documents: shortcodes read per DOM text node as GitHub reads them; HTML5's p closers end a p; a TOC press follows editor anchors

- The first `:name:`-shaped run in a text node decides for the whole node:
  blank text or a space before it turns every shortcode, else none. Filtered
  tags are text and do not split the node. Probed on GitHub's markdown API.
- `fieldset`, `menu` and the rest of HTML5's list end an open `p`.
- `CodeEditor` carries owner anchors through each edit; the document anchors
  every heading it reads, and a TOC press goes where its anchor went.

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

src/documents/document/edit.rs

@@ -12,27 +12,8 @@ use crate::{
     forms::{InputEvent, TextInput},
 };
 
-/// The one edit from `old` to `new`, by shared ends.
-pub(super) fn between(old: &str, new: &str) -> Option<(Range<usize>, usize)> {
-    let head: usize = old
-        .chars()
-        .zip(new.chars())
-        .take_while(|(a, b)| a == b)
-        .map(|(ch, _)| ch.len_utf8())
-        .sum();
-    let room = old.len().min(new.len()) - head;
-    let mut tail = 0;
-    for (a, b) in old.chars().rev().zip(new.chars().rev()) {
-        if a != b || tail + a.len_utf8() > room {
-            break;
-        }
-        tail += a.len_utf8();
-    }
-    (old != new).then(|| (head..old.len() - tail, new.len() - tail - head))
-}
-
 /// Where byte `at` lies after `edit`, if it survives.
-pub(super) fn moved(at: usize, edit: &Option<(Range<usize>, usize)>) -> Option<usize> {
+fn moved(at: usize, edit: &Option<(Range<usize>, usize)>) -> Option<usize> {
     match edit {
         None => Some(at),
         Some((replaced, _)) if at < replaced.start => Some(at),
@@ -200,15 +181,4 @@ mod tests {
         assert_eq!(super::moved(3, &edit), None, "inside is gone");
         assert_eq!(super::moved(7, &None), Some(7));
     }
-
-    #[test]
-    fn two_texts_part_at_their_shared_ends() {
-        assert_eq!(super::between("abc", "abc"), None);
-        assert_eq!(super::between("before\nB", "## B\nB"), Some((0..6, 4)));
-        assert_eq!(super::between("ab", "aXb"), Some((1..1, 1)));
-        assert_eq!(super::between("aa", "aaa"), Some((2..2, 1)));
-        assert_eq!(super::between("aXYb", "ab"), Some((1..3, 0)));
-        assert_eq!(super::between("é😄", "é"), Some((2..6, 0)));
-        assert_eq!(super::between("x😄", "y😄"), Some((0..1, 1)));
-    }
 }

src/documents/document/mod.rs

@@ -316,6 +316,9 @@ impl MarkdownDocument {
         let old = self.parsed.blocks.len();
         self.list
             .splice(head..old - tail, read.blocks.len() - head - tail);
+        let headings: Vec<usize> = read.headings.iter().map(|heading| heading.at).collect();
+        self.editor
+            .update(cx, |editor, _| editor.set_anchors(headings));
         self.parsed = Arc::new(read);
         cx.emit(DocumentEvent::Parsed);
         cx.notify();

src/documents/document/place.rs

@@ -1,11 +1,6 @@
-use std::sync::Arc;
-
 use gpui::{App, Context, Focusable as _, ListOffset, ScrollStrategy, Window, px};
 
-use super::{
-    MarkdownDocument, Placement,
-    edit::{between, moved},
-};
+use super::{MarkdownDocument, Placement};
 use crate::documents::{MarkdownMode, modes::joint};
 
 /// Line and column, from zero, of byte `at` in `text`.
@@ -194,24 +189,31 @@ impl MarkdownDocument {
             .saturating_sub(1)
     }
 
