| 1 | use unicode_segmentation::UnicodeSegmentation; |
| 2 | use unicode_width::UnicodeWidthStr; |
| 3 | |
| 4 | /// Get the display width of a string (handling wide chars like CJK) |
| 5 | pub fn display_width(s: &str) -> usize { |
| 6 | UnicodeWidthStr::width(s) |
| 7 | } |
| 8 | |
| 9 | /// Count grapheme clusters in a string |
| 10 | pub fn grapheme_count(s: &str) -> usize { |
| 11 | s.graphemes(true).count() |
| 12 | } |
| 13 | |
| 14 | /// Get the nth grapheme from a string |
| 15 | pub fn nth_grapheme(s: &str, n: usize) -> Option<&str> { |
| 16 | s.graphemes(true).nth(n) |
| 17 | } |
| 18 | |
| 19 | /// Convert a grapheme index to byte offset |
| 20 | pub fn grapheme_to_byte_offset(s: &str, grapheme_idx: usize) -> usize { |
| 21 | s.graphemes(true) |
| 22 | .take(grapheme_idx) |
| 23 | .map(|g| g.len()) |
| 24 | .sum() |
| 25 | } |
| 26 | |
| 27 | /// Convert a byte offset to grapheme index |
| 28 | pub fn byte_to_grapheme_offset(s: &str, byte_idx: usize) -> usize { |
| 29 | let mut count = 0; |
| 30 | let mut bytes = 0; |
| 31 | for g in s.graphemes(true) { |
| 32 | if bytes >= byte_idx { |
| 33 | break; |
| 34 | } |
| 35 | bytes += g.len(); |
| 36 | count += 1; |
| 37 | } |
| 38 | count |
| 39 | } |
| 40 |