Add support for the new Indic_Conjunct_Break property.

Author: dbuenzli

CHANGES.md

@@ -17,6 +17,8 @@
   `ID_Compat_Math_{Start,Continue}` properties.
 - Add `Uucd.Case.Nfkc_simple_fold.fold`, support for the new 
   `NFKC_Simple_Casefold` property.
+- Add `Uucd.Break.indic_conjunct_break`, support for the new 
+  `Indic_Conjunct_Break` property.
 
 v15.0.0 2022-09-15 Zagreb
 -------------------------

src/uucp.mli

@@ -91,8 +91,6 @@ module White = Uucp__white
        {{:http://www.unicode.org/reports/tr44/#Joining_Group}Joining_Group},
        {{:http://www.unicode.org/reports/tr44/#Joining_Type}Joining_Type},
        {{:http://www.unicode.org/reports/tr44/#Vertical_Orientation}Vertical_Orientation},
-       {{:http://www.unicode.org/reports/tr44/#Indic_Conjuct_Break}
-       Indic_Conjuct_Break},
        {{:http://www.unicode.org/reports/tr44/#Indic_Syllabic_Category}
        Indic_Syllabic_Category},
        {{:http://www.unicode.org/reports/tr44/#Indic_Positional_Category}

src/uucp__break.ml

@@ -28,6 +28,12 @@ module Low = struct
 
   let sentence_max = sentence_max
   let sentence_of_int = sentence_of_byte
+
+  let indic_conjunct_break u =
+    Uucp_tmapbyte.get Uucp_break_data.indic_conjunct_break_map (Uchar.to_int u)
+
+  let indic_conjunct_break_max = indic_conjunct_break_max
+  let indic_conjunct_break_of_int = indic_conjunct_break_of_byte
 end
 
 let line u = Array.unsafe_get Low.line_of_int (Low.line u)
@@ -36,6 +42,9 @@ let grapheme_cluster u = Array.unsafe_get Low.grapheme_cluster_of_int
 
 let word u = Array.unsafe_get Low.word_of_int (Low.word u)
 let sentence u = Array.unsafe_get Low.sentence_of_int (Low.sentence u)
+let indic_conjunct_break u =
+  Array.unsafe_get Low.indic_conjunct_break_of_int
+    (Low.indic_conjunct_break u)
 
 let east_asian_width u =
   Uucp_rmap.get Uucp_break_data.east_asian_width_map (Uchar.to_int u)

src/uucp__break.mli

@@ -63,8 +63,7 @@ type word =
 (** The type for word breaks. *)
 
 val pp_word : Format.formatter -> word -> unit
-(** [pp_grapheme_cluster ppf g] prints an unspecified representation of [g]
-      on [ppf]. *)
+(** [pp_word ppf b] prints an unspecified representation of [b] on [ppf]. *)
 
 val word : Uchar.t -> word
 (** [word u] is [u]'s
@@ -79,14 +78,27 @@ type sentence =
 (** The type for sentence breaks. *)
 
 val pp_sentence : Format.formatter -> sentence -> unit
-(** [pp_grapheme_cluster ppf g] prints an unspecified representation of [g]
-    on [ppf]. *)
+(** [pp_sentence ppf b] prints an unspecified representation of [b] on [ppf]. *)
 
 val sentence : Uchar.t -> sentence
 (** [sentence u] is [u]'s
     {{:http://www.unicode.org/reports/tr44/#Sentence_Break}sentence break}
     property. *)
 
+(** {1:indic_conjunct_break Indic conjunct break} *)
+
+type indic_conjunct_break = [ `Consonant | `Extend | `Linker | `None ]
+(** The type for Indic Conjunct Break. *)
+
+val pp_indic_conjunct_break : Format.formatter -> indic_conjunct_break -> unit
+(** [pp_indic_conjunct_break ppf b] prints an unspecified representation of [b]
+    on [ppf]. *)
+
+val indic_conjunct_break : Uchar.t -> indic_conjunct_break
+(** [indic_conjunct_break u] is [u]'s
+    {{:http://www.unicode.org/reports/tr44/#Indic_Conjunct_Break}
+    Indic conjunct break} property. *)
+
 (** {1:east_asian_width East Asian width} *)
 
 type east_asian_width = [ `A | `F | `H | `N | `Na | `W ]
@@ -98,8 +110,8 @@ val pp_east_asian_width : Format.formatter -> east_asian_width -> unit
 
 val east_asian_width : Uchar.t -> east_asian_width
 (** [east_asian_width u] is [u]'s
-    {{:http://www.unicode.org/reports/tr44/#East_Asian_Width}East Asian
-    width} property. *)
+    {{:http://www.unicode.org/reports/tr44/#East_Asian_Width}East
+    Asian width} property. *)
 
 (** {1:terminal_width Terminal width} *)
 
@@ -240,4 +252,16 @@ module Low : sig
   val sentence_of_int : sentence array
   (** [sentence_of_int.(i)] is the sentence break property value
       corresponding to [i]. *)
+
+  val indic_conjunct_break : Uchar.t -> int
+  (** [indic_conjunct_break u] is an integer that can be used with
+      {!indic_conjunct_break_of_int}. *)
+
+  val indic_conjunct_break_max : int
+  (** [indic_conjunct_break_max] is the maximal value returned by
+      {!val-indic_conjunct_break_of_int}. *)
+
+  val indic_conjunct_break_of_int : indic_conjunct_break array
+  (** [indic_conjunct_break.(i)] is the Indic conjunct break property
+      value corresponding to [i]. *)
 end

src/uucp_break_base.ml

@@ -115,6 +115,24 @@ let pp_sentence ppf v = Format.fprintf ppf "%s" begin match v with
   | `SE -> "SE" | `SP -> "SP" | `ST -> "ST" | `UP -> "UP" | `XX -> "XX"
   end
 
+(* Indic conjunct break *)
+
+type indic_conjunct_break =
+  [ `Consonant | `Extend | `Linker | `None ]
+
+let indic_conjunct_break_of_byte : indic_conjunct_break array =
+  [| `Consonant; `Extend; `Linker; `None |]
+
+let indic_conjunct_break_max = Array.length indic_conjunct_break_of_byte - 1
+
+let indic_conjunct_break_to_byte = function
+| `Consonant -> 0 | `Extend -> 1 | `Linker -> 2 | `None -> 3
+
+let pp_indic_conjunct_break ppf v = Format.fprintf ppf "%s" begin match v with
+  | `Consonant -> "Consonant" | `Extend -> "Extend" | `Linker -> "Linker"
+  | `None -> "None"
+  end
+
 (* East Asian width *)
 
 type east_asian_width = [ `A | `F | `H | `N | `Na | `W ]