├── BRZO
├── src
    ├── uucd.mllib
    ├── uucd.mli
    └── uucd.ml
├── doc
    ├── api.odocl
    └── index.mld
├── .merlin
├── .gitignore
├── _tags
├── pkg
    ├── META
    └── pkg.ml
├── DEVEL.md
├── LICENSE.md
├── README.md
├── test
    ├── test_uucd.ml
    └── example.ml
├── opam
├── CHANGES.md
└── B0.ml


/BRZO:
--------------------------------------------------------------------------------
1 | (srcs-x pkg)


--------------------------------------------------------------------------------
/src/uucd.mllib:
--------------------------------------------------------------------------------
1 | Uucd


--------------------------------------------------------------------------------
/doc/api.odocl:
--------------------------------------------------------------------------------
1 | Uucd
2 | 


--------------------------------------------------------------------------------
/.merlin:
--------------------------------------------------------------------------------
1 | PKG b0.kit xmlm
2 | B _b0/**
3 | 


--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
1 | _b0
2 | _build
3 | tmp
4 | *.install
5 | test/ucd.xml


--------------------------------------------------------------------------------
/_tags:
--------------------------------------------------------------------------------
1 | <**/*.{ml,mli}> : bin_annot, safe_string
2 | <src> : include
3 | <test> : include
4 | <src/uucd.{mli,ml}> : package(xmlm)
5 | <test/test.{byte,native}> : package(xmlm)
6 | <_b0> : -traverse


--------------------------------------------------------------------------------
/doc/index.mld:
--------------------------------------------------------------------------------
 1 | {0 Uucd {%html: <span class="version">%%VERSION%%</span>%}}
 2 | 
 3 | Uucd is an OCaml module to decode the data of the Unicode character
 4 | database from its XML representation.
 5 | 
 6 | {1:uucd Library [uucd]}
 7 | 
 8 | {!modules:
 9 | Uucd
10 | }
11 | 


--------------------------------------------------------------------------------
/pkg/META:
--------------------------------------------------------------------------------
1 | description = "Unicode character database decoder for OCaml"
2 | version = "%%VERSION_NUM%%"
3 | requires = "xmlm"
4 | archive(byte) = "uucd.cma"
5 | archive(native) = "uucd.cmxa"
6 | plugin(byte) = "uucd.cma"
7 | plugin(native) = "uucd.cmxs"
8 | exists_if = "uucd.cma uucd.cmxa"
9 | 


--------------------------------------------------------------------------------
/pkg/pkg.ml:
--------------------------------------------------------------------------------
 1 | #!/usr/bin/env ocaml
 2 | #use "topfind"
 3 | #require "topkg"
 4 | open Topkg
 5 | 
 6 | let distrib =
 7 |   (* FIXME OPAMv2, move this to an x-unicode-version field in the opam file. *)
 8 |   let watermarks = ("UNICODE_VERSION", `String "16.0.0") :: Pkg.watermarks in
 9 |   Pkg.distrib ~watermarks ()
10 | 
11 | let () =
12 |   Pkg.describe "uucd" ~distrib @@ fun c ->
13 |   Ok [ Pkg.mllib ~api:["Uucd"] "src/uucd.mllib"; ]
14 | 


--------------------------------------------------------------------------------
/DEVEL.md:
--------------------------------------------------------------------------------
 1 | # New Unicode release 
 2 | 
 3 | Bump the Unicode release number at the top of the `B0.ml` file and in
 4 | `pkg/pkg.ml`. Verify that everything is as expected with:
 5 | 
 6 |     b0 -- unicode-version
 7 | 
 8 | Download the latest xml unicode database to the `test/ucd.xml` file
 9 | which is ignored by git. If you have `curl` and `unzip` in your `PATH`
10 | you can simply issue:
11 | 
12 |     b0 -- download-ucdxml 
13 | 
14 | Then you should run
15 | 
16 |     b0 test
17 |    
18 | this will likely fail with a parse error. Adjust the parser and 
19 | datatypes with the help of: 
20 | 
21 |   <https://www.unicode.org/reports/tr42/proposed.html>
22 |   
23 |   
24 | 


--------------------------------------------------------------------------------
/LICENSE.md:
--------------------------------------------------------------------------------
 1 | Copyright (c) 2012 The uucd programmers
 2 | 
 3 | Permission to use, copy, modify, and/or distribute this software for any
 4 | purpose with or without fee is hereby granted, provided that the above
 5 | copyright notice and this permission notice appear in all copies.
 6 | 
 7 | THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
 8 | WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
 9 | MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
10 | ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
11 | WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
12 | ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
13 | OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
14 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | Uucd — Unicode character database decoder for OCaml
 2 | ===================================================
 3 | 
 4 | Uucd is an OCaml module to decode the data of the [Unicode character 
 5 | database][1] from its XML [representation][2]. It provides high-level 
 6 | (but not necessarily efficient) access to the data so that efficient 
 7 | representations can be extracted.
 8 | 
 9 | Uucd is made of a single module, depends on [Xmlm][xmlm] and is distributed
10 | under the ISC license.
11 | 
12 | [1]: http://www.unicode.org/reports/tr44/
13 | [2]: http://www.unicode.org/reports/tr42/
14 | [xmlm]: http://erratique.ch/software/xmlm 
15 | 
16 | Home page: <http://erratique.ch/software/uucd>  
17 | 
18 | ## Installation
19 | 
20 | Uucd can be installed with `opam`:
21 | 
22 |     opam install uucd
23 | 
24 | If you don't use `opam` consult the [`opam`](opam) file for build
25 | instructions and a complete specification of the dependencies.
26 | 
27 | ## Documentation
28 | 
29 | The documentation and API reference can be consulted [online][doc]
30 | or via `odig doc uucd`.
31 | 
32 | [doc]: http://erratique.ch/software/uucd/doc/
33 | 


--------------------------------------------------------------------------------
/test/test_uucd.ml:
--------------------------------------------------------------------------------
 1 | (*---------------------------------------------------------------------------
 2 |    Copyright (c) 2024 The uucd programmers. All rights reserved.
 3 |    SPDX-License-Identifier: ISC
 4 |   ---------------------------------------------------------------------------*)
 5 | 
 6 | open B0_std
 7 | open B0_testing
 8 | 
 9 | let test_decode =
10 |   Test.test "Uucd.decode" @@ fun file ->
11 |   Test.noraise ~__POS__ @@ fun () ->
12 |   let cwd = Os.Dir.cwd () |> Result.error_to_failure in
13 |   let inf = Fpath.(cwd // v "test/ucd.xml") in
14 |   let inf = Fpath.to_string inf in
15 |   try
16 |     In_channel.with_open_bin inf @@ fun ic ->
17 |     let d = Uucd.decoder (`Channel ic) in
18 |     match Uucd.decode d with
19 |     | `Ok db ->
20 |         let props = Uucd.Cpmap.find 0x0020 db.repertoire in
21 |         Test.(option T.any) (Uucd.find props Uucd.general_category) (Some `Zs)
22 |           ~__POS__
23 |     | `Error e ->
24 |         let (l0, c0), (l1, c1) = Uucd.decoded_range d in
25 |         Test.failstop ~__POS__ "%s:%d.%d-%d.%d: %s\n%!" inf l0 c0 l1 c1 e
26 |   with
27 |   | Sys_error e -> Test.failstop "%s" e ~__POS__
28 | 
29 | let main () = Test.main @@ fun () -> Test.autorun ()
30 | let () = if !Sys.interactive then () else exit (main ())
31 | 


--------------------------------------------------------------------------------
/test/example.ml:
--------------------------------------------------------------------------------
 1 | (*---------------------------------------------------------------------------
 2 |    Copyright (c) 2012 The uucd programmers. All rights reserved.
 3 |    SPDX-License-Identifier: CC0-1.0
 4 |   ---------------------------------------------------------------------------*)
 5 | 
 6 | let ucd_or_die inf =
 7 |   try
 8 |     let ic = if inf = "-" then stdin else open_in inf in
 9 |     let d = Uucd.decoder (`Channel ic) in
10 |     match Uucd.decode d with
11 |     | `Ok db -> db
12 |     | `Error e ->
13 |         let (l0, c0), (l1, c1) = Uucd.decoded_range d in
14 |         Printf.eprintf "%s:%d.%d-%d.%d: %s\n%!" inf l0 c0 l1 c1 e;
15 |         exit 1
16 |   with Sys_error e -> Printf.eprintf "%s\n%!" e; exit 1
17 | 
18 | let ucd_from_marshaled : string -> Uucd.t =
19 |   fun inf -> Marshal.from_channel (open_in inf)
20 | 
21 | let main () =
22 |   let usage = "test [ucd.xml]" in
23 |   let inf = ref None in
24 |   let anon_fun file = match !inf with
25 |   | Some _ -> raise (Arg.Bad ("Don't now what to do with " ^ file))
26 |   | None -> inf := Some file
27 |   in
28 |   Arg.parse [] anon_fun usage;
29 |   let inf = Option.value ~default:"-" !inf in
30 |   Marshal.to_channel stdout (ucd_or_die inf) []
31 | 
32 | let () = if !Sys.interactive then () else main ()
33 | 


--------------------------------------------------------------------------------
/opam:
--------------------------------------------------------------------------------
 1 | opam-version: "2.0"
 2 | name: "uucd"
 3 | synopsis: "Unicode character database decoder for OCaml"
 4 | description: """\
 5 | Uucd is an OCaml module to decode the data of the [Unicode character 
 6 | database][1] from its XML [representation][2]. It provides high-level 
 7 | (but not necessarily efficient) access to the data so that efficient 
 8 | representations can be extracted.
 9 | 
10 | Uucd is made of a single module, depends on [Xmlm][xmlm] and is distributed
11 | under the ISC license.
12 | 
13 | [1]: http://www.unicode.org/reports/tr44/
14 | [2]: http://www.unicode.org/reports/tr42/
15 | [xmlm]: http://erratique.ch/software/xmlm 
16 | 
17 | Home page: <http://erratique.ch/software/uucd>"""
18 | maintainer: "Daniel Bünzli <daniel.buenzl i@erratique.ch>"
19 | authors: "The uucd programmers"
20 | license: "ISC"
21 | tags: ["unicode" "database" "decoder" "org:erratique"]
22 | homepage: "https://erratique.ch/software/uucd"
23 | doc: "https://erratique.ch/software/uucd/doc/Uucd"
24 | bug-reports: "https://github.com/dbuenzli/uucd/issues"
25 | depends: [
26 |   "ocaml" {>= "4.08.0"}
27 |   "ocamlfind" {build}
28 |   "ocamlbuild" {build}
29 |   "topkg" {build & >= "1.1.0"}
30 |   "xmlm"
31 | ]
32 | build: ["ocaml" "pkg/pkg.ml" "build" "--dev-pkg" "%{dev}%"]
33 | dev-repo: "git+https://erratique.ch/repos/uucd.git"
34 | x-maintenance-intent: ["(latest)"]
35 | 


--------------------------------------------------------------------------------
/CHANGES.md:
--------------------------------------------------------------------------------
 1 | v17.0.0 2025-09-11 Zagreb
 2 | -------------------------
 3 | 
 4 | - Support for Unicode 17.0.0
 5 | 
 6 | v16.0.0 2024-09-11 Zagreb
 7 | -------------------------
 8 | 
 9 | - Support for Unicode 16.0.0
10 | 
11 | v15.1.0 2023-09-15 Zagreb
12 | -------------------------
13 | 
14 | - Support for Unicode 15.1.0
15 | 
16 | v15.0.0 2022-09-15 Zagreb
17 | -------------------------
18 | 
19 | - Support for Unicode 15.0.0
20 | 
21 | v14.0.0 2021-09-17 Zagreb
22 | -------------------------
23 | 
24 | - Support for Unicode 14.0.0
25 | 
26 | v13.0.0 2020-03-10 La Forclaz (VS)
27 | ----------------------------------
28 | 
29 | - Support for Unicode 13.0.0
30 | 
31 | v12.0.0 2019-03-07 La Forclaz (VS)
32 | ----------------------------------
33 | 
34 | - Support for Unicode 12.0.0
35 | 
36 | v11.0.0 2018-06-06 Lausanne
37 | ---------------------------
38 | 
39 | - Support for Unicode 11.0.0
40 | 
41 | v10.0.0 2017-06-20 Cambridge (UK)
42 | ---------------------------------
43 | 
44 | - Support for Unicode 10.0.0
45 | 
46 | v4.0.0 2016-06-26 Cambridge (UK)
47 | --------------------------------
48 | 
49 | - Updated for Unicode 9.0.0
50 | - Build depend on topkg.
51 | - Relicensed from BSD3 to ISC.
52 | 
53 | v3.0.0 2015-06-17 Cambridge (UK)
54 | --------------------------------
55 | 
56 | - Updated for Unicode 8.0.0
57 | 
58 | v2.0.0 2014-06-16 Cambridge (UK)
59 | --------------------------------
60 | 
61 | - Updated for Unicode 7.0.0
62 | 
63 | v1.0.0 2013-10-01 Lausanne
64 | --------------------------
65 | 
66 | - Updated for Unicode 6.3.0.
67 | - OPAM friendly workflow and drop OASIS support.
68 | 
69 | v0.9.2 2013-01-04 La Forclaz (VS)
70 | ---------------------------------
71 | 
72 | - Updated for Unicode 6.2.0.
73 | 
74 | v0.9.1 2013-01-04 La Forclaz (VS)
75 | ---------------------------------
76 | 
77 | - Fix Uucd.is_scalar_value always returning false.
78 | 
79 | v0.9.0 2012-09-07 Lausanne
80 | --------------------------
81 | 
82 | First release.
83 | 


