Add Indic_Conjunct_Break property. (#6379)

From #6367, @eggrobin suggests
to use Indic_Conjunct_Break (InCB) property for Grapheme Cluster Break.

Also, `InCB.toml` is incomplete yet like the following, since it is
added by ICU76 as a draft API.
```
values = [
  {discr = 0, long = "None", short = "None"},
]
```
It means that names (short / long / parse) are empty for this
implementation.

Author: makotokato

components/properties/src/props.rs

@@ -1425,6 +1425,60 @@ make_enumerated_property! {
     ule_ty: u8;
 }
 
+/// Property Indic_Conjunct_Break.
+/// See UAX #44:
+/// <https://www.unicode.org/reports/tr44/#Indic_Conjunct_Break>.
+///
+/// # Example
+///
+/// ```
+/// use icu::properties::{CodePointMapData, props::IndicConjunctBreak};
+///
+/// assert_eq!(CodePointMapData::<IndicConjunctBreak>::new().get('a'), IndicConjunctBreak::None);
+/// assert_eq!(CodePointMapData::<IndicConjunctBreak>::new().get('\u{094d}'), IndicConjunctBreak::Linker);
+/// assert_eq!(CodePointMapData::<IndicConjunctBreak>::new().get('\u{0915}'), IndicConjunctBreak::Consonant);
+/// assert_eq!(CodePointMapData::<IndicConjunctBreak>::new().get('\u{0300}'), IndicConjunctBreak::Extend);
+/// ```
+#[doc(hidden)] // draft API in ICU4C
+#[derive(Copy, Clone, Debug, Eq, PartialEq, Ord, PartialOrd, Hash)]
+#[cfg_attr(feature = "serde", derive(serde::Serialize, serde::Deserialize))]
+#[cfg_attr(feature = "datagen", derive(databake::Bake))]
+#[cfg_attr(feature = "datagen", databake(path = icu_properties::props))]
+#[allow(clippy::exhaustive_structs)] // newtype
+#[repr(transparent)]
+pub struct IndicConjunctBreak(pub(crate) u8);
+
+impl IndicConjunctBreak {
+    /// Returns an ICU4C `UIndicConjunctBreak` value.
+    pub const fn to_icu4c_value(self) -> u8 {
+        self.0
+    }
+    /// Constructor from an ICU4C `UIndicConjunctBreak` value.
+    pub const fn from_icu4c_value(value: u8) -> Self {
+        Self(value)
+    }
+}
+
+create_const_array! {
+#[doc(hidden)] // draft API in ICU4C
+#[allow(non_upper_case_globals)]
+impl IndicConjunctBreak {
+    pub const None: IndicConjunctBreak = IndicConjunctBreak(0);
+    pub const Consonant: IndicConjunctBreak = IndicConjunctBreak(1);
+    pub const Extend: IndicConjunctBreak = IndicConjunctBreak(2);
+    pub const Linker: IndicConjunctBreak = IndicConjunctBreak(3);
+}
+}
+
+make_enumerated_property! {
+    name: "Indic_Conjunct_Break";
+    short_name: "InCB";
+    ident: IndicConjunctBreak;
+    data_marker: crate::provider::PropertyEnumIndicConjunctBreakV1;
+    singleton: SINGLETON_PROPERTY_ENUM_INDIC_CONJUNCT_BREAK_V1;
+    ule_ty: u8;
+}
+
 /// Property Indic_Syllabic_Category.
 /// See UAX #44:
 /// <https://www.unicode.org/reports/tr44/#Indic_Syllabic_Category>.

components/properties/src/provider.rs

@@ -143,6 +143,7 @@ const _: () = {
     impl_property_enum_general_category_v1!(Baked);
     impl_property_enum_grapheme_cluster_break_v1!(Baked);
     impl_property_enum_hangul_syllable_type_v1!(Baked);
+    impl_property_enum_indic_conjunct_break_v1!(Baked);
     impl_property_enum_indic_syllabic_category_v1!(Baked);
     impl_property_enum_joining_type_v1!(Baked);
     impl_property_enum_line_break_v1!(Baked);
@@ -619,6 +620,12 @@ icu_provider::data_marker!(
     PropertyCodePointMap<'static, crate::props::HangulSyllableType>,
     is_singleton = true,
 );
+icu_provider::data_marker!(
+    /// Data marker for the 'IndicConjunctBreak' Unicode property
+    PropertyEnumIndicConjunctBreakV1,
+    PropertyCodePointMap<'static, crate::props::IndicConjunctBreak>,
+    is_singleton = true,
+);
 icu_provider::data_marker!(
     /// Data marker for the 'IndicSyllabicCategory' Unicode property
     PropertyEnumIndicSyllabicCategoryV1,
@@ -793,6 +800,7 @@ pub const MARKERS: &[DataMarkerInfo] = &[
     PropertyEnumGeneralCategoryV1::INFO,
     PropertyEnumGraphemeClusterBreakV1::INFO,
     PropertyEnumHangulSyllableTypeV1::INFO,
+    PropertyEnumIndicConjunctBreakV1::INFO,
     PropertyEnumIndicSyllabicCategoryV1::INFO,
     PropertyEnumJoiningTypeV1::INFO,
     PropertyEnumLineBreakV1::INFO,

