Mark U+070F SYRIAC ABBREVIATION MARK as zero width

unicode-rs · May 21, 2024 · 934c875 · 934c875
1 parent 7cb4f39
commit 934c875
Show file tree

Hide file tree

Showing 4 changed files with 14 additions and 2 deletions.
diff --git a/scripts/unicode.py b/scripts/unicode.py
@@ -241,6 +241,10 @@ def load_zero_widths() -> "list[bool]":
     # width 2. Therefore, we treat it as having width 2.
     zw_map[0x115F] = False
 
+    # Syriac abbreviation mark
+    # This is a `Prepended_Concatenation_Mark`, but unlike the others it's zero-width
+    zw_map[0x070F] = True
+
     return zw_map
 
 

diff --git a/src/lib.rs b/src/lib.rs
@@ -57,6 +57,7 @@
 //!      - [`'\u{1B43}'` BALINESE VOWEL SIGN PEPET TEDUNG](https://util.unicode.org/UnicodeJsps/character.jsp?a=1B43).
 //!    - [Characters](https://util.unicode.org/UnicodeJsps/list-unicodeset.jsp?a=%5Cp%7BHangul_Syllable_Type%3DV%7D%5Cp%7BHangul_Syllable_Type%3DT%7D)
 //!       with a [`Hangul_Syllable_Type`] of `Vowel_Jamo` (`V`) or `Trailing_Jamo` (`T`).
+//!    - `'\u{070F}'` [SYRIAC] ABBREVIATION MARK.
 //! 7. [Characters](https://util.unicode.org/UnicodeJsps/list-unicodeset.jsp?a=%5Cp%7BEast_Asian_Width%3DF%7D%5Cp%7BEast_Asian_Width%3DW%7D)
 //!    with an [`East_Asian_Width`] of [`Fullwidth`] or [`Wide`] have width 2.
 //! 8. [Characters](https://util.unicode.org/UnicodeJsps/list-unicodeset.jsp?a=%5Cp%7BEast_Asian_Width%3DA%7D)
@@ -78,6 +79,7 @@
 //!
 //! [Enclosed Ideographic Supplement]: https://unicode.org/charts/PDF/U1F200.pdf
 //!
+//! [Syriac]: https://www.unicode.org/versions/Unicode15.0.0/ch09.pdf#G13006
 //! [Lisu tone letter]: https://www.unicode.org/versions/Unicode15.0.0/ch18.pdf#G42078
 //!
 //! ## Canonical equivalence

diff --git a/src/tables.rs b/src/tables.rs
@@ -323,7 +323,7 @@ pub mod charwidth {
         0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x00, 0x00, 0x40, 0x54, 0x55, 0x55, 0x55, 0x55, 0x55,
         0x55, 0x55, 0x55, 0x55, 0x55, 0x15, 0x00, 0x00, 0x00, 0x00, 0x00, 0x55, 0x55, 0x55, 0x55,
         0x54, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x05, 0x00, 0x14, 0x00, 0x14, 0x04,
-        0x50, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x51, 0x55, 0x55, 0x55, 0x55, 0x55,
+        0x50, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x15, 0x51, 0x55, 0x55, 0x55, 0x55, 0x55,
         0x55, 0x55, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x40, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55,
         0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55,
         0x55, 0x05, 0x00, 0x00, 0x54, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55,

diff --git a/tests/tests.rs b/tests/tests.rs
@@ -100,11 +100,17 @@ fn test_jamo() {
 #[test]
 fn test_prepended_concatenation_marks() {
     assert_eq!('\u{0600}'.width(), Some(1));
-    assert_eq!('\u{070F}'.width(), Some(1));
     assert_eq!('\u{08E2}'.width(), Some(1));
     assert_eq!('\u{110BD}'.width(), Some(1));
 }
 
+#[test]
+fn test_syriac_abbreviation_mark() {
+    assert_eq!('\u{070F}'.width(), Some(0));
+    assert_eq!("\u{070F}".width(), 0);
+}
+
+
 #[test]
 fn test_interlinear_annotation_chars() {
     assert_eq!('\u{FFF9}'.width(), Some(1));