--------------------------------------------------------------------------------
/B0.ml:
--------------------------------------------------------------------------------
 1 | open B0_kit.V000
 2 | open Result.Syntax
 3 | 
 4 | let unicode_version = 17, 0, 0, None (* Adjust on new releases *)
 5 | 
 6 | (* OCaml library names *)
 7 | 
 8 | let b0_std = B0_ocaml.libname "b0.std"
 9 | let xmlm = B0_ocaml.libname "xmlm"
10 | let uucd = B0_ocaml.libname "uucd"
11 | 
12 | (* Libraries *)
13 | 
14 | let uucd_lib =
15 |   let srcs = [ `Dir ~/"src" ] and requires = [ xmlm ] in
16 |   B0_ocaml.lib uucd ~doc:"Uucd library" ~srcs ~requires
17 | 
18 | (* Actions *)
19 | 
20 | let uc_base = "http://www.unicode.org/Public"
21 | 
22 | let download_ucdxml =
23 |   let doc = "Download the Unicode character database to test/ucd.xml" in
24 |   B0_unit.of_action "download-ucdxml" ~doc @@ fun env _ ~args:_ ->
25 |   let* unzip = B0_env.get_cmd env (Cmd.arg "unzip") in
26 |   let version = B0_version.to_string unicode_version in
27 |   let ucd_url = Fmt.str "%s/%s/ucdxml/ucd.all.grouped.zip" uc_base version in
28 |   let ucd_file = B0_env.in_scope_dir env ~/"test/ucd.xml" in
29 |   Result.join @@ Os.File.with_tmp_fd @@ fun tmpfile tmpfd ->
30 |   (Log.stdout @@ fun m ->
31 |    m "@[<v>Downloading %s@,to %a@]" ucd_url Fpath.pp ucd_file);
32 |   let* () = B0_action_kit.fetch_url env ucd_url tmpfile in
33 |   let stdout = Os.Cmd.out_file ~force:true ~make_path:true ucd_file in
34 |   Os.Cmd.run Cmd.(unzip % "-p" %% path tmpfile) ~stdout
35 | 
36 | let show_version =
37 |   B0_unit.of_action "unicode-version" ~doc:"Show supported unicode version" @@
38 |   fun _ _ ~args:_ ->
39 |   Ok (Log.stdout (fun m -> m "%s" (B0_version.to_string unicode_version)))
40 | 
41 | (* Tests *)
42 | 
43 | let test_uucd =
44 |   let srcs = [ `File ~/"test/test_uucd.ml" ] in
45 |   let meta =
46 |     B0_meta.(empty |> tag test |> tag run |> ~~ B0_unit.Action.cwd `Scope_dir)
47 |   in
48 |   let requires = [uucd; b0_std] in
49 |   B0_ocaml.exe "test_uucd" ~doc:"Test decoder" ~srcs ~requires ~meta
50 | 
51 | let example =
52 |   let srcs = [ `File ~/"test/example.ml" ] in
53 |   let meta = B0_meta.(empty |> tag test) in
54 |   B0_ocaml.exe "example" ~doc:"Sample code" ~srcs ~meta ~requires:[uucd]
55 | 
56 | (* Packs *)
57 | 
58 | let default =
59 |   let meta =
60 |     B0_meta.empty
61 |     |> ~~ B0_meta.authors ["The uucd programmers"]
62 |     |> ~~ B0_meta.maintainers ["Daniel Bünzli <daniel.buenzl i@erratique.ch>"]
63 |     |> ~~ B0_meta.homepage "https://erratique.ch/software/uucd"
64 |     |> ~~ B0_meta.online_doc "https://erratique.ch/software/uucd/doc/Uucd"
65 |     |> ~~ B0_meta.licenses ["ISC"]
66 |     |> ~~ B0_meta.repo "git+https://erratique.ch/repos/uucd.git"
67 |     |> ~~ B0_meta.issues "https://github.com/dbuenzli/uucd/issues"
68 |     |> ~~ B0_meta.description_tags
69 |       ["unicode"; "database"; "decoder"; "org:erratique"]
70 |     |> B0_meta.tag B0_opam.tag
71 |     |> ~~ B0_opam.build
72 |       {|[["ocaml" "pkg/pkg.ml" "build" "--dev-pkg" "%{dev}%"]]|}
73 |     |> ~~ B0_opam.depends
74 |       [ "ocaml", {|>= "4.08.0"|};
75 |         "ocamlfind", {|build|};
76 |         "ocamlbuild", {|build|};
77 |         "topkg", {|build & >= "1.1.0"|};
78 |         "xmlm", {||} ]
79 |   in
80 |   B0_pack.make "default" ~doc:"uucd package" ~meta ~locked:true @@
81 |   B0_unit.list ()
82 | 


