mirror of
https://github.com/storytold/craft-libs.git
synced 2026-11-16 23:24:24 +00:00
* Add craft-wordmodel: WordCraft's document model without its editing code WordCraft's crates/doc (wordcraft-doc, at 07f97737) moved as it is, so the DOCX, RTF, ODT and other text-format crates can read into and write from one model. Module paths, type names and serde attributes are unchanged: an app that re-exports the crate keeps its native file format. Left in the app: range editing (edit.rs), IME text and equation editing. Not model, and already in craft-libs: code pages (craft-rtf), the ZIP entry-count check (craft-opc), the compound-file guard (craft-cfb). The paragraph walks moved to walk.rs and the unit helpers of wordcraft-geom to geom.rs. * craft-wordmodel: math_tree, the arguments of an equation node and a walk over its runs The DOCX reader and writer walk an equation's runs. The walk and the child accessors it uses were in WordCraft's equation editor (math_edit.rs), which stays in the app; they are structure, not editing. * craft-wordmodel: keep the document operations (edit.rs) with the model The DOCX and RTF readers use them: alternative-format chunks are merged into a document with adopt_blocks, and a reader formats ranges with format_range and inserts objects. They operate on the document, not on a view, so they belong beside it. The tests that drove them come back with them; the paragraph walks stay in walk.rs and edit re-exports them. base64 0.23, as WordCraft and craft-offcrypto use.
87 lines
3.8 KiB
Rust
87 lines
3.8 KiB
Rust
//! Script classification for bidirectional and complex-script text (Persian, Arabic, Hebrew…).
|
|
//!
|
|
//! The full Unicode Bidirectional Algorithm (UAX #9) runs in layout; this module only answers
|
|
//! the cheap questions the model and the engine need: does a character belong to a
|
|
//! right-to-left script, and is it formatted with the complex-script properties?
|
|
|
|
/// A character of a right-to-left script: Hebrew, Arabic (Persian, Urdu…), Syriac, Thaana, N'Ko,
|
|
/// Samaritan, Mandaic, and their presentation forms. Includes the Arabic-Indic and Persian
|
|
/// (Extended Arabic-Indic) digits and the Arabic combining marks.
|
|
pub fn is_rtl_script(c: char) -> bool {
|
|
matches!(u32::from(c),
|
|
0x0590..=0x08FF
|
|
| 0xFB1D..=0xFDFF
|
|
| 0xFE70..=0xFEFF
|
|
| 0x10800..=0x10FFF
|
|
| 0x1E800..=0x1EFFF)
|
|
}
|
|
|
|
/// A character Word formats with the complex-script properties (`w:cs` font, `w:szCs`, `w:bCs`,
|
|
/// `w:iCs`): right-to-left scripts, the Indic scripts, Thai and Lao.
|
|
pub fn is_complex_script(c: char) -> bool {
|
|
is_rtl_script(c) || matches!(u32::from(c), 0x0900..=0x0EFF)
|
|
}
|
|
|
|
/// A character that belongs to a word for word selection and Ctrl+arrow movement: letters,
|
|
/// digits, `_` and `'`, plus what sits inside Persian and Arabic words: the zero-width non-joiner
|
|
/// (نیمفاصله, as in «میخواهم»), the zero-width joiner, tatweel and the Arabic combining marks.
|
|
pub fn is_word_char(c: char) -> bool {
|
|
c.is_alphanumeric()
|
|
|| c == '_'
|
|
|| c == '\''
|
|
|| matches!(u32::from(c), 0x200C | 0x200D | 0x0640 | 0x0610..=0x061A | 0x064B..=0x065F | 0x0670 | 0x06D6..=0x06DC | 0x06DF..=0x06E8 | 0x06EA..=0x06ED | 0x08D3..=0x08FF | 0x0300..=0x036F)
|
|
}
|
|
|
|
/// Does `text` contain a right-to-left character?
|
|
pub fn has_rtl(text: &str) -> bool {
|
|
text.chars().any(is_rtl_script)
|
|
}
|
|
|
|
/// Does the first strong directional character in `text` belong to a right-to-left script?
|
|
///
|
|
/// Follows UAX #9 rules P2 and P3: characters with strong bidirectional class AL or R
|
|
/// (Arabic, Hebrew, Syriac, Thaana…) give `true`; strong L characters (Latin, Greek,
|
|
/// Cyrillic, CJK…) give `false`. Neutral, weak and whitespace characters are skipped.
|
|
pub fn first_strong_is_rtl(text: &str) -> bool {
|
|
for c in text.chars() {
|
|
if c == '\u{200F}' {
|
|
return true;
|
|
}
|
|
if c == '\u{200E}' {
|
|
return false;
|
|
}
|
|
if c.is_alphabetic() {
|
|
return is_rtl_script(c);
|
|
}
|
|
}
|
|
false
|
|
}
|
|
|
|
#[cfg(test)]
|
|
mod tests {
|
|
use super::*;
|
|
|
|
#[test]
|
|
fn classifies_persian_and_latin() {
|
|
// Persian letters, the Persian-only letters (پ چ ژ گ ک ی), ZWNJ-free word, digits.
|
|
assert!("سلام".chars().all(is_rtl_script));
|
|
assert!("پچژگکی".chars().all(is_rtl_script));
|
|
assert!("۰۱۲۳۴۵۶۷۸۹".chars().all(is_rtl_script));
|
|
assert!(is_rtl_script('\u{064E}'), "fatha (a combining mark) is Arabic script");
|
|
assert!("שלום".chars().all(is_rtl_script));
|
|
assert!(!"Hello 123".chars().any(is_rtl_script));
|
|
assert!(!is_rtl_script('\u{200C}'), "ZWNJ is a format character, not a letter");
|
|
assert!(is_complex_script('क') && !is_rtl_script('क'));
|
|
assert!(has_rtl("Word ورد 2024") && !has_rtl("Word 2024"));
|
|
assert!("میخواهم".chars().all(is_word_char), "ZWNJ is inside the word");
|
|
assert!("کِتاب".chars().all(is_word_char), "so are harakat");
|
|
assert!(!is_word_char(' ') && !is_word_char('،'));
|
|
assert!(first_strong_is_rtl("سلام"));
|
|
assert!(first_strong_is_rtl("من ناوم هێڤاره"));
|
|
assert!(first_strong_is_rtl(" 123. سلام"));
|
|
assert!(!first_strong_is_rtl("Hello سلام"));
|
|
assert!(!first_strong_is_rtl("123 Hello"));
|
|
assert!(!first_strong_is_rtl(""));
|
|
}
|
|
}
|