-    /// Reveals the pressed heading, moved by the edit since.
+    /// Reveals the pressed heading where the edits since carried it.
     pub(super) fn reveal_at(&mut self, at: usize, window: &mut Window, cx: &mut Context<Self>) {
-        if !self.parsed.headings.iter().any(|heading| heading.at == at) {
+        let headings = &self.parsed.headings;
+        let Some(index) = headings.iter().position(|heading| heading.at == at) else {
             return log::warn!("markdown document: a heading read away");
-        }
-        // The heading list drew from this read.
-        let drawn = Arc::clone(&self.parsed);
-        if self.commit(cx).is_some() || !self.read_now(cx) {
+        };
+        self.commit(cx);
+        let anchors = self.editor.read(cx).anchors();
+        let Some(found) = *anchors.get(index).expect("an anchor per heading read") else {
+            return log::warn!("markdown document: the pressed heading changed as one wrote");
+        };
+        if !self.read_now(cx) {
             self.reparse(true, cx);
         }
         if !self.read_now(cx) {
             return log::warn!("markdown document: a heading pressed while the text is read again");
         }
-        let edit = between(&drawn.text, self.editor.read(cx).text());
-        let headings = &self.parsed.headings;
-        let Some(found) = moved(at, &edit).filter(|at| headings.iter().any(|h| h.at == *at)) else {
-            return log::warn!("markdown document: the pressed heading changed as one wrote");
-        };
+        if !self
+            .parsed
+            .headings
+            .iter()
+            .any(|heading| heading.at == found)
+        {
+            return log::warn!("markdown document: the pressed heading reads as no heading now");
+        }
         let line = self.editor.read(cx).buffer.line_of(found);
         self.reveal(line, window, cx);
     }

src/documents/document/tests/toc.rs

@@ -132,3 +132,59 @@ fn a_press_while_the_text_waits_to_be_read_finds_the_heading(cx: &mut TestAppCon
         (26, 0)
     );
 }
+
+/// Makes `edits` while the text waits, caret at the top.
+fn edit_waiting<'a>(
+    text: &str,
+    edits: Vec<(std::ops::Range<usize>, String)>,
+    cx: &'a mut TestAppContext,
+) -> (Entity<MarkdownDocument>, &'a mut VisualTestContext) {
+    let (document, cx) = open(text, MarkdownMode::Split, cx);
+    document.update(cx, |document, cx| {
+        document
+            .editor
+            .update(cx, |editor, cx| editor.edit(edits, cx));
+        document.set_caret(0, 0, cx);
+    });
+    frames(cx);
+    assert!(!document.read_with(cx, |document, cx| document.read_now(cx)));
+    (document, cx)
+}
+
+fn caret(document: &Entity<MarkdownDocument>, cx: &mut VisualTestContext) -> (usize, usize) {
+    document.read_with(cx, |document, cx| document.caret(cx))
+}
+
+#[gpui::test]
+fn a_twin_written_right_at_the_heading_goes_before_it(cx: &mut TestAppContext) {
+    let edits = vec![(7..7, "## B\n\n".to_string())];
+    let (document, cx) = edit_waiting("[toc]\n\n## B\n\ntext\n", edits, cx);
+    press_entry(0, Modifiers::none(), cx);
+    assert_eq!(caret(&document, cx), (4, 0));
+}
+
+#[gpui::test]
+fn adjacent_twins_keep_who_was_deleted(cx: &mut TestAppContext) {
+    let twins = "[toc]\n\n## B\n\n## B\n\ntext\n";
+    let (document, cx) = edit_waiting(twins, vec![(7..13, String::new())], cx);
+    press_entry(0, Modifiers::none(), cx);
+    assert_eq!(
+        caret(&document, cx),
+        (0, 0),
+        "the deleted one moves nothing"
+    );
+    press_entry(1, Modifiers::none(), cx);
+    assert_eq!(caret(&document, cx), (2, 0), "the kept one moved up");
+}
+
+#[gpui::test]
+fn a_heading_between_two_edits_stays_found(cx: &mut TestAppContext) {
+    let text = "before\n\n[toc]\n\n# A\n\nafter\n";
+    let edits = vec![
+        (0..0, "start\n".to_string()),
+        (text.len()..text.len(), "end\n".to_string()),
+    ];
+    let (document, cx) = edit_waiting(text, edits, cx);
+    press_entry(0, Modifiers::none(), cx);
+    assert_eq!(caret(&document, cx), (5, 0));
+}