--------------------------------------------------------------------------------
/src/uucd.mli:
--------------------------------------------------------------------------------
   1 | (*---------------------------------------------------------------------------
   2 |    Copyright (c) 2012 The uucd programmers. All rights reserved.
   3 |    SPDX-License-Identifier: ISC
   4 |   ---------------------------------------------------------------------------*)
   5 | 
   6 | (** Unicode character database decoder.
   7 | 
   8 |     [Uucd] decodes the data of the
   9 |     {{:http://www.unicode.org/reports/tr44}Unicode character database}
  10 |     from its XML representation. It provides high-level (but not
  11 |     necessarily efficient) access to the data so that efficient
  12 |     representations can be extracted.
  13 | 
  14 |     [Uucd] decodes the representation described in the Annex #42 of
  15 |     Unicode %%UNICODE_VERSION%%. Subsequent versions may be decoded as
  16 |     long as no new cases are introduced in parsed enumerated
  17 |     properties.
  18 | 
  19 |     Consult the {{!basics}basics}.
  20 | 
  21 |     {b Note.} All strings returned by the module are UTF-8 encoded.
  22 | 
  23 |     {e Unicode version %%UNICODE_VERSION%%}
  24 | 
  25 |     {3 References}
  26 |     {ul
  27 |     {- The Unicode Consortium.
  28 |     {e {{:http://www.unicode.org/versions/latest}The Unicode Standard}}.
  29 |     (latest version)}
  30 |     {- Mark Davis, Ken Whistler.
  31 |     {e {{:http://www.unicode.org/reports/tr44/}UAX #44 Unicode Character
  32 |     Database}}. (latest version)}
  33 |     {- Eric Muller.
  34 |     {e {{:http://www.unicode.org/reports/tr42/}UAX #42 Unicode Character
  35 |     Database in XML}}. (latest version)}} *)
  36 | 
  37 | (** {1:chars Code points} *)
  38 | 
  39 | type cp = int
  40 | (** The type for Unicode {{:http://unicode.org/glossary/#code_point}code
  41 |     points}, ranges from [0x0000] to [0x10_FFFF]. *)
  42 | 
  43 | val is_cp : int -> bool
  44 | (** [is_cp n] is [true] iff [n] a Unicode
  45 |     {{:http://unicode.org/glossary/#code_point}code
  46 |     point}. *)
  47 | 
  48 | val is_scalar_value : int -> bool
  49 | (** [is_scalar_value n] is [true] iff [n] is a Unicode
  50 |     {{:http://unicode.org/glossary/#Unicode_scalar_value}scalar value}. *)
  51 | 
  52 | (** Code point maps. *)
  53 | module Cpmap : Map.S with type key = cp
  54 | 
  55 | (** {1:props Properties}
  56 | 
  57 |     Properties are referenced by their name and property values by
  58 |     their
  59 |     {{:http://www.unicode.org/Public/UNIDATA/PropertyValueAliases.txt}
  60 |     abbreviated name}. To understand their semantics refer to the
  61 |     {{:http://www.unicode.org/versions/latest/}standard}. *)
  62 | 
  63 | type props
  64 | (** The type for sets of properties. *)
  65 | 
  66 | type 'a prop
  67 | (** The type for properties with property value of type ['a]. *)
  68 | 
  69 | val find : props -> 'a prop -> 'a option
  70 | (** [find ps p] is the value of property [p] in [ps], if any. *)
  71 | 
  72 | val unknown_prop : string * string -> string prop
  73 | (** [unknown_prop (ns, n)] is a property read from an XML attribute
  74 |     whose expanded name is [(ns, n)]. This can be used to access a
  75 |     property unknown to the module. *)
  76 | 
  77 | (** {2:nonunihan Non Unihan properties}
  78 | 
  79 |     In alphabetical order. *)
  80 | 
  81 | val age : [ `Version of int * int | `Unassigned ] prop
  82 | val alphabetic : bool prop
  83 | val ascii_hex_digit : bool prop
  84 | val bidi_class : [
  85 | | `AL
  86 | | `AN
  87 | | `B
  88 | | `BN
  89 | | `CS
  90 | | `EN
  91 | | `ES
  92 | | `ET
  93 | | `FSI
  94 | | `L
  95 | | `LRE
  96 | | `LRI
  97 | | `LRO
  98 | | `NSM
  99 | | `ON
 100 | | `PDF
 101 | | `PDI
 102 | | `R
 103 | | `RLE
 104 | | `RLI
 105 | | `RLO
 106 | | `S
 107 | | `WS
 108 | ] prop
 109 | 
 110 | val bidi_control : bool prop
 111 | val bidi_mirrored : bool prop
 112 | val bidi_mirroring_glyph : cp option prop
 113 | val bidi_paired_bracket : [ `Self | `Cp of cp ] prop
 114 | val bidi_paired_bracket_type : [ `O | `C | `N ] prop
 115 | val block : [
 116 | | `ASCII
 117 | | `Adlam
 118 | | `Aegean_Numbers
 119 | | `Ahom
 120 | | `Alchemical
 121 | | `Alphabetic_PF
 122 | | `Anatolian_Hieroglyphs
 123 | | `Ancient_Greek_Music
 124 | | `Ancient_Greek_Numbers
 125 | | `Ancient_Symbols
 126 | | `Arabic
 127 | | `Arabic_Ext_A
 128 | | `Arabic_Ext_B
 129 | | `Arabic_Ext_C
 130 | | `Arabic_Math
 131 | | `Arabic_PF_A
 132 | | `Arabic_PF_B
 133 | | `Arabic_Sup
 134 | | `Armenian
 135 | | `Arrows
 136 | | `Avestan
 137 | | `Balinese
 138 | | `Bamum
 139 | | `Bamum_Sup
 140 | | `Bassa_Vah
 141 | | `Batak
 142 | | `Bengali
 143 | | `Beria_Erfe
 144 | | `Bhaiksuki
 145 | | `Block_Elements
 146 | | `Bopomofo
 147 | | `Bopomofo_Ext
 148 | | `Box_Drawing
 149 | | `Brahmi
 150 | | `Braille
 151 | | `Buginese
 152 | | `Buhid
 153 | | `Byzantine_Music
 154 | | `CJK
 155 | | `CJK_Compat
 156 | | `CJK_Compat_Forms
 157 | | `CJK_Compat_Ideographs
 158 | | `CJK_Compat_Ideographs_Sup
 159 | | `CJK_Ext_A
 160 | | `CJK_Ext_B
 161 | | `CJK_Ext_C
 162 | | `CJK_Ext_D
 163 | | `CJK_Ext_E
 164 | | `CJK_Ext_F
 165 | | `CJK_Ext_G
 166 | | `CJK_Ext_H
 167 | | `CJK_Ext_I
 168 | | `CJK_Ext_J
 169 | | `CJK_Radicals_Sup
 170 | | `CJK_Strokes
 171 | | `CJK_Symbols
 172 | | `Carian
 173 | | `Caucasian_Albanian
 174 | | `Chakma
 175 | | `Cham
 176 | | `Cherokee
 177 | | `Cherokee_Sup
 178 | | `Chess_Symbols
 179 | | `Chorasmian
 180 | | `Compat_Jamo
 181 | | `Control_Pictures
 182 | | `Coptic
 183 | | `Coptic_Epact_Numbers
 184 | | `Counting_Rod
 185 | | `Cuneiform
 186 | | `Cuneiform_Numbers
 187 | | `Currency_Symbols
 188 | | `Cypriot_Syllabary
 189 | | `Cypro_Minoan
 190 | | `Cyrillic
 191 | | `Cyrillic_Ext_A
 192 | | `Cyrillic_Ext_B
 193 | | `Cyrillic_Ext_C
 194 | | `Cyrillic_Ext_D
 195 | | `Cyrillic_Sup
 196 | | `Deseret
 197 | | `Devanagari
 198 | | `Devanagari_Ext
 199 | | `Devanagari_Ext_A
 200 | | `Diacriticals
 201 | | `Diacriticals_Ext
 202 | | `Diacriticals_For_Symbols
 203 | | `Diacriticals_Sup
 204 | | `Dingbats
 205 | | `Dives_Akuru
 206 | | `Dogra
 207 | | `Domino
 208 | | `Duployan
 209 | | `Early_Dynastic_Cuneiform
 210 | | `Egyptian_Hieroglyph_Format_Controls
 211 | | `Egyptian_Hieroglyphs
 212 | | `Egyptian_Hieroglyphs_Ext_A
 213 | | `Elbasan
 214 | | `Elymaic
 215 | | `Emoticons
 216 | | `Enclosed_Alphanum
 217 | | `Enclosed_Alphanum_Sup
 218 | | `Enclosed_CJK
 219 | | `Enclosed_Ideographic_Sup
 220 | | `Ethiopic
 221 | | `Ethiopic_Ext
 222 | | `Ethiopic_Ext_A
 223 | | `Ethiopic_Ext_B
 224 | | `Ethiopic_Sup
 225 | | `Garay
 226 | | `Geometric_Shapes
 227 | | `Geometric_Shapes_Ext
 228 | | `Georgian
 229 | | `Georgian_Ext
 230 | | `Georgian_Sup
 231 | | `Glagolitic
 232 | | `Glagolitic_Sup
 233 | | `Gothic
 234 | | `Grantha
 235 | | `Greek
 236 | | `Greek_Ext
 237 | | `Gujarati
 238 | | `Gunjala_Gondi
 239 | | `Gurmukhi
 240 | | `Gurung_Khema
 241 | | `Half_And_Full_Forms
 242 | | `Half_Marks
 243 | | `Hangul
 244 | | `Hanifi_Rohingya
 245 | | `Hanunoo
 246 | | `Hatran
 247 | | `Hebrew
 248 | | `High_PU_Surrogates
 249 | | `High_Surrogates
 250 | | `Hiragana
 251 | | `IDC
 252 | | `IPA_Ext
 253 | | `Ideographic_Symbols
 254 | | `Imperial_Aramaic
 255 | | `Indic_Number_Forms
 256 | | `Indic_Siyaq_Numbers
 257 | | `Inscriptional_Pahlavi
 258 | | `Inscriptional_Parthian
 259 | | `Jamo
 260 | | `Jamo_Ext_A
 261 | | `Jamo_Ext_B
 262 | | `Javanese
 263 | | `Kaithi
 264 | | `Kaktovik_Numerals
 265 | | `Kana_Ext_A
 266 | | `Kana_Ext_B
 267 | | `Kana_Sup
 268 | | `Kanbun
 269 | | `Kangxi
 270 | | `Kannada
 271 | | `Katakana
 272 | | `Katakana_Ext
 273 | | `Kawi
 274 | | `Kayah_Li
 275 | | `Kharoshthi
 276 | | `Khitan_Small_Script
 277 | | `Khmer
 278 | | `Khmer_Symbols
 279 | | `Khojki
 280 | | `Khudawadi
 281 | | `Kirat_Rai
 282 | | `Lao
 283 | | `Latin_1_Sup
 284 | | `Latin_Ext_A
 285 | | `Latin_Ext_Additional
 286 | | `Latin_Ext_B
 287 | | `Latin_Ext_C
 288 | | `Latin_Ext_D
 289 | | `Latin_Ext_E
 290 | | `Latin_Ext_F
 291 | | `Latin_Ext_G
 292 | | `Lepcha
 293 | | `Letterlike_Symbols
 294 | | `Limbu
 295 | | `Linear_A
 296 | | `Linear_B_Ideograms
 297 | | `Linear_B_Syllabary
 298 | | `Lisu
 299 | | `Lisu_Sup
 300 | | `Low_Surrogates
 301 | | `Lycian
 302 | | `Lydian
 303 | | `Mahajani
 304 | | `Mahjong
 305 | | `Makasar
 306 | | `Malayalam
 307 | | `Mandaic
 308 | | `Manichaean
 309 | | `Marchen
 310 | | `Masaram_Gondi
 311 | | `Math_Alphanum
 312 | | `Math_Operators
 313 | | `Mayan_Numerals
 314 | | `Medefaidrin
 315 | | `Meetei_Mayek
 316 | | `Meetei_Mayek_Ext
 317 | | `Mende_Kikakui
 318 | | `Meroitic_Cursive
 319 | | `Meroitic_Hieroglyphs
 320 | | `Miao
 321 | | `Misc_Arrows
 322 | | `Misc_Math_Symbols_A
 323 | | `Misc_Math_Symbols_B
 324 | | `Misc_Pictographs
 325 | | `Misc_Symbols
 326 | | `Misc_Symbols_Sup
 327 | | `Misc_Technical
 328 | | `Modi
 329 | | `Modifier_Letters
 330 | | `Modifier_Tone_Letters
 331 | | `Mongolian
 332 | | `Mongolian_Sup
 333 | | `Mro
 334 | | `Multani
 335 | | `Music
 336 | | `Myanmar
 337 | | `Myanmar_Ext_A
 338 | | `Myanmar_Ext_B
 339 | | `Myanmar_Ext_C
 340 | | `NB
 341 | | `NKo
 342 | | `Nabataean
 343 | | `Nag_Mundari
 344 | | `Nandinagari
 345 | | `New_Tai_Lue
 346 | | `Newa
 347 | | `Number_Forms
 348 | | `Nushu
 349 | | `Nyiakeng_Puachue_Hmong
 350 | | `OCR
 351 | | `Ogham
 352 | | `Ol_Onal
 353 | | `Ol_Chiki
 354 | | `Old_Hungarian
 355 | | `Old_Italic
 356 | | `Old_North_Arabian
 357 | | `Old_Permic
 358 | | `Old_Persian
 359 | | `Old_Sogdian
 360 | | `Old_South_Arabian
 361 | | `Old_Turkic
 362 | | `Old_Uyghur
 363 | | `Oriya
 364 | | `Ornamental_Dingbats
 365 | | `Osage
 366 | | `Osmanya
 367 | | `Ottoman_Siyaq_Numbers
 368 | | `PUA
 369 | | `Pahawh_Hmong
 370 | | `Palmyrene
 371 | | `Pau_Cin_Hau
 372 | | `Phags_Pa
 373 | | `Phaistos
 374 | | `Phoenician
 375 | | `Phonetic_Ext
 376 | | `Phonetic_Ext_Sup
 377 | | `Playing_Cards
 378 | | `Psalter_Pahlavi
 379 | | `Punctuation
 380 | | `Rejang
 381 | | `Rumi
 382 | | `Runic
 383 | | `Samaritan
 384 | | `Saurashtra
 385 | | `Sharada
 386 | | `Sharada_Sup
 387 | | `Shavian
 388 | | `Shorthand_Format_Controls
 389 | | `Siddham
 390 | | `Sidetic
 391 | | `Sinhala
 392 | | `Sinhala_Archaic_Numbers
 393 | | `Small_Forms
 394 | | `Small_Kana_Ext
 395 | | `Sogdian
 396 | | `Sora_Sompeng
 397 | | `Soyombo
 398 | | `Specials
 399 | | `Sundanese
 400 | | `Sundanese_Sup
 401 | | `Sunuwar
 402 | | `Sup_Arrows_A
 403 | | `Sup_Arrows_B
 404 | | `Sup_Arrows_C
 405 | | `Sup_Math_Operators
 406 | | `Sup_PUA_A
 407 | | `Sup_PUA_B
 408 | | `Sup_Punctuation
 409 | | `Sup_Symbols_And_Pictographs
 410 | | `Super_And_Sub
 411 | | `Sutton_SignWriting
 412 | | `Syloti_Nagri
 413 | | `Symbols_And_Pictographs_Ext_A
 414 | | `Symbols_For_Legacy_Computing
 415 | | `Symbols_For_Legacy_Computing_Sup
 416 | | `Syriac
 417 | | `Syriac_Sup
 418 | | `Tagalog
 419 | | `Tagbanwa
 420 | | `Tags
 421 | | `Tai_Le
 422 | | `Tai_Tham
 423 | | `Tai_Viet
 424 | | `Tai_Xuan_Jing
 425 | | `Tai_Yo
 426 | | `Takri
 427 | | `Tamil
 428 | | `Tamil_Sup
 429 | | `Tangsa
 430 | | `Tangut
 431 | | `Tangut_Components
 432 | | `Tangut_Components_Sup
 433 | | `Tangut_Sup
 434 | | `Telugu
 435 | | `Thaana
 436 | | `Thai
 437 | | `Tibetan
 438 | | `Tifinagh
 439 | | `Tirhuta
 440 | | `Todhri
 441 | | `Tolong_Siki
 442 | | `Toto
 443 | | `Transport_And_Map
 444 | | `Tulu_Tigalari
 445 | | `UCAS
 446 | | `UCAS_Ext
 447 | | `UCAS_Ext_A
 448 | | `Ugaritic
 449 | | `VS
 450 | | `VS_Sup
 451 | | `Vai
 452 | | `Vedic_Ext
 453 | | `Vertical_Forms
 454 | | `Vithkuqi
 455 | | `Wancho
 456 | | `Warang_Citi
 457 | | `Yezidi
 458 | | `Yi_Radicals
 459 | | `Yi_Syllables
 460 | | `Yijing