components/properties/src/runtime.rs

@@ -138,6 +138,7 @@ enum EnumeratedProperty {
     GeneralCategory = 0x1005,
     GraphemeClusterBreak = 0x1012,
     HangulSyllableType = 0x100B,
+    IndicConjunctBreak = 0x101A,
     IndicPositionalCategory = 0x1016,
     IndicSyllabicCategory = 0x1017,
     JoiningGroup = 0x1006,

components/properties/src/trievalue.rs

@@ -5,8 +5,8 @@
 use crate::bidi::BidiMirroringGlyph;
 use crate::props::{
     BidiClass, CanonicalCombiningClass, EastAsianWidth, GeneralCategory, GeneralCategoryGroup,
-    GraphemeClusterBreak, HangulSyllableType, IndicSyllabicCategory, JoiningType, LineBreak,
-    Script, SentenceBreak, VerticalOrientation, WordBreak,
+    GraphemeClusterBreak, HangulSyllableType, IndicConjunctBreak, IndicSyllabicCategory,
+    JoiningType, LineBreak, Script, SentenceBreak, VerticalOrientation, WordBreak,
 };
 use crate::script::ScriptWithExt;
 use core::convert::TryInto;
@@ -151,6 +151,18 @@ impl TrieValue for SentenceBreak {
     }
 }
 
+impl TrieValue for IndicConjunctBreak {
+    type TryFromU32Error = TryFromIntError;
+
+    fn try_from_u32(i: u32) -> Result<Self, Self::TryFromU32Error> {
+        u8::try_from(i).map(Self)
+    }
+
+    fn to_u32(self) -> u32 {
+        u32::from(self.0)
+    }
+}
+
 impl TrieValue for IndicSyllabicCategory {
     type TryFromU32Error = TryFromIntError;
 

provider/data/properties/data/mod.rs

@@ -71,6 +71,7 @@ property/enum/east/asian/width/v1, <singleton>, 5028B, 4971B, cbe33fdd284572e5
 property/enum/general/category/v1, <singleton>, 17572B, 17516B, fa8858c0d81ead14
 property/enum/grapheme/cluster/break/v1, <singleton>, 7840B, 7783B, bd0d2d3da35038da
 property/enum/hangul/syllable/type/v1, <singleton>, 888B, 829B, 67c6d3aaab48ff19
+property/enum/indic/conjunct/break/v1, <singleton>, 6724B, 6667B, 855285c232bd1220
 property/enum/indic/syllabic/category/v1, <singleton>, 6248B, 6189B, c10d1f8e12ae80ea
 property/enum/joining/type/v1, <singleton>, 7072B, 7015B, dff64b1d9027a0e6
 property/enum/line/break/v1, <singleton>, 15284B, 15228B, ec2f73fe17e5fb1c

provider/data/properties/data/property_enum_indic_conjunct_break_v1.rs.data

@@ -185,6 +185,7 @@ macro_rules! registry(
             icu::properties::provider::PropertyEnumGeneralCategoryV1: PropertyEnumGeneralCategoryV1,
             icu::properties::provider::PropertyEnumGraphemeClusterBreakV1: PropertyEnumGraphemeClusterBreakV1,
             icu::properties::provider::PropertyEnumHangulSyllableTypeV1: PropertyEnumHangulSyllableTypeV1,
+            icu::properties::provider::PropertyEnumIndicConjunctBreakV1: PropertyEnumIndicConjunctBreakV1,
             icu::properties::provider::PropertyEnumIndicSyllabicCategoryV1: PropertyEnumIndicSyllabicCategoryV1,
             icu::properties::provider::PropertyEnumJoiningTypeV1: PropertyEnumJoiningTypeV1,
             icu::properties::provider::PropertyEnumLineBreakV1: PropertyEnumLineBreakV1,