src/documents/tree/blocks.rs

@@ -99,6 +99,7 @@ impl Reader<'_> {
             rest = &rest[at..];
             if let Some(comment) = rest.strip_prefix("<!--") {
                 rest = comment.split_once("-->").map_or("", |(_, after)| after);
+                run.shortcodes.split();
                 continue;
             }
             let opens =
@@ -116,10 +117,7 @@ impl Reader<'_> {
             let (written, after) = rest.split_at(end);
             rest = after;
             match html::tag(written) {
-                Some(tag) if html::filtered(&tag.name) => {
-                    run.filter(&tag);
-                    run.spaced(&html::text(written));
-                }
+                Some(tag) if html::filtered(&tag.name) => run.words(written),
                 // A block closes what opened inside it.
                 Some(tag) if html::breaks(&tag.name) => {
                     run.line();
@@ -127,12 +125,18 @@ impl Reader<'_> {
                         true => run.end(&tag.name),
                         false => {
                             run.implied(&tag.name);
-                            if tag.name != "hr" {
-                                run.start(&tag.name, None, None);
+                            match tag.name == "hr" {
+                                true => run.shortcodes.split(),
+                                false => run.start(&tag.name, None, None),
                             }
                         }
                     }
                 }
+                // It ends a `p` but lays no block.
+                Some(tag) if !tag.closing && html::closes_p(&tag.name) => {
+                    run.implied(&tag.name);
+                    run.html(written);
+                }
                 // A line's end drops its space.
                 Some(tag) if tag.closing || tag.name == "br" => {
                     run.owed = run.owed.filter(|_| tag.name != "br");
@@ -142,7 +146,7 @@ impl Reader<'_> {
                     run.pay();
                     run.html(written);
                 }
-                None => {}
+                None => run.shortcodes.split(),
             }
         }
         run.words(rest);
@@ -153,11 +157,8 @@ impl Reader<'_> {
 impl Run {
     /// HTML text: references decoded, white space collapsed.
     fn words(&mut self, written: &str) {
-        let decoded = html::text(written);
-        match self.reads_emoji() {
-            true => self.spaced(&html::emoji(&decoded)),
-            false => self.spaced(&decoded),
-        }
+        let shown = self.shown(&html::text(written));
+        self.spaced(&shown);
     }
 
     /// Text with its white space collapsed.
@@ -215,8 +216,8 @@ impl Run {
         if let Some(item) = found {
             self.end(&item);
         }
-        // A table start closes it, so it is in scope.
-        if name != "tr" && self.count("p") > 0 {
+        if html::closes_p(name) && self.count("p") > 0 {
+            self.line();
             self.end("p");
         }
     }
@@ -417,18 +418,50 @@ mod tests {
     }
 
