[char_property] Implement *CharProperty traits

Character Properties are of different kinds and shapes, and as UNIC
components grow, we need a better way to be able to categorize them by
their shape, and a way to make sure we have consistent, noncolliding
API for them.

This is the first step into building a CharProperty taxonomy, with as
little as possibly needed to provide the assurances desired.

We hope that the implementation can be improved over time with new
features added to the language. There's already some proposals in this
front. See these discussions for more details:

* [Traits as contract, without changes to call-sites](https://users.rust-lang.org/t/traits-as-contract-without-changes-to-call-sites/11938/11>)

* [RFC: delegation of implementation](rust-lang/rfcs#1406)

Author: behnam

unic/ucd/age/src/age.rs

@@ -14,6 +14,7 @@ use std::fmt;
 use unic_utils::CharDataTable;
 
 pub use unic_ucd_core::UnicodeVersion;
+use unic_utils::CharProperty;
 
 
 /// Represents values of the Unicode character property
@@ -41,6 +42,12 @@ pub enum Age {
     Unassigned, // Unassigned is older (larger) than any age
 }
 
+impl CharProperty for Age {
+    fn of(ch: char) -> Self {
+        Self::of(ch)
+    }
+}
+
 use Age::{Assigned, Unassigned};
 
 

unic/ucd/age/src/lib.rs

@@ -10,7 +10,7 @@
 // except according to those terms.
 
 
-#![forbid(unsafe_code)]
+#![forbid(unsafe_code, unconditional_recursion)]
 #![deny(missing_docs)]
 
 //! # UNIC — UCD — Character Age

unic/ucd/bidi/src/bidi_class.rs

@@ -9,9 +9,11 @@
 // option. This file may not be copied, modified, or distributed
 // except according to those terms.
 
+
 use std::fmt;
 
-use unic_utils::CharDataTable;
+use unic_utils::{CharDataTable, CharProperty, EnumeratedCharProperty};
+
 
 /// Represents the Unicode character
 /// [*Bidi_Class*](http://www.unicode.org/reports/tr44/#Bidi_Class) property, also known as the
@@ -48,6 +50,18 @@ pub enum BidiClass {
     // [UNIC_UPDATE_ON_UNICODE_UPDATE] Source: `tables/bidi_class_type.rsv`
 }
 
+impl CharProperty for BidiClass {
+    fn of(ch: char) -> Self {
+        Self::of(ch)
+    }
+}
+
+impl EnumeratedCharProperty for BidiClass {
+    fn all_values() -> &'static [Self] {
+        Self::all_values()
+    }
+}
+
 
 /// Abbreviated name aliases for
 /// [*Bidi_Class*](http://www.unicode.org/reports/tr44/#Bidi_Class) property.
@@ -111,6 +125,37 @@ impl BidiClass {
         *TABLE.find_or(ch, &L)
     }
 
+    /// Exhaustive list of all `BidiClass` property values.
+    pub fn all_values() -> &'static [BidiClass] {
+        use BidiClass::*;
+        const ALL_VALUES: &[BidiClass] = &[
+            ArabicLetter,
+            ArabicNumber,
+            ParagraphSeparator,
+            BoundaryNeutral,
+            CommonSeparator,
+            EuropeanNumber,
+            EuropeanSeparator,
+            EuropeanTerminator,
+            FirstStrongIsolate,
+            LeftToRight,
+            LeftToRightEmbedding,
+            LeftToRightIsolate,
+            LeftToRightOverride,
+            NonspacingMark,
+            OtherNeutral,
+            PopDirectionalFormat,
+            PopDirectionalIsolate,
+            RightToLeft,
+            RightToLeftEmbedding,
+            RightToLeftIsolate,
+            RightToLeftOverride,
+            SegmentSeparator,
+            WhiteSpace,
+        ];
+        ALL_VALUES
+    }
+
     /// Abbreviated name of the *Bidi_Class* property value.
     ///
     /// <http://www.unicode.org/Public/UCD/latest/ucd/PropertyValueAliases.txt#Bidi_Class>
@@ -213,6 +258,14 @@ impl BidiClass {
     }
 }
 
+
+impl Default for BidiClass {
+    fn default() -> Self {
+        BidiClass::LeftToRight
+    }
+}
+
+
 impl fmt::Display for BidiClass {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
         write!(f, "{}", self.display())

unic/ucd/bidi/src/lib.rs

@@ -10,7 +10,7 @@
 // except according to those terms.
 
 
-#![forbid(unsafe_code)]
+#![forbid(unsafe_code, unconditional_recursion)]
 #![deny(missing_docs)]
 
 //! # UNIC — UCD — Bidi

unic/ucd/category/Cargo.toml

@@ -15,6 +15,6 @@ exclude = []
 travis-ci = { repository = "behnam/rust-unic", branch = "master" }
 
 [dependencies]
+matches = "0.1"
 unic-ucd-core = { path = "../core/", version = "0.5.0" }
 unic-utils = { path = "../../utils/", version = "0.5.0" }
-matches = "0.1"

unic/ucd/category/src/category.rs

@@ -8,15 +8,19 @@
 // option. This file may not be copied, modified, or distributed
 // except according to those terms.
 