 461 | | `Zanabazar_Square
 462 | | `Znamenny_Music
 463 | ] prop
 464 | 
 465 | val canonical_combining_class : int prop
 466 | val cased : bool prop
 467 | val case_folding : [`Self | `Cps of cp list ] prop
 468 | val case_ignorable : bool prop
 469 | val changes_when_casefolded : bool prop
 470 | val changes_when_casemapped : bool prop
 471 | val changes_when_lowercased : bool prop
 472 | val changes_when_nfkc_casefolded : bool prop
 473 | val changes_when_titlecased : bool prop
 474 | val changes_when_uppercased : bool prop
 475 | val composition_exclusion : bool prop
 476 | val dash : bool prop
 477 | val decomposition_mapping : [`Self | `Cps of cp list ] prop
 478 | val decomposition_type : [
 479 | | `Can
 480 | | `Com
 481 | | `Enc
 482 | | `Fin
 483 | | `Font
 484 | | `Fra
 485 | | `Init
 486 | | `Iso
 487 | | `Med
 488 | | `Nar
 489 | | `Nb
 490 | | `Sml
 491 | | `Sqr
 492 | | `Sub
 493 | | `Sup
 494 | | `Vert
 495 | | `Wide
 496 | | `None
 497 | ] prop
 498 | 
 499 | val default_ignorable_code_point : bool prop
 500 | val deprecated : bool prop
 501 | val diacritic : bool prop
 502 | val east_asian_width : [ `A | `F | `H | `N | `Na | `W ] prop
 503 | val emoji : bool prop
 504 | val emoji_presentation : bool prop
 505 | val emoji_modifier : bool prop
 506 | val emoji_modifier_base : bool prop
 507 | val emoji_component : bool prop
 508 | val equivalent_unified_ideograph : cp option prop
 509 | val extended_pictographic : bool prop
 510 | val extender : bool prop
 511 | val full_composition_exclusion : bool prop
 512 | val general_category : [
 513 | | `Lu
 514 | | `Ll
 515 | | `Lt
 516 | | `Lm
 517 | | `Lo
 518 | | `Mn
 519 | | `Mc
 520 | | `Me
 521 | | `Nd
 522 | | `Nl
 523 | | `No
 524 | | `Pc
 525 | | `Pd
 526 | | `Ps
 527 | | `Pe
 528 | | `Pi
 529 | | `Pf
 530 | | `Po
 531 | | `Sm
 532 | | `Sc
 533 | | `Sk
 534 | | `So
 535 | | `Zs
 536 | | `Zl
 537 | | `Zp
 538 | | `Cc
 539 | | `Cf
 540 | | `Cs
 541 | | `Co
 542 | | `Cn
 543 | ] prop
 544 | 
 545 | val grapheme_base : bool prop
 546 | val grapheme_cluster_break : [
 547 | | `CN
 548 | | `CR
 549 | | `EB
 550 | | `EBG
 551 | | `EM
 552 | | `EX
 553 | | `GAZ
 554 | | `L
 555 | | `LF
 556 | | `LV
 557 | | `LVT
 558 | | `PP
 559 | | `RI
 560 | | `SM
 561 | | `T
 562 | | `V
 563 | | `XX
 564 | | `ZWJ
 565 | ] prop
 566 | 
 567 | val grapheme_extend : bool prop
 568 | val hangul_syllable_type : [ `L | `LV | `LVT | `T | `V | `NA ] prop
 569 | val hex_digit : bool prop
 570 | val id_continue : bool prop
 571 | val id_compat_math_continue : bool prop
 572 | val id_compat_math_start : bool prop
 573 | val id_start : bool prop
 574 | val ideographic : bool prop
 575 | val ids_binary_operator : bool prop
 576 | val ids_trinary_operator : bool prop
 577 | val ids_unary_operator : bool prop
 578 | 
 579 | val indic_conjunct_break : [
 580 | | `Consonant
 581 | | `Extend
 582 | | `Linker
 583 | | `None ] prop
 584 | 
 585 | val indic_syllabic_category : [
 586 | | `Avagraha
 587 | | `Bindu
 588 | | `Brahmi_Joining_Number
 589 | | `Cantillation_Mark
 590 | | `Consonant
 591 | | `Consonant_Dead
 592 | | `Consonant_Final
 593 | | `Consonant_Head_Letter
 594 | | `Consonant_Initial_Postfixed
 595 | | `Consonant_Killer
 596 | | `Consonant_Medial
 597 | | `Consonant_Placeholder
 598 | | `Consonant_Preceding_Repha
 599 | | `Consonant_Prefixed
 600 | | `Consonant_Repha
 601 | | `Consonant_Subjoined
 602 | | `Consonant_Succeeding_Repha
 603 | | `Consonant_With_Stacker
 604 | | `Gemination_Mark
 605 | | `Invisible_Stacker
 606 | | `Joiner
 607 | | `Modifying_Letter
 608 | | `Non_Joiner
 609 | | `Nukta
 610 | | `Number
 611 | | `Number_Joiner
 612 | | `Other
 613 | | `Pure_Killer
 614 | | `Reordering_Killer
 615 | | `Register_Shifter
 616 | | `Syllable_Modifier
 617 | | `Tone_Letter
 618 | | `Tone_Mark
 619 | | `Virama
 620 | | `Visarga
 621 | | `Vowel
 622 | | `Vowel_Dependent
 623 | | `Vowel_Independent
 624 | ] prop
 625 | 
 626 | val indic_matra_category : [
 627 | | `Right
 628 | | `Left
 629 | | `Visual_Order_Left
 630 | | `Left_And_Right
 631 | | `Top
 632 | | `Bottom
 633 | | `Top_And_Bottom
 634 | | `Top_And_Right
 635 | | `Top_And_Left
 636 | | `Top_And_Left_And_Right
 637 | | `Bottom_And_Right
 638 | | `Top_And_Bottom_And_Right
 639 | | `Overstruck
 640 | | `Invisible
 641 | | `NA
 642 | ] prop
 643 | 
 644 | val indic_positional_category : [
 645 | | `Bottom
 646 | | `Bottom_And_Left
 647 | | `Bottom_And_Right
 648 | | `Invisible
 649 | | `Left
 650 | | `Left_And_Right
 651 | | `NA
 652 | | `Overstruck
 653 | | `Right
 654 | | `Top
 655 | | `Top_And_Bottom
 656 | | `Top_And_Bottom_And_Left
 657 | | `Top_And_Bottom_And_Right
 658 | | `Top_And_Left
 659 | | `Top_And_Left_And_Right
 660 | | `Top_And_Right
 661 | | `Visual_Order_Left
 662 | ] prop
 663 | 
 664 | val jamo_short_name : string prop
 665 | val join_control : bool prop
 666 | val joining_group : [
 667 | | `African_Feh
 668 | | `African_Noon
 669 | | `African_Qaf
 670 | | `Ain
 671 | | `Alaph
 672 | | `Alef
 673 | | `Alef_Maqsurah
 674 | | `Beh
 675 | | `Beth
 676 | | `Burushaski_Yeh_Barree
 677 | | `Dal
 678 | | `Dalath_Rish
 679 | | `E
 680 | | `Farsi_Yeh
 681 | | `Fe
 682 | | `Feh
 683 | | `Final_Semkath
 684 | | `Gaf
 685 | | `Gamal
 686 | | `Hah
 687 | | `Hanifi_Rohingya_Kinna_Ya
 688 | | `Hanifi_Rohingya_Pa
 689 | | `Hamza_On_Heh_Goal
 690 | | `He
 691 | | `Heh
 692 | | `Heh_Goal
 693 | | `Heth
 694 | | `Kaf
 695 | | `Kaph
 696 | | `Kashmiri_Yeh
 697 | | `Khaph
 698 | | `Knotted_Heh
 699 | | `Lam
 700 | | `Lamadh
 701 | | `Malayalam_Bha
 702 | | `Malayalam_Ja
 703 | | `Malayalam_Lla
 704 | | `Malayalam_Llla
 705 | | `Malayalam_Nga
 706 | | `Malayalam_Nna
 707 | | `Malayalam_Nnna
 708 | | `Malayalam_Nya
 709 | | `Malayalam_Ra
 710 | | `Malayalam_Ssa
 711 | | `Malayalam_Tta
 712 | | `Manichaean_Aleph
 713 | | `Manichaean_Ayin
 714 | | `Manichaean_Beth
 715 | | `Manichaean_Daleth
 716 | | `Manichaean_Dhamedh
 717 | | `Manichaean_Five
 718 | | `Manichaean_Gimel
 719 | | `Manichaean_Heth
 720 | | `Manichaean_Hundred
 721 | | `Manichaean_Kaph
 722 | | `Manichaean_Lamedh
 723 | | `Manichaean_Mem
 724 | | `Manichaean_Nun
 725 | | `Manichaean_One
 726 | | `Manichaean_Pe
 727 | | `Manichaean_Qoph
 728 | | `Manichaean_Resh
 729 | | `Manichaean_Sadhe
 730 | | `Manichaean_Samekh
 731 | | `Manichaean_Taw
 732 | | `Manichaean_Ten
 733 | | `Manichaean_Teth
 734 | | `Manichaean_Thamedh
 735 | | `Manichaean_Twenty
 736 | | `Manichaean_Waw
 737 | | `Manichaean_Yodh
 738 | | `Manichaean_Zayin
 739 | | `Meem
 740 | | `Mim
 741 | | `No_Joining_Group
 742 | | `Noon
 743 | | `Nun
 744 | | `Nya
 745 | | `Pe
 746 | | `Qaf
 747 | | `Qaph
 748 | | `Reh
 749 | | `Reversed_Pe
 750 | | `Rohingya_Yeh
 751 | | `Sad
 752 | | `Sadhe
 753 | | `Seen
 754 | | `Semkath
 755 | | `Shin
 756 | | `Straight_Waw
 757 | | `Swash_Kaf
 758 | | `Syriac_Waw
 759 | | `Tah
 760 | | `Taw
 761 | | `Teh_Marbuta
 762 | | `Teh_Marbuta_Goal
 763 | | `Teth
 764 | | `Thin_Noon
 765 | | `Thin_Yeh
 766 | | `Vertical_Tail
 767 | | `Waw
 768 | | `Yeh
 769 | | `Yeh_Barree
 770 | | `Yeh_With_Tail
 771 | | `Yudh
 772 | | `Yudh_He
 773 | | `Zain
 774 | | `Zhain
 775 | | `BAA
 776 | | `FA
 777 | | `HAA
 778 | | `HA_GOAL
 779 | | `HA
 780 | | `CAF
 781 | | `KNOTTED_HA
 782 | | `RA
 783 | | `SWASH_CAF
 784 | | `HAMZAH_ON_HA_GOAL
 785 | | `TAA_MARBUTAH
 786 | | `YA_BARREE
 787 | | `YA
 788 | | `ALEF_MAQSURAH
 789 | ] prop
 790 | 
 791 | val joining_type : [ `U | `C | `T | `D | `L | `R ] prop
 792 | val line_break : [
 793 | | `AI
 794 | | `AK
 795 | | `AL
 796 | | `AP
 797 | | `AS
 798 | | `B2
 799 | | `BA
 800 | | `BB
 801 | | `BK
 802 | | `CB
 803 | | `CJ
 804 | | `CL
 805 | | `CM
 806 | | `CP
 807 | | `CR
 808 | | `EX
 809 | | `GL
 810 | | `H2
 811 | | `H3
 812 | | `HH
 813 | | `HL
 814 | | `HY
 815 | | `ID
 816 | | `IN
 817 | | `IS
 818 | | `JL
 819 | | `JT
 820 | | `JV
 821 | | `LF
 822 | | `NL
 823 | | `NS
 824 | | `NU
 825 | | `OP
 826 | | `PO
 827 | | `PR
 828 | | `QU
 829 | | `RI
 830 | | `SA
 831 | | `SG
 832 | | `SP
 833 | | `SY
 834 | | `VF
 835 | | `VI
 836 | | `WJ
 837 | | `XX
 838 | | `ZW
 839 | | `EB
 840 | | `EM
 841 | | `ZWJ
 842 | ] prop
 843 | 
 844 | val logical_order_exception : bool prop
 845 | val lowercase : bool prop
 846 | val lowercase_mapping : [`Self | `Cps of cp list ] prop
 847 | val math : bool prop
 848 | val name : [`Pattern of string | `Name of string ] prop
 849 | (** In the [`Pattern] case occurrences of the character ['#']
 850 |     ([U+0023]) in the string must be replaced by the value of the code
 851 |     point as four to six uppercase hexadecimal digits (the minimal
 852 |     needed). E.g. the pattern ["CJK UNIFIED IDEOGRAPH-#"] associated
 853 |     to code point [U+3400] gives the name ["CJK UNIFIED IDEOGRAPH-3400"].  *)
 854 | 
 855 | val modifier_combining_mark : bool prop
 856 | 
 857 | val name_alias :
 858 |   (string * [`Abbreviation | `Alternate | `Control | `Correction | `Figment])
 859 | list prop
 860 | 
 861 | val nfc_quick_check : [ `True | `False | `Maybe ] prop
 862 | val nfd_quick_check : [ `True | `False | `Maybe ] prop
 863 | val nfkc_quick_check : [ `True | `False | `Maybe ] prop
 864 | val nfkc_casefold : [`Self | `Cps of cp list] prop
 865 | val nfkc_simple_casefold : [ `Self | `Cps of cp list ] prop
 866 | val nfkd_quick_check : [ `True | `False | `Maybe ] prop
 867 | val noncharacter_code_point : bool prop
 868 | val numeric_type : [ `None | `De | `Di | `Nu ] prop
 869 | val numeric_value :
 870 |   [ `NaN | `Nums of [`Frac of int * int | `Num of int64 ] list] prop
 871 | 
 872 | val other_alphabetic : bool prop
 873 | val other_default_ignorable_code_point : bool prop
 874 | val other_grapheme_extend : bool prop
 875 | val other_id_continue : bool prop
 876 | val other_id_start : bool prop
 877 | val other_lowercase : bool prop
 878 | val other_math : bool prop
 879 | val other_uppercase : bool prop
 880 | val pattern_syntax : bool prop
 881 | val pattern_white_space : bool prop
 882 | val prepended_concatenation_mark : bool prop
 883 | val quotation_mark : bool prop
 884 | val radical : bool prop
 885 | val regional_indicator : bool prop
 886 | 
 887 | type script = [
 888 | | `Adlm
 889 | | `Aghb
 890 | | `Ahom
 891 | | `Arab
 892 | | `Armi
 893 | | `Armn
 894 | | `Avst
 895 | | `Bali
 896 | | `Bamu
 897 | | `Bass
 898 | | `Batk
 899 | | `Beng
 900 | | `Berf
 901 | | `Bhks
 902 | | `Bopo
 903 | | `Brah
 904 | | `Brai
 905 | | `Bugi
 906 | | `Buhd
 907 | | `Cakm
 908 | | `Cans
 909 | | `Cari
 910 | | `Cham
 911 | | `Cher
 912 | | `Chrs
 913 | | `Copt
 914 | | `Cpmn
 915 | | `Cprt
 916 | | `Cyrl
 917 | | `Deva
 918 | | `Diak
 919 | | `Dogr
 920 | | `Dsrt
 921 | | `Dupl
 922 | | `Egyp
 923 | | `Elba
 924 | | `Elym
 925 | | `Ethi
 926 | | `Gara
 927 | | `Geor
 928 | | `Glag
 929 | | `Gong
 930 | | `Gonm
 931 | | `Goth
 932 | | `Gran
 933 | | `Grek
 934 | | `Gujr
 935 | | `Gukh
 936 | | `Guru
 937 | | `Hang
 938 | | `Hani
 939 | | `Hano
 940 | | `Hatr
 941 | | `Hebr
 942 | | `Hira
 943 | | `Hluw
 944 | | `Hmng
 945 | | `Hmnp
 946 | | `Hrkt
 947 | | `Hung
 948 | | `Ital
 949 | | `Java
 950 | | `Kali
 951 | | `Kana
 952 | | `Kawi
 953 | | `Khar
 954 | | `Khmr
 955 | | `Khoj
 956 | | `Knda
 957 | | `Krai
 958 | | `Kthi
 959 | | `Kits
 960 | | `Lana
 961 | | `Laoo
 962 | | `Latn
 963 | | `Lepc
 964 | | `Limb
 965 | | `Lina
 966 | | `Linb
 967 | | `Lisu
 968 | | `Lyci
 969 | | `Lydi
 970 | | `Mahj
 971 | | `Maka
 972 | | `Mand
 973 | | `Mani
 974 | | `Marc
 975 | | `Medf
 976 | | `Mend
 977 | | `Merc
 978 | | `Mero
 979 | | `Mlym
 980 | | `Modi
 981 | | `Mong
 982 | | `Mroo
 983 | | `Mtei
 984 | | `Mult
 985 | | `Mymr
 986 | | `Nagm
 987 | | `Nand
 988 | | `Narb
 989 | | `Nbat
 990 | | `Newa
 991 | | `Nkoo
 992 | | `Nshu
 993 | | `Ogam
 994 | | `Olck
 995 | | `Onao
 996 | | `Orkh
 997 | | `Orya