     #[test]
-    fn filtered_tags_keep_shortcodes_and_names_end_as_html5_ends_them() {
-        let block = html("<script title=\":smile:\">:smile:</script>").expect("text");
-        assert_eq!(block.text, "<script title=\":smile:\">:smile:</script>");
-        assert_eq!(html("<div>:smile:</div>").expect("text").text, "😄");
-        let attribute = html("a <script title=\":smile:\">x</script> c").expect("text");
-        assert_eq!(attribute.text, "a <script title=\":smile:\">x</script> c");
-        let body = html("a <script>:smile:</script> :smile:").expect("text");
-        assert_eq!(body.text, "a <script>:smile:</script> 😄");
+    fn filtered_tags_are_text_and_names_end_as_html5_ends_them() {
+        // GitHub's answers, `.work/R4.3-fix3/github-*.log`.
+        for (source, shown) in [
+            (
+                "<div><script>:smile:</script> :smile:</div>",
+                "<script>:smile:</script> :smile:",
+            ),
+            (
+                "<div><script><b>:smile:</b></script> :smile:</div>",
+                "<script>😄</script> 😄",
+            ),
+            (
+                "<div><script> :smile:</script> :smile:</div>",
+                "<script> 😄</script> 😄",
+            ),
+            (
+                "<div><script title=\" :smile:\"> x:smile:</div>",
+                "<script title=\" 😄\"> x😄",
+            ),
+            (
+                "<div><iframe title=\":smile:\"> :smile:</div>",
+                "<iframe title=\":smile:\"> :smile:",
+            ),
+            ("<div>\n:smile: x:smile:\n</div>", "😄 x😄"),
+            ("<div>\t:smile: x:smile:</div>", "😄 x😄"),
+            ("<div>a\n :smile: x:smile:</div>", "a 😄 x😄"),
+            ("<div>y\n:smile: x:smile:</div>", "y :smile: x:smile:"),
+            ("<div>:smile:</div>", "😄"),
+        ] {
+            assert_eq!(html(source).expect("text").text, shown, "{source:?}");
+        }
         let named = "<div>a<script:custom>x</script:custom>b<script!>y</script!>c</div>";
         assert_eq!(html(named).expect("text").text, "axbyc");
     }
 
+    #[test]
+    fn every_html5_p_closer_ends_a_p() {
+        for name in ["fieldset", "menu"] {
+            let line = html(&format!("<div><p><mark>x<{name}>y</{name}>z</div>")).expect("text");
+            let mark = [(0..1, Style::Mark)];
+            assert_eq!((line.text.as_str(), &line.styles[..]), ("x\nyz", &mark[..]));
+        }
+    }
+
     #[test]
     fn hostile_html_reads_in_linear_time() {
         let started = web_time::Instant::now();

src/documents/tree/emoji.rs

@@ -0,0 +1,103 @@
+/// `text` with each known `:shortcode:` as its emoji.
+fn emoji(text: &str) -> String {
+    let mut out = String::with_capacity(text.len());
+    let mut rest = text;
+    while let Some(at) = rest.find(':') {
+        out.push_str(&rest[..at]);
+        let after = &rest[at + 1..];
+        let len = after
+            .find(|ch: char| !shortcode_char(ch))
+            .unwrap_or(after.len());
+        let found = after[len..]
+            .starts_with(':')
+            .then(|| emojis::get_by_shortcode(&after[..len]))
+            .flatten();
+        match found {
+            Some(found) => {
+                out.push_str(found.as_str());
+                rest = &after[len + 1..];
+            }
+            None => {
+                out.push(':');
+                rest = after;
+            }
+        }
+    }
+    out.push_str(rest);
+    out
+}
+
+fn shortcode_char(ch: char) -> bool {
+    ch.is_ascii_alphanumeric() || matches!(ch, '_' | '+' | '-')
+}
+
+/// Where the first `:name:` starts.
+fn candidate(text: &str) -> Option<usize> {
+    let mut from = 0;
+    while let Some(at) = text[from..].find(':').map(|at| from + at) {
+        let after = &text[at + 1..];
+        let len = after
+            .find(|ch: char| !shortcode_char(ch))
+            .unwrap_or(after.len());
+        if len > 0 && after[len..].starts_with(':') {
+            return Some(at);
+        }
+        from = at + 1 + len;
+    }
+    None
+}
+
+/// One DOM text node's shortcodes, as GitHub reads them.
+#[derive(Default)]
+pub(crate) struct Shortcodes {
+    /// Settled by the node's first `:name:`.
+    reads: Option<bool>,
+    /// Text before it held more than white space.
+    inked: bool,
+    last: Option<char>,
+}
+
+impl Shortcodes {
+    /// A new DOM text node starts.
+    pub(crate) fn split(&mut self) {
+        *self = Self::default();
+    }
+
+    /// Blank or spaced text before the first reads them all.
+    pub(crate) fn read(&mut self, text: &str) -> String {
+        if self.reads.is_none() {
+            let at = candidate(text);
+            let lead = &text[..at.unwrap_or(text.len())];
+            self.inked |= !lead.chars().all(|ch| ch.is_ascii_whitespace());
+            self.last = lead.chars().next_back().or(self.last);
+            self.reads = at.map(|_| !self.inked || self.last == Some(' '));
+        }
+        match self.reads {
+            Some(true) => emoji(text),
+            _ => text.to_string(),
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn known_shortcodes_become_emoji() {
+        assert_eq!(emoji("hi :smile: :+1:"), "hi 😄 👍");
+        assert_eq!(emoji(":nope: at 10:30 and ::"), ":nope: at 10:30 and ::");
+        assert_eq!(emoji("a:smile:b :x:smile:"), "a😄b ❌smile:");
+        assert_eq!(emoji("é :smile: 中"), "é 😄 中");
+    }
+
+    #[test]
+    fn long_runs_scan_in_linear_time() {
+        let colons = ":zq".repeat(1 << 16);
+        let started = web_time::Instant::now();
+        assert_eq!(emoji(&colons).len(), colons.len());
+        assert_eq!(Shortcodes::default().read(&colons).len(), colons.len());
+        let spent = started.elapsed();
+        assert!(spent.as_secs() < 2, "192 KiB took {spent:?}");
+    }
+}