-use unic_utils::CharDataTable;
+
+use std::fmt;
+
+use unic_utils::{CharDataTable, CharProperty, EnumeratedCharProperty};
+
 
 /// Represents the Unicode Character
 /// [*General_Category*](http://unicode.org/reports/tr44/#General_Category) property.
 ///
 /// This is a useful breakdown into various character types which can be used as a default
 /// categorization in implementations. For the property values, see
 /// [*General_Category Values*](http://unicode.org/reports/tr44/#General_Category_Values).
-#[derive(Clone, Copy, Debug, PartialEq, Eq)]
+#[derive(Clone, Copy, Debug, Eq, Hash, PartialEq)]
 pub enum GeneralCategory {
     /// An uppercase letter (Short form: `Lu`)
     UppercaseLetter,
@@ -80,6 +84,21 @@ pub enum GeneralCategory {
     Unassigned,
 }
 
+
+impl CharProperty for GeneralCategory {
+    fn of(ch: char) -> Self {
+        Self::of(ch)
+    }
+}
+
+
+impl EnumeratedCharProperty for GeneralCategory {
+    fn all_values() -> &'static [Self] {
+        Self::all_values()
+    }
+}
+
+
 pub mod abbr_names {
     pub use super::GeneralCategory::UppercaseLetter as Lu;
     pub use super::GeneralCategory::LowercaseLetter as Ll;
@@ -125,8 +144,6 @@ impl GeneralCategory {
     }
 
     /// Exhaustive list of all `GeneralCategory` property values.
-    ///
-    /// Reference: <http://unicode.org/reports/tr44/#General_Category_Values>
     pub fn all_values() -> &'static [GeneralCategory] {
         use GeneralCategory::*;
         const ALL_VALUES: &[GeneralCategory] = &[
@@ -163,8 +180,16 @@ impl GeneralCategory {
         ];
         ALL_VALUES
     }
+
+    /// Human-readable description of the property value.
+    // TODO: Needs to be improved by returning long-name with underscores replaced by space.
+    #[inline]
+    pub fn display(&self) -> String {
+        format!("{:?}", self).to_owned()
+    }
 }
 
+
 impl GeneralCategory {
     /// `Lu` | `Ll` | `Lt`  (Short form: `LC`)
     pub fn is_cased_letter(&self) -> bool {
@@ -207,6 +232,21 @@ impl GeneralCategory {
     }
 }
 
+
+impl Default for GeneralCategory {
+    fn default() -> Self {
+        GeneralCategory::Unassigned
+    }
+}
+
+
+impl fmt::Display for GeneralCategory {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        write!(f, "{}", self.display())
+    }
+}
+
+
 #[cfg(test)]
 mod tests {
     use super::GeneralCategory as GC;
@@ -305,4 +345,11 @@ mod tests {
             assert_eq!(GC::of(c), GC::Unassigned);
         }
     }
+
+    #[test]
+    fn test_display() {
+        //assert_eq!(format!("{}", GC::UppercaseLetter), "Uppercase Letter");
+        assert_eq!(format!("{}", GC::UppercaseLetter), "UppercaseLetter");
+        assert_eq!(format!("{}", GC::Unassigned), "Unassigned");
+    }
 }

unic/ucd/category/src/lib.rs

@@ -8,7 +8,7 @@
 // option. This file may not be copied, modified, or distributed
 // except according to those terms.
 
-#![deny(unsafe_code, missing_docs)]
+#![deny(unsafe_code, missing_docs, unconditional_recursion)]
 
 //! # UNIC — UCD — Category
 //!
@@ -38,6 +38,7 @@
 
 #[macro_use]
 extern crate matches;
+
 extern crate unic_ucd_core;
 extern crate unic_utils;
 

unic/ucd/core/src/lib.rs

@@ -9,7 +9,7 @@
 // except according to those terms.
 
 
-#![forbid(unsafe_code, missing_docs)]
+#![forbid(unsafe_code, missing_docs, unconditional_recursion)]
 
 //! # UNIC — UCD — Core
 //!

unic/ucd/normal/src/canonical_combining_class.rs

@@ -15,7 +15,9 @@
 //! Reference: <http://unicode.org/reports/tr44/#Canonical_Combining_Class_Values>
 
 
-use unic_utils::CharDataTable;
+use std::fmt;
+
+use unic_utils::{CharDataTable, CharProperty};
 
 
 /// Represents *Canonical_Combining_Class* property of a Unicode character.
@@ -82,13 +84,33 @@ pub mod values {
 }
 
 
+impl CharProperty for CanonicalCombiningClass {
+    fn of(ch: char) -> Self {
+        Self::of(ch)
+    }
+}
+
+
 impl CanonicalCombiningClass {
     /// Find the character *Canonical_Combining_Class* property value.
     pub fn of(ch: char) -> CanonicalCombiningClass {
         const TABLE: &'static [(char, char, CanonicalCombiningClass)] =
             include!("tables/canonical_combining_class_values.rsv");
         *TABLE.find_or(ch, &CanonicalCombiningClass(0))
     }
+
+    /// Human-readable description of the property value.
+    // TODO: Needs to be improved by returning long-name with underscores replaced by space.
+    #[inline]
+    pub fn display(&self) -> String {
+        format!("{}", self.number())
+    }
+}
+
+impl fmt::Display for CanonicalCombiningClass {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        write!(f, "{}", self.display())
+    }
 }
 
 
@@ -224,4 +246,10 @@ mod tests {
         assert_eq!(CCC::of('\u{0315}').number(), 232);
         assert_eq!(CCC::of('\u{1e94a}').number(), 7);
     }
+
+    #[test]
+    fn test_display() {
+        assert_eq!(format!("{}", CCC::of('\u{0000}')), "0");
+        assert_eq!(format!("{}", CCC::of('\u{0300}')), "230");
+    }
 }