 998 | | `Osge
 999 | | `Osma
1000 | | `Ougr
1001 | | `Palm
1002 | | `Pauc
1003 | | `Perm
1004 | | `Phag
1005 | | `Phli
1006 | | `Phlp
1007 | | `Phnx
1008 | | `Plrd
1009 | | `Prti
1010 | | `Qaai
1011 | | `Rjng
1012 | | `Rohg
1013 | | `Runr
1014 | | `Samr
1015 | | `Sarb
1016 | | `Saur
1017 | | `Sgnw
1018 | | `Shaw
1019 | | `Shrd
1020 | | `Sidd
1021 | | `Sidt
1022 | | `Sind
1023 | | `Sinh
1024 | | `Sogd
1025 | | `Sogo
1026 | | `Sora
1027 | | `Soyo
1028 | | `Sund
1029 | | `Sunu
1030 | | `Sylo
1031 | | `Syrc
1032 | | `Tagb
1033 | | `Takr
1034 | | `Tale
1035 | | `Talu
1036 | | `Taml
1037 | | `Tang
1038 | | `Tavt
1039 | | `Tayo
1040 | | `Telu
1041 | | `Tfng
1042 | | `Tglg
1043 | | `Thaa
1044 | | `Thai
1045 | | `Tibt
1046 | | `Tirh
1047 | | `Tnsa
1048 | | `Todr
1049 | | `Tols
1050 | | `Toto
1051 | | `Tutg
1052 | | `Ugar
1053 | | `Vaii
1054 | | `Vith
1055 | | `Wara
1056 | | `Wcho
1057 | | `Xpeo
1058 | | `Xsux
1059 | | `Yezi
1060 | | `Yiii
1061 | | `Zanb
1062 | | `Zinh
1063 | | `Zyyy
1064 | | `Zzzz
1065 | ]
1066 | 
1067 | val script : script prop
1068 | val script_extensions : script list prop
1069 | 
1070 | val sentence_break : [
1071 | | `AT
1072 | | `CL
1073 | | `CR
1074 | | `EX
1075 | | `FO
1076 | | `LE
1077 | | `LF
1078 | | `LO
1079 | | `NU
1080 | | `SC
1081 | | `SE
1082 | | `SP
1083 | | `ST
1084 | | `UP
1085 | | `XX
1086 | ] prop
1087 | 
1088 | val simple_case_folding : [ `Self | `Cp of cp ] prop
1089 | val simple_lowercase_mapping : [ `Self | `Cp of cp ] prop
1090 | val simple_titlecase_mapping : [ `Self | `Cp of cp ] prop
1091 | val simple_uppercase_mapping : [ `Self | `Cp of cp ] prop
1092 | val soft_dotted : bool prop
1093 | val sterm : bool prop
1094 | val terminal_punctuation : bool prop
1095 | val titlecase_mapping : [`Self | `Cps of cp list ] prop
1096 | val uax_42_element : [ `Reserved | `Noncharacter | `Surrogate | `Char ] prop
1097 | (** Not normative, artefact of [Uucd]. Corresponds to the
1098 |     {{:http://www.unicode.org/reports/tr42/#w1aac13b9b1}XML element name}
1099 |     that describes the code point. *)
1100 | 
1101 | val unicode_1_name : string prop
1102 | val unified_ideograph : bool prop
1103 | val uppercase : bool prop
1104 | val uppercase_mapping : [`Self | `Cps of cp list ] prop
1105 | val variation_selector : bool prop
1106 | val vertical_orientation : [ `U | `R | `Tu | `Tr ] prop
1107 | val white_space : bool prop
1108 | val word_break : [
1109 | | `CR
1110 | | `DQ
1111 | | `EB
1112 | | `EBG
1113 | | `EM
1114 | | `EX
1115 | | `Extend
1116 | | `FO
1117 | | `GAZ
1118 | | `HL
1119 | | `KA
1120 | | `LE
1121 | | `LF
1122 | | `MB
1123 | | `ML
1124 | | `MN
1125 | | `NL
1126 | | `NU
1127 | | `RI
1128 | | `SQ
1129 | | `WSegSpace
1130 | | `XX
1131 | | `ZWJ
1132 | ] prop
1133 | 
1134 | val xid_continue : bool prop
1135 | val xid_start : bool prop
1136 | 
1137 | (** {2:unihan Unihan properties}
1138 | 
1139 |     In alphabetic order. For now unihan properties are always
1140 |     represented as strings. *)
1141 | 
1142 | val kAccountingNumeric : string prop
1143 | val kAlternateHanYu : string prop
1144 | val kAlternateJEF : string prop
1145 | val kAlternateKangXi : string prop
1146 | val kAlternateMorohashi : string prop
1147 | val kAlternateTotalStrokes : string prop
1148 | val kBigFive : string prop
1149 | val kCCCII : string prop
1150 | val kCNS1986 : string prop
1151 | val kCNS1992 : string prop
1152 | val kCangjie : string prop
1153 | val kCantonese : string prop
1154 | val kCheungBauer : string prop
1155 | val kCheungBauerIndex : string prop
1156 | val kCihaiT : string prop
1157 | val kCompatibilityVariant : string prop
1158 | val kCowles : string prop
1159 | val kDaeJaweon : string prop
1160 | val kDefinition : string prop
1161 | val kEACC : string prop
1162 | val kFanqie : string prop
1163 | val kFenn : string prop
1164 | val kFennIndex : string prop
1165 | val kFourCornerCode : string prop
1166 | val kFrequency : string prop
1167 | val kGB0 : string prop
1168 | val kGB1 : string prop
1169 | val kGB3 : string prop
1170 | val kGB5 : string prop
1171 | val kGB8 : string prop
1172 | val kGSR : string prop
1173 | val kGradeLevel : string prop
1174 | val kHDZRadBreak : string prop
1175 | val kHKGlyph : string prop
1176 | val kHKSCS : string prop
1177 | val kHanYu : string prop
1178 | val kHangul : string prop
1179 | val kHanyuPinlu : string prop
1180 | val kHanyuPinyin : string prop
1181 | val kIBMJapan : string prop
1182 | val kIICore : string prop
1183 | val kIRGDaeJaweon : string prop
1184 | val kIRGDaiKanwaZiten : string prop
1185 | val kIRGHanyuDaZidian : string prop
1186 | val kIRGKangXi : string prop
1187 | val kIRG_GSource : string prop
1188 | val kIRG_HSource : string prop
1189 | val kIRG_JSource : string prop
1190 | val kIRG_KPSource : string prop
1191 | val kIRG_KSource : string prop
1192 | val kIRG_MSource : string prop
1193 | val kIRG_SSource : string prop
1194 | val kIRG_TSource : string prop
1195 | val kIRG_USource : string prop
1196 | val kIRG_UKSource : string prop
1197 | val kIRG_VSource : string prop
1198 | val kJapanese : string prop
1199 | val kJapaneseKun : string prop
1200 | val kJapaneseOn : string prop
1201 | val kJHJ : string prop
1202 | val kJIS0213 : string prop
1203 | val kJinmeiyoKanji : string prop
1204 | val kJis0 : string prop
1205 | val kJis1 : string prop
1206 | val kJoyoKanji : string prop
1207 | val kKPS0 : string prop
1208 | val kKPS1 : string prop
1209 | val kKSC0 : string prop
1210 | val kKSC1 : string prop
1211 | val kKangXi : string prop
1212 | val kKarlgren : string prop
1213 | val kKorean : string prop
1214 | val kKoreanEducationHanja : string prop
1215 | val kKoreanName : string prop
1216 | val kLau : string prop
1217 | val kMainlandTelegraph : string prop
1218 | val kMandarin : string prop
1219 | val kMatthews : string prop
1220 | val kMeyerWempe : string prop
1221 | val kMojiJoho : string prop
1222 | val kMorohashi : string prop
1223 | val kNelson : string prop
1224 | val kNSHU_DubenSrc : string prop
1225 | val kNSHU_Reading : string prop
1226 | val kOtherNumeric : string prop
1227 | val kPhonetic : string prop
1228 | val kPrimaryNumeric : string prop
1229 | val kPseudoGB1 : string prop
1230 | val kRSAdobe_Japan1_6 : string prop
1231 | val kRSJapanese : string prop
1232 | val kRSKanWa : string prop
1233 | val kRSKangXi : string prop
1234 | val kRSKorean : string prop
1235 | val kRSMerged : string prop
1236 | val kRSUnicode : string prop
1237 | val kSBGY : string prop
1238 | val kSemanticVariant : string prop
1239 | val kSimplifiedVariant : string prop
1240 | val kSMSZD2003Index : string prop
1241 | val kSMSZD2003Readings : string prop
1242 | val kSpecializedSemanticVariant : string prop
1243 | val kSpoofingVariant : string prop
1244 | val kStrange : string prop
1245 | val kUnihanCore2020 : string prop
1246 | val kTGH : string prop
1247 | val kTGHZ2013 : string prop
1248 | val kTGT_MergedSrc : string prop
1249 | val kTGT_RSUnicode : string prop
1250 | val kTaiwanTelegraph : string prop
1251 | val kTang : string prop
1252 | val kTayNumeric : string prop
1253 | val kTotalStrokes : string prop
1254 | val kTraditionalVariant : string prop
1255 | val kVietnamese : string prop
1256 | val kVietnameseNumeric : string prop
1257 | val kWubi : string prop
1258 | val kXHC1983 : string prop
1259 | val kZhuang : string prop
1260 | val kXerox : string prop
1261 | val kZhuangNumeric : string prop
1262 | val kZVariant : string prop
1263 | 
1264 | (** {1:unikemet Unikemet properties} *)
1265 | 
1266 | val kEH_Cat : string prop
1267 | val kEH_Core : string prop
1268 | val kEH_Desc : string prop
1269 | val kEH_Func : string prop
1270 | val kEH_FVal : string prop
1271 | val kEH_UniK : string prop
1272 | val kEH_JSesh : string prop
1273 | val kEH_HG : string prop
1274 | val kEH_IFAO : string prop
1275 | val kEH_NoMirror : bool prop
1276 | val kEH_NoRotate : bool prop
1277 | val kEH_AltSeq : string prop
1278 | 
1279 | (** {1:db Unicode character databases} *)
1280 | 
1281 | type block = (cp * cp) * string
1282 | (** The type for blocks. Code point range, name of the block. *)
1283 | 
1284 | type named_sequence = string * cp list
1285 | (** The type for named sequences. Sequence name, code point sequence. *)
1286 | 
1287 | type standardized_variant =
1288 |     cp list * string * [ `Isolate | `Initial | `Medial | `Final ] list
1289 | (** The type for standarized variants. Code point sequence,
1290 |     description, when. *)
1291 | 
1292 | type cjk_radical = string * cp * cp
1293 | (** The type for CJK radicals. Radical number, CJK radical character,
1294 |     CJK unified ideograph. *)
1295 | 
1296 | type do_not_emit = { instead_of : cp list; use : cp list; because : string; }
1297 | (** The type for do not emit character sequences. *)
1298 | 
1299 | type t =
1300 |   { description : string;
1301 |     repertoire : props Cpmap.t;
1302 |     blocks : block list;
1303 |     named_sequences : named_sequence list;
1304 |     provisional_named_sequences : named_sequence list;
1305 |     standardized_variants : standardized_variant list;
1306 |     cjk_radicals : cjk_radical list;
1307 |     do_not_emit : do_not_emit list
1308 | }
1309 | (** The type for Unicode character databases.
1310 | 
1311 |     {b Note.} Absence of an optional top-level field in the database
1312 |     is denoted by the neutral element of its type (empty string, empty
1313 |     list, {!Cpmap.empty}).  This means that the module doesn't
1314 |     distinguish between absence of a field and presence of the field
1315 |     with empty data (but incurs no problems in this context). *)
1316 | 
1317 | val cp_prop : t -> cp -> 'a prop -> 'a option
1318 | (** [cp_prop ucd cp p] is the property [p] of the code point [cp]
1319 |     in [db]'s repertoire, if [p] is in the repertoire and the property
1320 |     exists for [cp]. *)
1321 | 
1322 | (** {1:decoder Decode} *)
1323 | 
1324 | type src = [ `Channel of in_channel | `String of string ]
1325 | (** The type for input sources. *)
1326 | 
1327 | type decoder
1328 | (** The type for Unicode character database decoders. *)
1329 | 
1330 | val decoder : [< src] -> decoder
1331 | (** [decoder src] is a decoder that inputs from [src]. *)
1332 | 
1333 | val decode : decoder -> [`Ok of t | `Error of string ]
1334 | (** [decode d] decodes a database from [d] or returns an error. *)
1335 | 
1336 | val decoded_range : decoder -> (int * int) * (int * int)
1337 | (** [decoded_range d] is the range of characters spanning the [`Error]
1338 |     decoded by [d]. A pair of line and column numbers respectively one and
1339 |     zero based. *)
1340 | 
1341 | (** {1:basics Basics}
1342 | 
1343 |     The database and subsets of it for Unicode %%UNICODE_VERSION%% are
1344 |     available
1345 |     {{:http://www.unicode.org/Public/%%UNICODE_VERSION%%/ucdxml/}here}.
1346 |     Databases with groups should be preferred, they maximize value
1347 |     sharing and improve parsing performance.
1348 | 
1349 |     A database is decoded as follows:
1350 | {[
1351 | let ucd_or_die inf = try
1352 |   let ic = if inf = "-" then stdin else open_in inf in
1353 |   let d = Uucd.decoder (`Channel ic) in
1354 |   match Uucd.decode d with
1355 |   | `Ok db -> db
1356 |   | `Error e ->
1357 |     let (l0, c0), (l1, c1) = Uucd.decoded_range d in
1358 |     Printf.eprintf "%s:%d.%d-%d.%d: %s\n%!" inf l0 c0 l1 c1 e;
1359 |     exit 1
1360 | with Sys_error e -> Printf.eprintf "%s\n%!" e; exit 1
1361 | 
1362 | let ucd = ucd_or_die "/tmp/ucd.all.grouped.xml"
1363 | ]}
1364 |     The convenience function {!cp_prop} can be used to query
1365 |     the property of a given code point. For example the
1366 |     {{!general_category}general category} of [U+1F42B]
1367 |     is given by:
1368 | {[
1369 | let u_1F42B_gc = Uucd.cp_prop ucd 0x1F42B Uucd.general_category
1370 | ]}
1371 | *)
1372 | 