src/documents/tree/html.rs

@@ -96,6 +96,52 @@ pub(crate) fn breaks(name: &str) -> bool {
     )
 }
 
+/// Start tags that end an open `p`, as HTML5 lists them.
+pub(crate) fn closes_p(name: &str) -> bool {
+    matches!(
+        name,
+        "address"
+            | "article"
+            | "aside"
+            | "blockquote"
+            | "center"
+            | "details"
+            | "dialog"
+            | "dir"
+            | "div"
+            | "dl"
+            | "dd"
+            | "dt"
+            | "fieldset"
+            | "figcaption"
+            | "figure"
+            | "footer"
+            | "form"
+            | "h1"
+            | "h2"
+            | "h3"
+            | "h4"
+            | "h5"
+            | "h6"
+            | "header"
+            | "hgroup"
+            | "hr"
+            | "li"
+            | "listing"
+            | "main"
+            | "menu"
+            | "nav"
+            | "ol"
+            | "p"
+            | "pre"
+            | "search"
+            | "section"
+            | "summary"
+            | "table"
+            | "ul"
+    )
+}
+
 /// Bytes through the `>` ending the tag at `html`'s start.
 pub(crate) fn tag_end(html: &str) -> Option<usize> {
     let (mut quote, mut last) = (None, '<');
@@ -280,39 +326,6 @@ fn numeric(code: Option<u32>) -> char {
     .unwrap_or(char::REPLACEMENT_CHARACTER)
 }
 
-/// `text` with each known `:shortcode:` as its emoji.
-pub(crate) fn emoji(text: &str) -> String {
-    let mut out = String::with_capacity(text.len());
-    let mut rest = text;
-    while let Some(at) = rest.find(':') {
-        out.push_str(&rest[..at]);
-        let after = &rest[at + 1..];
-        let len = after
-            .find(|ch: char| !shortcode_char(ch))
-            .unwrap_or(after.len());
-        let found = after[len..]
-            .starts_with(':')
-            .then(|| emojis::get_by_shortcode(&after[..len]))
-            .flatten();
-        match found {
-            Some(found) => {
-                out.push_str(found.as_str());
-                rest = &after[len + 1..];
-            }
-            None => {
-                out.push(':');
-                rest = after;
-            }
-        }
-    }
-    out.push_str(rest);
-    out
-}
-
-fn shortcode_char(ch: char) -> bool {
-    ch.is_ascii_alphanumeric() || matches!(ch, '_' | '+' | '-')
-}
-
 /// `n` in superscript digits.
 pub(crate) fn superscript(n: usize) -> String {
     const DIGITS: [char; 10] = ['⁰', '¹', '²', '³', '⁴', '⁵', '⁶', '⁷', '⁸', '⁹'];
@@ -385,23 +398,14 @@ mod tests {
 
