria-label="Choose download format"><span aria-hidden="true">▾</span></summary><div class="absolute left-0 top-full z-20 mt-1 min-w-52 border border-rule bg-paper p-1 shadow-[0_18px_32px_-26px_rgb(0_0_0_/_0.6)]"><a class="btn group w-full justify-between border-0" href="{{ downloads.primary.href }}"><span>{% if downloads.primary.label == "EPUB" %}Standard {% endif %}{{ downloads.primary.label }}</span><span class="ml-4 text-muted group-hover:text-paper">{{ downloads.primary.size }}</span></a>{% for download in downloads.others %}<a class="btn group w-full justify-between border-0" href="{{ download.href }}"><span>{{ download.label }}</span><span class="ml-4 text-muted group-hover:text-paper">{{ download.size }}</span></a>{% endfor %}</div></details></div>{% endif %}{% when None %}{% endmatch %}</div>{% endif %}
   <section class="mt-12" aria-labelledby="index-heading"><h2 id="index-heading" class="text-center text-3xl font-semibold leading-[1.1] tracking-[-0.01em]">In This Issue</h2>
-    {% for section in sections %}<section class="mt-14"><h3 class="reader-section-heading">{{ section.name }}</h3><ul class="m-0 list-none p-0">{% for entry in section.entries %}<li class="border-b border-rule py-6" data-toc-entry="{{ entry.href }}"><h4 class="font-serif font-semibold leading-[1.1] tracking-[-0.01em] {% if entry.is_lead %}text-3xl{% else %}text-2xl{% endif %}"><a class="text-ink no-underline hover:text-accent" href="{{ entry.href }}">{{ entry.title }}</a></h4><p class="mt-2 font-sans text-sm text-muted">{% let source = entry.source %}{% include "_source.html" %} · {{ entry.reading_minutes }} min read{% if page.is_admin() %} · <a class="text-muted hover:text-accent" href="{{ entry.dashboard_href }}">dashboard</a>{% endif %}</p>{% if !entry.summary.is_empty() %}<p class="index-summary mt-4">{{ entry.summary }}</p>{% endif %}{% match entry.why %}{% when Some with (why) %}<p class="mt-4 border-l-2 border-accent pl-3 italic text-ink-2">Why it's here: {{ why }}</p>{% when None %}{% endmatch %}{% match entry.understanding %}{% when Some with (line) %}<p class="mt-3 font-sans text-sm text-muted">{{ line }}</p>{% when None %}{% endmatch %}{% match entry.rating %}{% when Some with (widget) %}{% include "_rating_widget.html" %}{% when None %}{% endmatch %}</li>{% endfor %}</ul></section>{% endfor %}
+    {% for section in sections %}<section class="mt-14"><h3 class="reader-section-heading">{{ section.name }}</h3><ul class="m-0 list-none p-0">{% for entry in section.entries %}<li class="border-b border-rule py-6" data-toc-entry="{{ entry.href }}"><h4 class="font-serif font-semibold leading-[1.1] tracking-[-0.01em] {% if entry.is_lead %}text-3xl{% else %}text-2xl{% endif %}"><a class="text-ink no-underline hover:text-accent" href="{{ entry.href }}">{{ entry.title }}</a></h4><p class="mt-2 font-sans text-sm text-muted">{% match entry.author %}{% when Some with (author) %}{{ author }} · {% when None %}{% endmatch %}{% let source = entry.source %}{% include "_source.html" %} · {{ entry.reading_minutes }} min read{% if page.is_admin() %} · <a class="text-muted hover:text-accent" href="{{ entry.dashboard_href }}">dashboard</a>{% endif %}</p>{% if !entry.summary.is_empty() %}<p class="index-summary mt-4">{{ entry.summary }}</p>{% endif %}{% match entry.why %}{% when Some with (why) %}<p class="mt-4 border-l-2 border-accent pl-3 italic text-ink-2">Why it's here: {{ why }}</p>{% when None %}{% endmatch %}{% match entry.understanding %}{% when Some with (line) %}<p class="mt-3 font-sans text-sm text-muted">{{ line }}</p>{% when None %}{% endmatch %}{% match entry.rating %}{% when Some with (widget) %}{% include "_rating_widget.html" %}{% when None %}{% endmatch %}</li>{% endfor %}</ul></section>{% endfor %}
   </section>
   {% if has_world || has_behind %}<nav class="my-12 flex flex-wrap items-center justify-center gap-x-3 gap-y-1 border-y border-rule py-4 text-center font-sans text-sm uppercase tracking-[0.08em]" aria-label="Issue chapters">{% if has_world %}<a class="text-ink no-underline hover:text-accent" href="/issues/{{ date }}/world">World Briefing</a>{% endif %}{% if has_world && has_behind %}<span class="text-muted" aria-hidden="true">·</span>{% endif %}{% if has_behind %}<a class="text-ink no-underline hover:text-accent" href="/issues/{{ date }}/behind">Behind the paper</a>{% endif %}</nav>{% endif %}
   <footer id="colophon" class="mt-14 scroll-mt-6 font-sans text-sm leading-relaxed" data-toc-entry="/issues/{{ date }}#colophon"><h2 class="reader-section-heading">Colophon</h2><p class="my-4 text-ink-2"><em>The Daily EPUB</em> is assembled every morning from a personal feed reader.</p><dl class="kv border-y border-rule py-4 text-xs sm:text-sm"><dt>Generated</dt><dd>{{ colophon.generated_at }}</dd><dt>Bulk model</dt><dd>{{ colophon.bulk_model }}</dd><dt>Editor model</dt><dd>{{ colophon.editor_model }}</dd><dt>Summaries model</dt><dd>{{ colophon.summaries_model }}</dd><dt>Entries considered</dt><dd>{% match colophon.entries_fetched %}{% when Some with (entries) %}{{ entries }}{% match colophon.feeds_seen %}{% when Some with (feeds) %} from {{ feeds }} feeds{% when None %}{% endmatch %}{% when None %}n/a{% endmatch %}</dd><dt>Candidates scored</dt><dd>{% match colophon.candidates %}{% when Some with (candidates) %}{{ candidates }}{% when None %}n/a{% endmatch %}</dd><dt>Articles selected</dt><dd>{{ colophon.article_count }} across {{ colophon.section_count }} sections</dd><dt>Words</dt><dd>{{ colophon.total_words }} · ~{{ colophon.reading_minutes }} min read</dd>{% for cost in colophon.provider_costs %}<dt>{{ cost.provider }} cost</dt><dd>{{ cost.cost }}</dd>{% endfor %}<dt>Total token cost</dt><dd>{% match colophon.cost_usd %}{% when Some with (cost) %}{{ cost }}{% when None %}n/a{% endmatch %}</dd><dt>Generator</dt><dd>{{ colophon.generator_version }}</dd></dl></footer>