--------------------------------------------------------------------------------
/src/uucd.ml:
--------------------------------------------------------------------------------
   1 | (*---------------------------------------------------------------------------
   2 |    Copyright (c) 2012 The uucd programmers. All rights reserved.
   3 |    SPDX-License-Identifier: ISC
   4 |   ---------------------------------------------------------------------------*)
   5 | 
   6 | let str = Printf.sprintf
   7 | let str_of_name (u,l) = str "{%s}%s" u l
   8 | let split_string s sep =
   9 |   let rec split accum j =
  10 |     let i = try (String.rindex_from s j sep) with Not_found -> -1 in
  11 |     if (i = -1) then
  12 |       let p = String.sub s 0 (j + 1) in
  13 |       if p <> "" then p :: accum else accum
  14 |     else
  15 |     let p = String.sub s (i + 1) (j - i) in
  16 |     let accum' = if p <> "" then p :: accum else accum in
  17 |     split accum' (i - 1)
  18 |   in
  19 |   split [] (String.length s - 1)
  20 | 
  21 | (* Error messages *)
  22 | 
  23 | let err s = failwith s
  24 | let err_data = "character data not allowed here"
  25 | let err_exp_el_end = "expected end of element"
  26 | let err_exp_data = "expected character data"
  27 | let err_wf = "document not well formed"
  28 | let err_dup n = str "duplicate element (%s)" (str_of_name n)
  29 | let err_miss_att n = str "missing attribute (%s)" n
  30 | let err_att_val v = str "invalid attribute value (\"%s\")" v
  31 | let err_invalid_cp v = str "invalid code point (\"%s\")" v
  32 | let err_empty_cps = "empty code point sequence"
  33 | let err_exp_ucd fnd = str "expected ucd element found %s" (str_of_name fnd)
  34 | let err_invalid_cp_spec = str "invalid code point specification"
  35 | let err_invalid_name_alias_spec = str "invalid name alias specification"
  36 | 
  37 | (* Code points *)
  38 | 
  39 | module Cp = struct
  40 |   type t = int
  41 |   let compare : int -> int -> int = compare
  42 | end
  43 | 
  44 | type cp = Cp.t
  45 | 
  46 | let is_cp i = 0x0000 <= i && i <= 0x10_FFFF
  47 | let is_scalar_value i =
  48 |   (0x0000 <= i && i <= 0xD7FF) || (0xE000 <= i && i <= 0x10FFFF)
  49 | 
  50 | let cp_of_string v =                           (* parses a code point value. *)
  51 |   let is_hex c = (0x30 <= c && c <= 0x39) || (0x41 <= c && c <= 0x46) in
  52 |   let cp = ref 0 in
  53 |   for k = 0 to (String.length v) - 1 do
  54 |     let c = Char.code v.[k] in
  55 |     if not (is_hex c) then err (err_invalid_cp v) else
  56 |     cp := !cp * 16 + (if c <= 0x39 then c - 48 else c - 55)
  57 |   done;
  58 |   if is_cp !cp then !cp else err (err_invalid_cp v)
  59 | 
  60 | let cps_of_string ?(empty = false) v = (* parses a code point sequence value. *)
  61 |   if (v = "") then (if empty then [] else err err_empty_cps) else
  62 |   List.map cp_of_string (split_string v ' ')
  63 | 
  64 | module Cpmap = Map.Make (Cp)
  65 | 
  66 | (* Properties *)
  67 | 
  68 | type key =                            (* the type for property keys (names). *)
  69 | | Age
  70 | | Alphabetic
  71 | | Ascii_hex_digit
  72 | | Bidi_class
  73 | | Bidi_control
  74 | | Bidi_mirrored
  75 | | Bidi_mirroring_glyph
  76 | | Bidi_paired_bracket
  77 | | Bidi_paired_bracket_type
  78 | | Block
  79 | | Canonical_combining_class
  80 | | Cased
  81 | | Case_folding
  82 | | Case_ignorable
  83 | | Changes_when_casefolded
  84 | | Changes_when_casemapped
  85 | | Changes_when_lowercased
  86 | | Changes_when_nfkc_casefolded
  87 | | Changes_when_titlecased
  88 | | Changes_when_uppercased
  89 | | Composition_exclusion
  90 | | Dash
  91 | | Decomposition_mapping
  92 | | Decomposition_type
  93 | | Default_ignorable_code_point
  94 | | Deprecated
  95 | | Diacritic
  96 | | East_asian_width
  97 | | Emoji
  98 | | Emoji_presentation
  99 | | Emoji_modifier
 100 | | Emoji_modifier_base
 101 | | Emoji_component
 102 | | Equivalent_unified_ideograph
 103 | | Extender
 104 | | Extended_pictographic
 105 | | Full_composition_exclusion
 106 | | General_category
 107 | | Grapheme_base
 108 | | Grapheme_cluster_break
 109 | | Grapheme_extend
 110 | | Hangul_syllable_type
 111 | | Hex_digit
 112 | | Id_continue
 113 | | Id_compat_math_continue
 114 | | Id_compat_math_start
 115 | | Id_start
 116 | | Ideographic
 117 | | Ids_binary_operator
 118 | | Ids_trinary_operator
 119 | | Ids_unary_operator
 120 | | Indic_conjunct_break
 121 | | Indic_syllabic_category
 122 | | Indic_matra_category
 123 | | Indic_positional_category
 124 | | Jamo_short_name
 125 | | Join_control
 126 | | Joining_group
 127 | | Joining_type
 128 | | Line_break
 129 | | Logical_order_exception
 130 | | Lowercase
 131 | | Lowercase_mapping
 132 | | Math
 133 | | Modifier_combining_mark
 134 | | Name
 135 | | Name_alias
 136 | | Nfc_quick_check
 137 | | Nfd_quick_check
 138 | | Nfkc_quick_check
 139 | | Nfkc_casefold
 140 | | Nfkc_simple_casefold
 141 | | Nfkd_quick_check
 142 | | Noncharacter_code_point
 143 | | Numeric_type
 144 | | Numeric_value
 145 | | Other_alphabetic
 146 | | Other_default_ignorable_code_point
 147 | | Other_grapheme_extend
 148 | | Other_id_continue
 149 | | Other_id_start
 150 | | Other_lowercase
 151 | | Other_math
 152 | | Other_uppercase
 153 | | Pattern_syntax
 154 | | Pattern_white_space
 155 | | Prepended_concatenation_mark
 156 | | Quotation_mark
 157 | | Radical
 158 | | Regional_indicator
 159 | | Script
 160 | | Script_extensions
 161 | | Sentence_break
 162 | | Simple_case_folding
 163 | | Simple_lowercase_mapping
 164 | | Simple_titlecase_mapping
 165 | | Simple_uppercase_mapping
 166 | | Soft_dotted
 167 | | Sterm
 168 | | Terminal_punctuation
 169 | | Titlecase_mapping
 170 | | UAX_42_element
 171 | | Unicode_1_name
 172 | | Unified_ideograph
 173 | | Uppercase
 174 | | Uppercase_mapping
 175 | | Variation_selector
 176 | | Vertical_orientation
 177 | | White_space
 178 | | Word_break
 179 | | Xid_continue
 180 | | Xid_start
 181 | (* Unihan *)
 182 | | KAccountingNumeric
 183 | | KAlternateHanYu
 184 | | KAlternateJEF
 185 | | KAlternateKangXi
 186 | | KAlternateMorohashi
 187 | | KAlternateTotalStrokes
 188 | | KBigFive
 189 | | KCCCII
 190 | | KCNS1986
 191 | | KCNS1992
 192 | | KCangjie
 193 | | KCantonese
 194 | | KCheungBauer
 195 | | KCheungBauerIndex
 196 | | KCihaiT
 197 | | KCompatibilityVariant
 198 | | KCowles
 199 | | KDaeJaweon
 200 | | KDefinition
 201 | | KEACC
 202 | | KFanqie
 203 | | KFenn
 204 | | KFennIndex
 205 | | KFourCornerCode
 206 | | KFrequency
 207 | | KGB0
 208 | | KGB1
 209 | | KGB3
 210 | | KGB5
 211 | | KGB8
 212 | | KGSR
 213 | | KGradeLevel
 214 | | KHDZRadBreak
 215 | | KHKGlyph
 216 | | KHKSCS
 217 | | KHanYu
 218 | | KHangul
 219 | | KHanyuPinlu
 220 | | KHanyuPinyin
 221 | | KIBMJapan
 222 | | KIICore
 223 | | KIRGDaeJaweon
 224 | | KIRGDaiKanwaZiten
 225 | | KIRGHanyuDaZidian
 226 | | KIRGKangXi
 227 | | KIRG_GSource
 228 | | KIRG_HSource
 229 | | KIRG_JSource
 230 | | KIRG_KPSource
 231 | | KIRG_KSource
 232 | | KIRG_MSource
 233 | | KIRG_SSource
 234 | | KIRG_TSource
 235 | | KIRG_USource
 236 | | KIRG_UKSource
 237 | | KIRG_VSource
 238 | | KJapanese
 239 | | KJHJ
 240 | | KJIS0213
 241 | | KJapaneseKun
 242 | | KJapaneseOn
 243 | | KJinmeiyoKanji
 244 | | KJis0
 245 | | KJis1
 246 | | KJoyoKanji
 247 | | KKPS0
 248 | | KKPS1
 249 | | KKSC0
 250 | | KKSC1
 251 | | KKangXi
 252 | | KKarlgren
 253 | | KKorean
 254 | | KKoreanEducationHanja
 255 | | KKoreanName
 256 | | KLau
 257 | | KMainlandTelegraph
 258 | | KMandarin
 259 | | KMatthews
 260 | | KMeyerWempe
 261 | | KMojiJoho
 262 | | KMorohashi
 263 | | KNelson
 264 | | KNSHU_DubenSrc
 265 | | KNSHU_Reading
 266 | | KOtherNumeric
 267 | | KPhonetic
 268 | | KPrimaryNumeric
 269 | | KPseudoGB1
 270 | | KRSAdobe_Japan1_6
 271 | | KRSJapanese
 272 | | KRSKanWa
 273 | | KRSKangXi
 274 | | KRSKorean
 275 | | KRSMerged
 276 | | KRSUnicode
 277 | | KSBGY
 278 | | KSemanticVariant
 279 | | KSimplifiedVariant
 280 | | KSMSZD2003Index
 281 | | KSMSZD2003Readings
 282 | | KSpecializedSemanticVariant
 283 | | KSpoofingVariant
 284 | | KStrange
 285 | | KTGH
 286 | | KTGHZ2013
 287 | | KTGT_MergedSrc
 288 | | KTGT_RSUnicode
 289 | | KTaiwanTelegraph
 290 | | KTang
 291 | | KTayNumeric
 292 | | KTotalStrokes
 293 | | KTraditionalVariant
 294 | | KUnihanCore2020
 295 | | KVietnamese
 296 | | KVietnameseNumeric
 297 | | KWubi
 298 | | KXHC1983
 299 | | KXerox
 300 | | KZhuang
 301 | | KZhuangNumeric
 302 | | KZVariant
 303 | (* Unikemet *)
 304 | | KEH_Cat
 305 | | KEH_Core
 306 | | KEH_Desc
 307 | | KEH_Func
 308 | | KEH_FVal
 309 | | KEH_UniK
 310 | | KEH_JSesh
 311 | | KEH_HG
 312 | | KEH_IFAO
 313 | | KEH_NoMirror
 314 | | KEH_NoRotate
 315 | | KEH_AltSeq
 316 | | Other of (string * string)                           (* expanded XML name. *)
 317 | 
 318 | type script = [
 319 | | `Adlm
 320 | | `Aghb
 321 | | `Ahom
 322 | | `Arab
 323 | | `Armi
 324 | | `Armn
 325 | | `Avst
 326 | | `Bali
 327 | | `Bamu
 328 | | `Bass
 329 | | `Batk
 330 | | `Beng
 331 | | `Berf
 332 | | `Bhks
 333 | | `Bopo
 334 | | `Brah
 335 | | `Brai
 336 | | `Bugi
 337 | | `Buhd
 338 | | `Cakm
 339 | | `Cans
 340 | | `Cari
 341 | | `Cham
 342 | | `Cher
 343 | | `Chrs
 344 | | `Copt
 345 | | `Cpmn
 346 | | `Cprt
 347 | | `Cyrl
 348 | | `Deva
 349 | | `Diak
 350 | | `Dogr
 351 | | `Dsrt
 352 | | `Dupl
 353 | | `Egyp
 354 | | `Elba
 355 | | `Elym
 356 | | `Ethi
 357 | | `Gara
 358 | | `Geor
 359 | | `Glag
 360 | | `Gong
 361 | | `Gonm
 362 | | `Goth
 363 | | `Gran
 364 | | `Grek
 365 | | `Gujr
 366 | | `Gukh
 367 | | `Guru
 368 | | `Hang
 369 | | `Hani
 370 | | `Hano
 371 | | `Hatr
 372 | | `Hebr
 373 | | `Hira
 374 | | `Hluw
 375 | | `Hmng
 376 | | `Hmnp
 377 | | `Hrkt
 378 | | `Hung
 379 | | `Ital
 380 | | `Java
 381 | | `Kali
 382 | | `Kana
 383 | | `Kawi
 384 | | `Khar
 385 | | `Khmr
 386 | | `Khoj
 387 | | `Knda
 388 | | `Krai
 389 | | `Kthi
 390 | | `Kits
 391 | | `Lana
 392 | | `Laoo
 393 | | `Latn
 394 | | `Lepc
 395 | | `Limb
 396 | | `Lina
 397 | | `Linb
 398 | | `Lisu
 399 | | `Lyci
 400 | | `Lydi
 401 | | `Mahj
 402 | | `Maka
 403 | | `Mand
 404 | | `Mani
 405 | | `Marc
 406 | | `Medf
 407 | | `Mend
 408 | | `Merc
 409 | | `Mero
 410 | | `Mlym
 411 | | `Modi
 412 | | `Mong
 413 | | `Mroo
 414 | | `Mtei
 415 | | `Mult
 416 | | `Mymr
 417 | | `Nagm
 418 | | `Nand
 419 | | `Narb
 420 | | `Nbat
 421 | | `Newa
 422 | | `Nkoo
 423 | | `Nshu
 424 | | `Ogam
 425 | | `Olck
 426 | | `Onao
 427 | | `Orkh
 428 | | `Orya
 429 | | `Osge
 430 | | `Osma
 431 | | `Ougr
 432 | | `Palm
 433 | | `Pauc
 434 | | `Perm
 435 | | `Phag
 436 | | `Phli
 437 | | `Phlp
 438 | | `Phnx
 439 | | `Plrd
 440 | | `Prti
 441 | | `Qaai
 442 | | `Rjng
 443 | | `Rohg
 444 | | `Runr
 445 | | `Samr
 446 | | `Sarb
 447 | | `Saur
 448 | | `Sgnw
 449 | | `Shaw
 450 | | `Shrd
 451 | | `Sidd
 452 | | `Sidt
 453 | | `Sind
 454 | | `Sinh
 455 | | `Sogd
 456 | | `Sogo
 457 | | `Sora
 458 | | `Soyo
 459 | | `Sund
 460 | | `Sunu
 461 | | `Sylo
 462 | | `Syrc