     #[test]
     fn long_runs_scan_in_linear_time() {
-        let (amps, colons) = ("&".repeat(1 << 18), ":zq".repeat(1 << 16));
+        let amps = "&".repeat(1 << 18);
         let started = web_time::Instant::now();
         assert_eq!(decoded(&amps, true).len(), amps.len());
         assert_eq!(text(&amps).len(), amps.len());
-        assert_eq!(emoji(&colons).len(), colons.len());
         let spent = started.elapsed();
         assert!(spent.as_secs() < 2, "256 KiB took {spent:?}");
     }
 
-    #[test]
-    fn known_shortcodes_become_emoji() {
-        assert_eq!(emoji("hi :smile: :+1:"), "hi 😄 👍");
-        assert_eq!(emoji(":nope: at 10:30 and ::"), ":nope: at 10:30 and ::");
-        assert_eq!(emoji("a:smile:b :x:smile:"), "a😄b ❌smile:");
-        assert_eq!(emoji("é :smile: 中"), "é 😄 中");
-    }
-
     #[test]
     fn text_takes_the_longest_legacy_name() {
         assert_eq!(

src/documents/tree/mod.rs

@@ -5,6 +5,7 @@ use markdown::mdast::{self, AlignKind};
 use super::markdown::{span, tree, walk};
 
 mod blocks;
+mod emoji;
 mod html;
 
 pub use blocks::{AlertKind, DocumentHeading};
@@ -102,8 +103,8 @@ struct Run {
     named: HashMap<String, usize>,
     /// Inside an autolink: its text stays as written.
     verbatim: bool,
-    /// Filtered tags open: their text keeps shortcodes.
-    filtered: usize,
+    /// The current DOM text node's shortcodes.
+    shortcodes: emoji::Shortcodes,
     /// White space owed, and the open elements before it.
     owed: Option<(char, usize)>,
 }
@@ -124,17 +125,18 @@ impl Run {
         self.named.get(name).copied().unwrap_or(0)
     }
 
-    /// Outside autolinks, `<code>` and filtered tags.
-    fn reads_emoji(&self) -> bool {
-        !self.verbatim && self.count("code") == 0 && self.filtered == 0
+    /// Text with its shortcodes read, outside autolinks and `<code>`.
+    fn shown(&mut self, written: &str) -> String {
+        match !self.verbatim && self.count("code") == 0 {
+            true => self.shortcodes.read(written),
+            false => written.to_string(),
+        }
     }
 
     /// Text as shown: shortcodes read, lines joined.
     fn push_text(&mut self, written: &str) {
-        match self.reads_emoji() {
-            true => self.push_plain(&html::emoji(written)),
-            false => self.push_plain(written),
-        }
+        let shown = self.shown(written);
+        self.push_plain(&shown);
     }
 
     fn push_plain(&mut self, shown: &str) {
@@ -142,14 +144,6 @@ impl Run {
         self.text.text.push_str(&soft);
     }
 
