diff options
| author | Laurenz <laurmaedje@gmail.com> | 2022-04-16 22:42:49 +0200 |
|---|---|---|
| committer | Laurenz <laurmaedje@gmail.com> | 2022-04-16 23:06:47 +0200 |
| commit | 4494b443bb34fed2208ee3fc87e9a18e7d14b2ab (patch) | |
| tree | 25a655821b81d10659132fae26861a2aff2d5a95 /src/parse | |
| parent | c5b3f8ee98203191d83d3cfca39bb0f35ee6efc2 (diff) | |
Ellipsis
Diffstat (limited to 'src/parse')
| -rw-r--r-- | src/parse/mod.rs | 1 | ||||
| -rw-r--r-- | src/parse/tokens.rs | 16 |
2 files changed, 12 insertions, 5 deletions
diff --git a/src/parse/mod.rs b/src/parse/mod.rs index 7536b2ca..be947170 100644 --- a/src/parse/mod.rs +++ b/src/parse/mod.rs @@ -214,6 +214,7 @@ fn markup_node(p: &mut Parser, at_start: &mut bool) { | NodeKind::Shy | NodeKind::EnDash | NodeKind::EmDash + | NodeKind::Ellipsis | NodeKind::Quote(_) | NodeKind::Linebreak(_) | NodeKind::Raw(_) diff --git a/src/parse/tokens.rs b/src/parse/tokens.rs index ae3d7b9c..f6e1f296 100644 --- a/src/parse/tokens.rs +++ b/src/parse/tokens.rs @@ -140,6 +140,7 @@ impl<'s> Tokens<'s> { // Markup. '~' => NodeKind::NonBreakingSpace, '-' => self.hyph(), + '.' if self.s.eat_if("..") => NodeKind::Ellipsis, '\'' => NodeKind::Quote(false), '"' => NodeKind::Quote(true), '*' if !self.in_word() => NodeKind::Star, @@ -216,7 +217,7 @@ impl<'s> Tokens<'s> { // Comments, parentheses, code. '/' | '[' | ']' | '{' | '}' | '#' | // Markup - '~' | '\'' | '"' | '*' | '_' | '`' | '$' | '-' | '\\' + '~' | '-' | '.' | '\'' | '"' | '*' | '_' | '`' | '$' | '\\' }; loop { @@ -224,12 +225,17 @@ impl<'s> Tokens<'s> { TABLE.get(c as usize).copied().unwrap_or_else(|| c.is_whitespace()) }); + // Allow a single space, optionally preceded by . or - if something + // alphanumeric follows directly. This leads to less text nodes, + // which is good for performance. let mut s = self.s; - if !(s.eat_if(' ') && s.at(char::is_alphanumeric)) { + s.eat_if(['.', '-']); + s.eat_if(' '); + if !s.at(char::is_alphanumeric) { break; } - self.s.eat(); + self.s = s; } NodeKind::Text(self.s.from(start).into()) @@ -831,7 +837,7 @@ mod tests { fn test_tokenize_text() { // Test basic text. t!(Markup[" /"]: "hello" => Text("hello")); - t!(Markup[" /"]: "hello-world" => Text("hello"), Minus, Text("world")); + t!(Markup[" /"]: "hello-world" => Text("hello-world")); // Test code symbols in text. t!(Markup[" /"]: "a():\"b" => Text("a():"), Quote(true), Text("b")); @@ -897,7 +903,7 @@ mod tests { t!(Markup[" "]: "." => EnumNumbering(None)); t!(Markup[" "]: "1." => EnumNumbering(Some(1))); t!(Markup[" "]: "1.a" => EnumNumbering(Some(1)), Text("a")); - t!(Markup[" /"]: "a1." => Text("a1.")); + t!(Markup[" /"]: "a1." => Text("a1"), EnumNumbering(None)); } #[test] |