 463 | | `Tagb
 464 | | `Takr
 465 | | `Tale
 466 | | `Talu
 467 | | `Taml
 468 | | `Tang
 469 | | `Tavt
 470 | | `Tayo
 471 | | `Telu
 472 | | `Tfng
 473 | | `Tglg
 474 | | `Thaa
 475 | | `Thai
 476 | | `Tibt
 477 | | `Tirh
 478 | | `Tnsa
 479 | | `Todr
 480 | | `Tols
 481 | | `Toto
 482 | | `Tutg
 483 | | `Ugar
 484 | | `Vaii
 485 | | `Vith
 486 | | `Wara
 487 | | `Wcho
 488 | | `Xpeo
 489 | | `Xsux
 490 | | `Yezi
 491 | | `Yiii
 492 | | `Zanb
 493 | | `Zinh
 494 | | `Zyyy
 495 | | `Zzzz
 496 | ]
 497 | 
 498 | type block_prop = [
 499 | | `ASCII
 500 | | `Adlam
 501 | | `Aegean_Numbers
 502 | | `Ahom
 503 | | `Alchemical
 504 | | `Alphabetic_PF
 505 | | `Anatolian_Hieroglyphs
 506 | | `Ancient_Greek_Music
 507 | | `Ancient_Greek_Numbers
 508 | | `Ancient_Symbols
 509 | | `Arabic
 510 | | `Arabic_Ext_A
 511 | | `Arabic_Ext_B
 512 | | `Arabic_Ext_C
 513 | | `Arabic_Math
 514 | | `Arabic_PF_A
 515 | | `Arabic_PF_B
 516 | | `Arabic_Sup
 517 | | `Armenian
 518 | | `Arrows
 519 | | `Avestan
 520 | | `Balinese
 521 | | `Bamum
 522 | | `Bamum_Sup
 523 | | `Bassa_Vah
 524 | | `Batak
 525 | | `Bengali
 526 | | `Beria_Erfe
 527 | | `Bhaiksuki
 528 | | `Block_Elements
 529 | | `Bopomofo
 530 | | `Bopomofo_Ext
 531 | | `Box_Drawing
 532 | | `Brahmi
 533 | | `Braille
 534 | | `Buginese
 535 | | `Buhid
 536 | | `Byzantine_Music
 537 | | `CJK
 538 | | `CJK_Compat
 539 | | `CJK_Compat_Forms
 540 | | `CJK_Compat_Ideographs
 541 | | `CJK_Compat_Ideographs_Sup
 542 | | `CJK_Ext_A
 543 | | `CJK_Ext_B
 544 | | `CJK_Ext_C
 545 | | `CJK_Ext_D
 546 | | `CJK_Ext_E
 547 | | `CJK_Ext_F
 548 | | `CJK_Ext_G
 549 | | `CJK_Ext_H
 550 | | `CJK_Ext_I
 551 | | `CJK_Ext_J
 552 | | `CJK_Radicals_Sup
 553 | | `CJK_Strokes
 554 | | `CJK_Symbols
 555 | | `Carian
 556 | | `Caucasian_Albanian
 557 | | `Chakma
 558 | | `Cham
 559 | | `Cherokee
 560 | | `Cherokee_Sup
 561 | | `Chess_Symbols
 562 | | `Chorasmian
 563 | | `Compat_Jamo
 564 | | `Control_Pictures
 565 | | `Coptic
 566 | | `Coptic_Epact_Numbers
 567 | | `Counting_Rod
 568 | | `Cuneiform
 569 | | `Cuneiform_Numbers
 570 | | `Currency_Symbols
 571 | | `Cypriot_Syllabary
 572 | | `Cypro_Minoan
 573 | | `Cyrillic
 574 | | `Cyrillic_Ext_A
 575 | | `Cyrillic_Ext_B
 576 | | `Cyrillic_Ext_C
 577 | | `Cyrillic_Ext_D
 578 | | `Cyrillic_Sup
 579 | | `Deseret
 580 | | `Devanagari
 581 | | `Devanagari_Ext
 582 | | `Devanagari_Ext_A
 583 | | `Diacriticals
 584 | | `Diacriticals_Ext
 585 | | `Diacriticals_For_Symbols
 586 | | `Diacriticals_Sup
 587 | | `Dingbats
 588 | | `Dives_Akuru
 589 | | `Dogra
 590 | | `Domino
 591 | | `Duployan
 592 | | `Early_Dynastic_Cuneiform
 593 | | `Egyptian_Hieroglyph_Format_Controls
 594 | | `Egyptian_Hieroglyphs
 595 | | `Egyptian_Hieroglyphs_Ext_A
 596 | | `Elbasan
 597 | | `Elymaic
 598 | | `Emoticons
 599 | | `Enclosed_Alphanum
 600 | | `Enclosed_Alphanum_Sup
 601 | | `Enclosed_CJK
 602 | | `Enclosed_Ideographic_Sup
 603 | | `Ethiopic
 604 | | `Ethiopic_Ext
 605 | | `Ethiopic_Ext_A
 606 | | `Ethiopic_Ext_B
 607 | | `Ethiopic_Sup
 608 | | `Garay
 609 | | `Geometric_Shapes
 610 | | `Geometric_Shapes_Ext
 611 | | `Georgian
 612 | | `Georgian_Ext
 613 | | `Georgian_Sup
 614 | | `Glagolitic
 615 | | `Glagolitic_Sup
 616 | | `Gothic
 617 | | `Grantha
 618 | | `Greek
 619 | | `Greek_Ext
 620 | | `Gujarati
 621 | | `Gunjala_Gondi
 622 | | `Gurmukhi
 623 | | `Gurung_Khema
 624 | | `Half_And_Full_Forms
 625 | | `Half_Marks
 626 | | `Hangul
 627 | | `Hanifi_Rohingya
 628 | | `Hanunoo
 629 | | `Hatran
 630 | | `Hebrew
 631 | | `High_PU_Surrogates
 632 | | `High_Surrogates
 633 | | `Hiragana
 634 | | `IDC
 635 | | `IPA_Ext
 636 | | `Ideographic_Symbols
 637 | | `Imperial_Aramaic
 638 | | `Indic_Number_Forms
 639 | | `Indic_Siyaq_Numbers
 640 | | `Inscriptional_Pahlavi
 641 | | `Inscriptional_Parthian
 642 | | `Jamo
 643 | | `Jamo_Ext_A
 644 | | `Jamo_Ext_B
 645 | | `Javanese
 646 | | `Kaithi
 647 | | `Kaktovik_Numerals
 648 | | `Kana_Ext_A
 649 | | `Kana_Ext_B
 650 | | `Kana_Sup
 651 | | `Kanbun
 652 | | `Kangxi
 653 | | `Kannada
 654 | | `Katakana
 655 | | `Katakana_Ext
 656 | | `Kawi
 657 | | `Kayah_Li
 658 | | `Kharoshthi
 659 | | `Khitan_Small_Script
 660 | | `Khmer
 661 | | `Khmer_Symbols
 662 | | `Khojki
 663 | | `Khudawadi
 664 | | `Kirat_Rai
 665 | | `Lao
 666 | | `Latin_1_Sup
 667 | | `Latin_Ext_A
 668 | | `Latin_Ext_Additional
 669 | | `Latin_Ext_B
 670 | | `Latin_Ext_C
 671 | | `Latin_Ext_D
 672 | | `Latin_Ext_E
 673 | | `Latin_Ext_F
 674 | | `Latin_Ext_G
 675 | | `Lepcha
 676 | | `Letterlike_Symbols
 677 | | `Limbu
 678 | | `Linear_A
 679 | | `Linear_B_Ideograms
 680 | | `Linear_B_Syllabary
 681 | | `Lisu
 682 | | `Lisu_Sup
 683 | | `Low_Surrogates
 684 | | `Lycian
 685 | | `Lydian
 686 | | `Mahajani
 687 | | `Mahjong
 688 | | `Makasar
 689 | | `Malayalam
 690 | | `Mandaic
 691 | | `Manichaean
 692 | | `Marchen
 693 | | `Masaram_Gondi
 694 | | `Math_Alphanum
 695 | | `Math_Operators
 696 | | `Mayan_Numerals
 697 | | `Medefaidrin
 698 | | `Meetei_Mayek
 699 | | `Meetei_Mayek_Ext
 700 | | `Mende_Kikakui
 701 | | `Meroitic_Cursive
 702 | | `Meroitic_Hieroglyphs
 703 | | `Miao
 704 | | `Misc_Arrows
 705 | | `Misc_Math_Symbols_A
 706 | | `Misc_Math_Symbols_B
 707 | | `Misc_Pictographs
 708 | | `Misc_Symbols
 709 | | `Misc_Symbols_Sup
 710 | | `Misc_Technical
 711 | | `Modi
 712 | | `Modifier_Letters
 713 | | `Modifier_Tone_Letters
 714 | | `Mongolian
 715 | | `Mongolian_Sup
 716 | | `Mro
 717 | | `Multani
 718 | | `Music
 719 | | `Myanmar
 720 | | `Myanmar_Ext_A
 721 | | `Myanmar_Ext_B
 722 | | `Myanmar_Ext_C
 723 | | `NB
 724 | | `NKo
 725 | | `Nabataean
 726 | | `Nag_Mundari
 727 | | `Nandinagari
 728 | | `New_Tai_Lue
 729 | | `Newa
 730 | | `Number_Forms
 731 | | `Nushu
 732 | | `Nyiakeng_Puachue_Hmong
 733 | | `OCR
 734 | | `Ogham
 735 | | `Ol_Onal
 736 | | `Ol_Chiki
 737 | | `Old_Hungarian
 738 | | `Old_Italic
 739 | | `Old_North_Arabian
 740 | | `Old_Permic
 741 | | `Old_Persian
 742 | | `Old_Sogdian
 743 | | `Old_South_Arabian
 744 | | `Old_Turkic
 745 | | `Old_Uyghur
 746 | | `Oriya
 747 | | `Ornamental_Dingbats
 748 | | `Osage
 749 | | `Osmanya
 750 | | `Ottoman_Siyaq_Numbers
 751 | | `PUA
 752 | | `Pahawh_Hmong
 753 | | `Palmyrene
 754 | | `Pau_Cin_Hau
 755 | | `Phags_Pa
 756 | | `Phaistos
 757 | | `Phoenician
 758 | | `Phonetic_Ext
 759 | | `Phonetic_Ext_Sup
 760 | | `Playing_Cards
 761 | | `Psalter_Pahlavi
 762 | | `Punctuation
 763 | | `Rejang
 764 | | `Rumi
 765 | | `Runic
 766 | | `Samaritan
 767 | | `Saurashtra
 768 | | `Sharada
 769 | | `Sharada_Sup
 770 | | `Shavian
 771 | | `Shorthand_Format_Controls
 772 | | `Siddham
 773 | | `Sidetic
 774 | | `Sinhala
 775 | | `Sinhala_Archaic_Numbers
 776 | | `Small_Forms
 777 | | `Small_Kana_Ext
 778 | | `Sogdian
 779 | | `Sora_Sompeng
 780 | | `Soyombo
 781 | | `Specials
 782 | | `Sundanese
 783 | | `Sundanese_Sup
 784 | | `Sunuwar
 785 | | `Sup_Arrows_A
 786 | | `Sup_Arrows_B
 787 | | `Sup_Arrows_C
 788 | | `Sup_Math_Operators
 789 | | `Sup_PUA_A
 790 | | `Sup_PUA_B
 791 | | `Sup_Punctuation
 792 | | `Sup_Symbols_And_Pictographs
 793 | | `Super_And_Sub
 794 | | `Sutton_SignWriting
 795 | | `Syloti_Nagri
 796 | | `Symbols_And_Pictographs_Ext_A
 797 | | `Symbols_For_Legacy_Computing
 798 | | `Symbols_For_Legacy_Computing_Sup
 799 | | `Syriac
 800 | | `Syriac_Sup
 801 | | `Tagalog
 802 | | `Tagbanwa
 803 | | `Tags
 804 | | `Tai_Le
 805 | | `Tai_Tham
 806 | | `Tai_Viet
 807 | | `Tai_Xuan_Jing
 808 | | `Tai_Yo
 809 | | `Takri
 810 | | `Tamil
 811 | | `Tamil_Sup
 812 | | `Tangsa
 813 | | `Tangut
 814 | | `Tangut_Components
 815 | | `Tangut_Components_Sup
 816 | | `Tangut_Sup
 817 | | `Telugu
 818 | | `Thaana
 819 | | `Thai
 820 | | `Tibetan
 821 | | `Tifinagh
 822 | | `Tirhuta
 823 | | `Todhri
 824 | | `Tolong_Siki
 825 | | `Toto
 826 | | `Transport_And_Map
 827 | | `Tulu_Tigalari
 828 | | `UCAS
 829 | | `UCAS_Ext
 830 | | `UCAS_Ext_A
 831 | | `Ugaritic
 832 | | `VS
 833 | | `VS_Sup
 834 | | `Vai
 835 | | `Vedic_Ext
 836 | | `Vertical_Forms
 837 | | `Vithkuqi
 838 | | `Wancho
 839 | | `Warang_Citi
 840 | | `Yezidi
 841 | | `Yi_Radicals
 842 | | `Yi_Syllables
 843 | | `Yijing
 844 | | `Zanabazar_Square
 845 | | `Znamenny_Music
 846 | ]
 847 | 
 848 | type value =                                (* the type for property values. *)
 849 | | Age_v of [ `Version of int * int | `Unassigned ]
 850 | | Block_v of block_prop
 851 | | Bidi_class_v of [
 852 |     | `AL
 853 |     | `AN
 854 |     | `B
 855 |     | `BN
 856 |     | `CS
 857 |     | `EN
 858 |     | `ES
 859 |     | `ET
 860 |     | `L
 861 |     | `LRE
 862 |     | `LRO
 863 |     | `NSM
 864 |     | `ON
 865 |     | `PDF
 866 |     | `R
 867 |     | `RLE
 868 |     | `RLO
 869 |     | `S
 870 |     | `WS
 871 |     | `LRI
 872 |     | `RLI
 873 |     | `FSI
 874 |     | `PDI
 875 |   ]
 876 | | Bidi_paired_bracket_type_v of [ `O | `C | `N ]
 877 | | Bool_v of bool
 878 | | Bool_maybe_v of [ `True | `False | `Maybe ]
 879 | | Cp_v of cp
 880 | | Cp_map_v of [ `Self | `Cp of cp ]
 881 | | Cp_opt_v of cp option
 882 | | Decomposition_type_v of [
 883 |     | `Can
 884 |     | `Com
 885 |     | `Enc
 886 |     | `Fin
 887 |     | `Font
 888 |     | `Fra
 889 |     | `Init
 890 |     | `Iso
 891 |     | `Med
 892 |     | `Nar
 893 |     | `Nb
 894 |     | `Sml
 895 |     | `Sqr
 896 |     | `Sub
 897 |     | `Sup
 898 |     | `Vert
 899 |     | `Wide
 900 |     | `None
 901 |   ]
 902 | | East_asian_width_v of [ `A | `F | `H | `N | `Na | `W ]
 903 | | General_category_v of [
 904 |     | `Lu
 905 |     | `Ll
 906 |     | `Lt
 907 |     | `Lm
 908 |     | `Lo
 909 |     | `Mn
 910 |     | `Mc
 911 |     | `Me
 912 |     | `Nd
 913 |     | `Nl
 914 |     | `No
 915 |     | `Pc
 916 |     | `Pd
 917 |     | `Ps
 918 |     | `Pe
 919 |     | `Pi
 920 |     | `Pf
 921 |     | `Po
 922 |     | `Sm
 923 |     | `Sc
 924 |     | `Sk
 925 |     | `So
 926 |     | `Zs
 927 |     | `Zl
 928 |     | `Zp
 929 |     | `Cc
 930 |     | `Cf
 931 |     | `Cs
 932 |     | `Co
 933 |     | `Cn
 934 |   ]
 935 | | Grapheme_cluster_break_v of [
 936 |   | `CN
 937 |   | `CR
 938 |   | `EB
 939 |   | `EBG
 940 |   | `EM
 941 |   | `EX
 942 |   | `GAZ
 943 |   | `L
 944 |   | `LF
 945 |   | `LV
 946 |   | `LVT
 947 |   | `PP
 948 |   | `RI
 949 |   | `SM
 950 |   | `T
 951 |   | `V
 952 |   | `XX
 953 |   | `ZWJ ]
 954 | | Hangul_syllable_type_v of [ `L | `LV | `LVT | `T | `V | `NA ]
 955 | | Int_v of int
 956 | | Indic_conjunct_break_v of
 957 |     [ `Consonant
 958 |     | `Extend
 959 |     | `Linker
 960 |     | `None ]
 961 | | Indic_syllabic_category_v of
 962 |     [ `Avagraha
 963 |     | `Bindu
 964 |     | `Brahmi_Joining_Number
 965 |     | `Cantillation_Mark
 966 |     | `Consonant
 967 |     | `Consonant_Dead
 968 |     | `Consonant_Final
 969 |     | `Consonant_Head_Letter
 970 |     | `Consonant_Initial_Postfixed
 971 |     | `Consonant_Killer
 972 |     | `Consonant_Medial
 973 |     | `Consonant_Placeholder
 974 |     | `Consonant_Preceding_Repha
 975 |     | `Consonant_Prefixed
 976 |     | `Consonant_Repha