-    /// Counts a filtered tag opened or closed.
-    fn filter(&mut self, tag: &html::Tag) {
-        self.filtered = match tag.closing {
-            true => self.filtered.saturating_sub(1),
-            false => self.filtered + 1,
-        };
-    }
-
     fn push(&mut self, opened: Opened) {
         *self.named.entry(opened.name.clone()).or_default() += 1;
         self.open.push(opened);
@@ -163,15 +157,15 @@ impl Run {
     /// Opens or closes an element for an inline HTML tag.
     fn html(&mut self, written: &str) {
         let Some(tag) = html::tag(written) else {
-            return;
+            return self.shortcodes.split();
         };
+        if html::filtered(&tag.name) {
+            return self.push_text(&html::text(written));
+        }
+        self.shortcodes.split();
         if tag.name == "br" {
             return self.text.text.push('\n');
         }
-        if html::filtered(&tag.name) {
-            self.filter(&tag);
-            return self.push_plain(&html::text(written));
-        }
         let Some(style) = html::inline_style(&tag.name) else {
             return;
         };
@@ -191,6 +185,7 @@ impl Run {
         if name == "a" {
             self.end("a");
         }
+        self.shortcodes.split();
         self.push(Opened {
             name: name.to_string(),
             start: self.text.text.len(),
@@ -204,6 +199,7 @@ impl Run {
         if self.count(name) == 0 {
             return;
         }
+        self.shortcodes.split();
         let at = self
             .open
             .iter()
@@ -402,6 +398,10 @@ impl<'a> Reader<'a> {
     }
 
     fn inline_into(&self, node: &mdast::Node, run: &mut Run, images: &mut Images) {
+        // Any element ends the DOM text node.
+        if !matches!(node, mdast::Node::Text(_) | mdast::Node::Html(_)) {
+            run.shortcodes.split();
+        }
         let text = &mut run.text;
         let (children, (name, style), url) = match node {
             mdast::Node::Text(words) => return run.push_text(&words.value),

src/documents/tree/tests.rs

@@ -362,3 +362,40 @@ fn unknown_tags_show_text_and_only_anchors_link() {
     let urls: Vec<&str> = query.links.iter().map(|(_, url)| url.as_str()).collect();
     assert_eq!(urls, ["https://x.test/?q=1&p=2", "/path/"]);
 }
+
+#[test]
+fn the_first_shortcode_decides_its_text_node() {
+    // GitHub's answers, `.work/R4.3-fix3/github-*.log`.
+    for (source, shown) in [
+        ("a>:smile: :smile:", "a>:smile: :smile:"),
+        ("a> :smile: :smile:", "a> 😄 😄"),
+        ("x:smile: :smile:", "x:smile: :smile:"),
+        ("a;:smile: :smile:", "a;:smile: :smile:"),
+        ("a :smile: b>:smile:", "a 😄 b>😄"),
+        ("a :zzzq: x:smile: :smile:", "a :zzzq: x😄 😄"),
+        ("ax:zzzq: :smile:", "ax:zzzq: :smile:"),
+        ("a :x-y: z:smile:", "a :x-y: z😄"),
+        ("a :x.y: z:smile:", "a :x.y: z:smile:"),
+        ("a.:x.y: :smile:", "a.:x.y: 😄"),
+        ("x\t:smile: y:smile:", "x\t:smile: y:smile:"),
+        ("x\u{a0}:smile: y:smile:", "x\u{a0}:smile: y:smile:"),
+        ("x\n:smile: y:smile:", "x :smile: y:smile:"),
+        ("*x*:smile: :smile:", "x😄 😄"),
+        ("*x*\n:smile: y:smile:", "x 😄 y😄"),
+        ("x:smile: `c` :smile:", "x:smile: c 😄"),
+        ("x:smile:<!-- c --> :smile:", "x:smile: 😄"),
+        ("x:smile:<span>s</span> :smile:", "x:smile:s 😄"),
+        ("x&amp;:smile: :smile:", "x&:smile: :smile:"),
+        ("x:smile:  \n:smile:", "x:smile:\n😄"),
+        (
+            "a <script>x</style>:smile:</script> :smile:",
+            "a <script>x</style>:smile:</script> :smile:",
+        ),
+        (
+            "a <script><b>:smile:</b></script> :smile:",
+            "a <script>😄</script> 😄",
+        ),
+    ] {
+        assert_eq!(line(source).text, shown, "{source:?}");
+    }
+}