gatewayd: links: url_len and closes as their comments say

M5b review, findings 1 and 2. url_len ended a clean reply's URL at any
`<` outside parentheses, not at a `<` before white space, a bracket,
`<`, `>` or the end; closes used a count of characters as a byte
offset, so a closer indented with a no-break space did not close its
fence. Both bodies, and fence_end's (an index replaced by `get`), are
the reference's again. tests/links_review.rs pins both cases with the
reference's output.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

crates/gatewayd/src/links/inline.rs

@@ -439,41 +439,28 @@ fn scheme_less(rest: &str) -> bool {
 /// out: it may start an autolink); unless `whole`, up to any `<`, `>`, `|` or backtick too. Then
 /// less the characters of `TRAILING` at its end. `whole` is the most marked may read as the URL.
 fn url_len(rest: &str, whole: bool) -> usize {
-    let mut depth = 0;
+    let mut depth = 0usize;
-    let mut gt_seen = false;
     let mut end = rest.len();
     for (i, c) in rest.char_indices() {
-        if c.is_whitespace() {
+        let next = rest.get(i + 1..).and_then(|after| after.chars().next());
+        let open = c == '<' && next.is_none_or(|n| n.is_whitespace() || "()<>".contains(n));
+        let part = if whole {
+            !open
+        } else {
+            !matches!(c, '<' | '>' | '|' | '`')
+        };
+        if c.is_whitespace() || !part || (c == ')' && depth == 0) {
             end = i;
             break;
         }
-        if !whole && (c == '<' || c == '>' || c == '|' || c == '`') {
+        if c == '(' {
-            end = i;
+            depth += 1;
-            break;
+        } else if c == ')' {
-        }
+            depth -= 1;
-        match c {
-            '(' => depth += 1,
-            ')' if depth == 0 => {
-                end = i;
-                break;
-            }
-            ')' => depth -= 1,
-            '<' if depth == 0 && !gt_seen => {
-                end = i;
-                break;
-            }
-            '>' => gt_seen = true,
-            _ => {}
         }
     }
-    while let Some(last) = rest
+    rest.get(..end)
-        .get(..end)
+        .unwrap_or_default()
-        .and_then(|prefix| prefix.chars().next_back())
+        .trim_end_matches(TRAILING)
-    {
+        .len()
-        if !TRAILING.contains(&last) {
-            break;
-        }
-        end -= last.len_utf8();
-    }
-    end
 }

crates/gatewayd/src/links/mod.rs

@@ -217,18 +217,15 @@ fn nested_start(line: &str) -> bool {
 /// `None` (it leaves a list item in CommonMark, and the block with it). No closer: `None`, since
 /// marked reads an unclosed fence as code only at times.
 fn fence_end(lines: &[&str], at: usize) -> Option<usize> {
-    let (indent, run) = opener(lines[at])?;
+    let (indent, run) = opener(lines.get(at)?)?;
-    let mut i = at + 1;
+    for (i, line) in lines.iter().enumerate().skip(at + 1) {
-    while let Some(line) = lines.get(i) {
         if closes(line, run) {
             return Some(i);
         }
-        if !content(line).is_empty()
+        let text = content(line);
-            && content(line).chars().take_while(|&c| c == ' ').count() < indent
+        if !text.is_empty() && text.len() - text.trim_start_matches(' ').len() < indent {
-        {
             return None;
         }
-        i += 1;
     }
     None
 }
@@ -263,22 +260,14 @@ fn opener(line: &str) -> Option<(usize, &str)> {
 /// come only backticks and `~`, then only spaces, tabs or no-break spaces.
 fn closes(line: &str, run: &str) -> bool {
     let text = content(line);
-    let leading = text
+    let rest = text.trim_start_matches([' ', '\u{a0}']);
-        .chars()
+    if text.chars().count() - rest.chars().count() > 3 {
-        .take_while(|&c| c == ' ' || c == '\u{a0}')
-        .count();
-    if leading > 3 {
         return false;
     }
-    let Some(after) = text.get(leading..) else {
+    let Some(tail) = rest.strip_prefix(run) else {
         return false;
     };
-    if !after.starts_with(run) {
+    tail.trim_end_matches([' ', '\t', '\u{a0}'])
-        return false;
-    }
-    let rest = after.get(run.len()..).unwrap_or("");
-    let after_ticks = rest.trim_start_matches(['`', '~']);
-    after_ticks
         .chars()
-        .all(|c| c == ' ' || c == '\t' || c == '\u{a0}')
+        .all(|c| c == '`' || c == '~')
 }

crates/gatewayd/tests/links_review.rs

@@ -0,0 +1,29 @@
+//! Two cases the M5b review found where `links::disarm` did not follow the comments of its
+//! helpers: a `<` inside a clean reply's URL, and a fence closed by a line indented with a no-break
+//! space (M5b review, implementer log). Each expected text is the reference's.
+
+use gatewayd::links::disarm;
+
+#[test]
+fn a_url_runs_on_past_a_less_than_sign_that_starts_no_autolink() {
+    // `url_len`: only a `<` before white space, a bracket, `<`, `>` or the end stops the URL of a
+    // clean reply, so the image after it is wrapped with the URL, whole.
+    let text = "see https://a.example/x<![i](https://e.example/d) now";
+    assert_eq!(
+        disarm(text, false).text,
+        "see `https://a.example/x<![i](https://e.example/d)` now"
+    );
+    assert_eq!(
+        disarm(text, true).text,
+        "see `https://a.example/x`< `![i](https://e.example/d)` now"
+    );
+}
+
+#[test]
+fn a_closer_indented_with_a_no_break_space_closes_the_fence() {
+    // `closes`: up to three spaces or no-break spaces before the closing run, counted in
+    // characters; the no-break space is two bytes.
+    let text = "```\n![i](https://e.example/d)\n\u{a0}```\nafter";
+    assert_eq!(disarm(text, false).text, text);
+    assert_eq!(disarm(text, true).text, text);
+}