Address PR comments.

- Move char functions into their own module under helix_core.
- Use matches!() macro where appropriate.
- Use a static lifetime on indent_unit() now that we can.

1 files changed, 41 insertions, 0 deletions

diff --git a/helix-core/src/chars.rs b/helix-core/src/chars.rs
new file mode 100644
index 00000000..243a1374
--- /dev/null
+++ b/helix-core/src/chars.rs
@@ -0,0 +1,41 @@
+/// Determine whether a character is a line break.
+pub fn char_is_linebreak(c: char) -> bool {
+    matches!(
+        c,
+        '\u{000A}' | // LineFeed
+        '\u{000B}' | // VerticalTab
+        '\u{000C}' | // FormFeed
+        '\u{000D}' | // CarriageReturn
+        '\u{0085}' | // NextLine
+        '\u{2028}' | // Line Separator
+        '\u{2029}' // ParagraphSeparator
+    )
+}
+
+/// Determine whether a character qualifies as (non-line-break)
+/// whitespace.
+pub fn char_is_whitespace(c: char) -> bool {
+    // TODO: this is a naive binary categorization of whitespace
+    // characters.  For display, word wrapping, etc. we'll need a better
+    // categorization based on e.g. breaking vs non-breaking spaces
+    // and whether they're zero-width or not.
+    match c {
+        //'\u{1680}' | // Ogham Space Mark (here for completeness, but usually displayed as a dash, not as whitespace)
+        '\u{0009}' | // Character Tabulation
+        '\u{0020}' | // Space
+        '\u{00A0}' | // No-break Space
+        '\u{180E}' | // Mongolian Vowel Separator
+        '\u{202F}' | // Narrow No-break Space
+        '\u{205F}' | // Medium Mathematical Space
+        '\u{3000}' | // Ideographic Space
+        '\u{FEFF}'   // Zero Width No-break Space
+        => true,
+
+        // En Quad, Em Quad, En Space, Em Space, Three-per-em Space,
+        // Four-per-em Space, Six-per-em Space, Figure Space,
+        // Punctuation Space, Thin Space, Hair Space, Zero Width Space.
+        c if ('\u{2000}' ..= '\u{200B}').contains(&c) => true,
+
+        _ => false,
+    }
+}