 977 |     | `Consonant_Subjoined
 978 |     | `Consonant_Succeeding_Repha
 979 |     | `Consonant_With_Stacker
 980 |     | `Gemination_Mark
 981 |     | `Invisible_Stacker
 982 |     | `Joiner
 983 |     | `Modifying_Letter
 984 |     | `Non_Joiner
 985 |     | `Nukta
 986 |     | `Number
 987 |     | `Number_Joiner
 988 |     | `Other
 989 |     | `Pure_Killer
 990 |     | `Reordering_Killer
 991 |     | `Register_Shifter
 992 |     | `Syllable_Modifier
 993 |     | `Tone_Letter
 994 |     | `Tone_Mark
 995 |     | `Virama
 996 |     | `Visarga
 997 |     | `Vowel
 998 |     | `Vowel_Dependent
 999 |     | `Vowel_Independent ]
1000 | | Indic_matra_category_v of [
1001 |     | `Right
1002 |     | `Left
1003 |     | `Visual_Order_Left
1004 |     | `Left_And_Right
1005 |     | `Top
1006 |     | `Bottom
1007 |     | `Top_And_Bottom
1008 |     | `Top_And_Right
1009 |     | `Top_And_Left
1010 |     | `Top_And_Left_And_Right
1011 |     | `Bottom_And_Right
1012 |     | `Top_And_Bottom_And_Right
1013 |     | `Overstruck
1014 |     | `Invisible
1015 |     | `NA
1016 |   ]
1017 | | Indic_positional_category_v of [
1018 |     | `Bottom
1019 |     | `Bottom_And_Left
1020 |     | `Bottom_And_Right
1021 |     | `Invisible
1022 |     | `Left
1023 |     | `Left_And_Right
1024 |     | `NA
1025 |     | `Overstruck
1026 |     | `Right
1027 |     | `Top
1028 |     | `Top_And_Bottom
1029 |     | `Top_And_Bottom_And_Left
1030 |     | `Top_And_Bottom_And_Right
1031 |     | `Top_And_Left
1032 |     | `Top_And_Left_And_Right
1033 |     | `Top_And_Right
1034 |     | `Visual_Order_Left
1035 |     ]
1036 | | Joining_group_v of [
1037 |     | `African_Feh
1038 |     | `African_Noon
1039 |     | `African_Qaf
1040 |     | `Ain
1041 |     | `Alaph
1042 |     | `Alef
1043 |     | `Alef_Maqsurah
1044 |     | `Beh
1045 |     | `Beth
1046 |     | `Burushaski_Yeh_Barree
1047 |     | `Dal
1048 |     | `Dalath_Rish
1049 |     | `E
1050 |     | `Farsi_Yeh
1051 |     | `Fe
1052 |     | `Feh
1053 |     | `Final_Semkath
1054 |     | `Gaf
1055 |     | `Gamal
1056 |     | `Hah
1057 |     | `Hanifi_Rohingya_Kinna_Ya
1058 |     | `Hanifi_Rohingya_Pa
1059 |     | `Hamza_On_Heh_Goal
1060 |     | `He
1061 |     | `Heh
1062 |     | `Heh_Goal
1063 |     | `Heth
1064 |     | `Kaf
1065 |     | `Kaph
1066 |     | `Kashmiri_Yeh
1067 |     | `Khaph
1068 |     | `Knotted_Heh
1069 |     | `Lam
1070 |     | `Lamadh
1071 |     | `Malayalam_Bha
1072 |     | `Malayalam_Ja
1073 |     | `Malayalam_Lla
1074 |     | `Malayalam_Llla
1075 |     | `Malayalam_Nga
1076 |     | `Malayalam_Nna
1077 |     | `Malayalam_Nnna
1078 |     | `Malayalam_Nya
1079 |     | `Malayalam_Ra
1080 |     | `Malayalam_Ssa
1081 |     | `Malayalam_Tta
1082 |     | `Manichaean_Aleph
1083 |     | `Manichaean_Ayin
1084 |     | `Manichaean_Beth
1085 |     | `Manichaean_Daleth
1086 |     | `Manichaean_Dhamedh
1087 |     | `Manichaean_Five
1088 |     | `Manichaean_Gimel
1089 |     | `Manichaean_Heth
1090 |     | `Manichaean_Hundred
1091 |     | `Manichaean_Kaph
1092 |     | `Manichaean_Lamedh
1093 |     | `Manichaean_Mem
1094 |     | `Manichaean_Nun
1095 |     | `Manichaean_One
1096 |     | `Manichaean_Pe
1097 |     | `Manichaean_Qoph
1098 |     | `Manichaean_Resh
1099 |     | `Manichaean_Sadhe
1100 |     | `Manichaean_Samekh
1101 |     | `Manichaean_Taw
1102 |     | `Manichaean_Ten
1103 |     | `Manichaean_Teth
1104 |     | `Manichaean_Thamedh
1105 |     | `Manichaean_Twenty
1106 |     | `Manichaean_Waw
1107 |     | `Manichaean_Yodh
1108 |     | `Manichaean_Zayin
1109 |     | `Meem
1110 |     | `Mim
1111 |     | `No_Joining_Group
1112 |     | `Noon
1113 |     | `Nun
1114 |     | `Nya
1115 |     | `Pe
1116 |     | `Qaf
1117 |     | `Qaph
1118 |     | `Reh
1119 |     | `Reversed_Pe
1120 |     | `Rohingya_Yeh
1121 |     | `Sad
1122 |     | `Sadhe
1123 |     | `Seen
1124 |     | `Semkath
1125 |     | `Shin
1126 |     | `Straight_Waw
1127 |     | `Swash_Kaf
1128 |     | `Syriac_Waw
1129 |     | `Tah
1130 |     | `Taw
1131 |     | `Teh_Marbuta
1132 |     | `Teh_Marbuta_Goal
1133 |     | `Teth
1134 |     | `Thin_Noon
1135 |     | `Thin_Yeh
1136 |     | `Vertical_Tail
1137 |     | `Waw
1138 |     | `Yeh
1139 |     | `Yeh_Barree
1140 |     | `Yeh_With_Tail
1141 |     | `Yudh
1142 |     | `Yudh_He
1143 |     | `Zain
1144 |     | `Zhain
1145 |     | `BAA
1146 |     | `FA
1147 |     | `HAA
1148 |     | `HA_GOAL
1149 |     | `HA
1150 |     | `CAF
1151 |     | `KNOTTED_HA
1152 |     | `RA
1153 |     | `SWASH_CAF
1154 |     | `HAMZAH_ON_HA_GOAL
1155 |     | `TAA_MARBUTAH
1156 |     | `YA_BARREE
1157 |     | `YA
1158 |     | `ALEF_MAQSURAH ]
1159 | | Joining_type_v of [ `U | `C | `T | `D | `L | `R ]
1160 | | Line_break_v of [
1161 |     | `AI
1162 |     | `AK
1163 |     | `AL
1164 |     | `AP
1165 |     | `AS
1166 |     | `B2
1167 |     | `BA
1168 |     | `BB
1169 |     | `BK
1170 |     | `CB
1171 |     | `CJ
1172 |     | `CL
1173 |     | `CM
1174 |     | `CP
1175 |     | `CR
1176 |     | `EB
1177 |     | `EM
1178 |     | `EX
1179 |     | `GL
1180 |     | `H2
1181 |     | `H3
1182 |     | `HH
1183 |     | `HL
1184 |     | `HY
1185 |     | `ID
1186 |     | `IN
1187 |     | `IS
1188 |     | `JL
1189 |     | `JT
1190 |     | `JV
1191 |     | `LF
1192 |     | `NL
1193 |     | `NS
1194 |     | `NU
1195 |     | `OP
1196 |     | `PO
1197 |     | `PR
1198 |     | `QU
1199 |     | `RI
1200 |     | `SA
1201 |     | `SG
1202 |     | `SP
1203 |     | `SY
1204 |     | `VF
1205 |     | `VI
1206 |     | `WJ
1207 |     | `XX
1208 |     | `ZW
1209 |     | `ZWJ
1210 |   ]
1211 | | Name_v of [`Pattern of string | `Name of string ]
1212 | | Name_alias_v of
1213 |     (string * [`Abbreviation | `Alternate | `Control | `Correction | `Figment])
1214 |       list
1215 | | Numeric_type_v of [ `None | `De | `Di | `Nu ]
1216 | | Numeric_value_v of
1217 |     [ `NaN | `Nums of [`Frac of int * int | `Num of int64 ] list]
1218 | | Script_v of script
1219 | | Script_extensions_v of script list
1220 | | Sentence_break_v of [
1221 |     | `AT
1222 |     | `CL
1223 |     | `CR
1224 |     | `EX
1225 |     | `FO
1226 |     | `LE
1227 |     | `LF
1228 |     | `LO
1229 |     | `NU
1230 |     | `SC
1231 |     | `SE
1232 |     | `SP
1233 |     | `ST
1234 |     | `UP
1235 |     | `XX
1236 |   ]
1237 | | Cps_v of cp list
1238 | | Cps_map_v of [ `Self | `Cps of cp list ]
1239 | | String_v of string
1240 | | UAX_42_element_v of [ `Reserved | `Noncharacter | `Surrogate | `Char ]
1241 | | Vertical_orientation_v of [ `U | `R | `Tu | `Tr ]
1242 | | Word_break_v of [
1243 |     | `CR
1244 |     | `DQ
1245 |     | `EB
1246 |     | `EBG
1247 |     | `EM
1248 |     | `EX
1249 |     | `Extend
1250 |     | `FO
1251 |     | `GAZ
1252 |     | `HL
1253 |     | `KA
1254 |     | `LE
1255 |     | `LF
1256 |     | `MB
1257 |     | `ML
1258 |     | `MN
1259 |     | `NL
1260 |     | `NU
1261 |     | `RI
1262 |     | `SQ
1263 |     | `WSegSpace
1264 |     | `XX
1265 |     | `ZWJ
1266 |   ]
1267 | 
1268 | (* property value projection *)
1269 | 
1270 | let o_age = function Age_v v -> v | _ -> assert false
1271 | let o_bidi_class = function Bidi_class_v v -> v | _ -> assert false
1272 | let o_bidi_paired_bracket_type =
1273 |   function Bidi_paired_bracket_type_v v -> v | _ -> assert false
1274 | 
1275 | let o_block = function Block_v v -> v | _ -> assert false
1276 | let o_bool = function Bool_v v -> v | _ -> assert false
1277 | let o_bool_maybe = function Bool_maybe_v v -> v | _ -> assert false
1278 | let o_cp = function Cp_v v -> v | _ -> assert false
1279 | let o_cp_map = function Cp_map_v v -> v | _ -> assert false
1280 | let o_cp_opt = function Cp_opt_v v -> v | _ -> assert false
1281 | let o_decomposition_type =
1282 |   function Decomposition_type_v v -> v | _ -> assert false
1283 | 
1284 | let o_east_asian_width = function East_asian_width_v v -> v | _ -> assert false
1285 | let o_general_category = function General_category_v v -> v | _ -> assert false
1286 | let o_grapheme_cluster_break =
1287 |   function Grapheme_cluster_break_v v -> v | _ -> assert false
1288 | 
1289 | let o_hangul_syllable_type =
1290 |   function Hangul_syllable_type_v v -> v | _ -> assert false
1291 | 
1292 | let o_int = function Int_v v -> v | _ -> assert false
1293 | 
1294 | let o_indic_conjunct_break =
1295 |   function Indic_conjunct_break_v v -> v | _ -> assert false
1296 | 
1297 | let o_indic_syllabic_category =
1298 |   function Indic_syllabic_category_v v -> v | _ -> assert false
1299 | 
1300 | let o_indic_matra_category =
1301 |   function Indic_matra_category_v v -> v | _ -> assert false
1302 | 
1303 | let o_indic_positional_category =
1304 |   function Indic_positional_category_v v -> v | _ -> assert false
1305 | 
1306 | let o_joining_group = function Joining_group_v v -> v | _ -> assert false
1307 | let o_joining_type = function Joining_type_v v -> v | _ -> assert false
1308 | let o_line_break = function Line_break_v v -> v | _ -> assert false
1309 | let o_name = function Name_v v -> v | _ -> assert false
1310 | let o_name_alias = function Name_alias_v v -> v | _ -> assert false
1311 | let o_numeric_type = function Numeric_type_v v -> v | _ -> assert false
1312 | let o_numeric_value = function Numeric_value_v v -> v | _ -> assert false
1313 | let o_script = function Script_v v -> v | _ -> assert false
1314 | let o_script_extensions =
1315 |   function Script_extensions_v v -> v | _ -> assert false
1316 | 
1317 | let o_sentence_break = function Sentence_break_v v -> v | _ -> assert false
1318 | let o_cps = function Cps_v v -> v | _ -> assert false
1319 | let o_cps_map = function Cps_map_v v -> v | _ -> assert false
1320 | let o_string = function String_v v -> v | _ -> assert false
1321 | let o_uax_42_element = function UAX_42_element_v v -> v | _ -> assert false
1322 | let o_vertical_orientation =
1323 |   function Vertical_orientation_v v -> v | _ -> assert false
1324 | let o_word_break = function Word_break_v v -> v | _ -> assert false
1325 | 
1326 | (* property value injection *)
1327 | 
1328 | let i_age v = Age_v begin match v with
1329 | | "unassigned" -> `Unassigned
1330 | | v ->
1331 |     try match List.map int_of_string (split_string v '.') with
1332 |     | [v1; v2;] -> `Version (v1, v2)
1333 |     | _ -> failwith ""
1334 |     with Failure _ -> err (err_att_val v)
1335 | end
1336 | 
1337 | let i_bidi_class v = Bidi_class_v begin match v with
1338 | | "AL" -> `AL
1339 | | "AN" -> `AN
1340 | | "B" -> `B
1341 | | "BN" -> `BN
1342 | | "CS" -> `CS
1343 | | "EN" -> `EN
1344 | | "ES" -> `ES
1345 | | "ET" -> `ET
1346 | | "L" -> `L
1347 | | "LRE" -> `LRE
1348 | | "LRO" -> `LRO
1349 | | "NSM" -> `NSM
1350 | | "ON" -> `ON
1351 | | "PDF" -> `PDF
1352 | | "R" -> `R
1353 | | "RLE" -> `RLE
1354 | | "RLO" -> `RLO
1355 | | "S" -> `S
1356 | | "WS" -> `WS
1357 | | "LRI" -> `LRI
1358 | | "RLI" -> `RLI
1359 | | "FSI" -> `FSI
1360 | | "PDI" -> `PDI
1361 | | v -> err (err_att_val v)
1362 | end
1363 | 
1364 | let i_bidi_paired_bracket_type v = Bidi_paired_bracket_type_v begin match v with
1365 | | "o" -> `O
1366 | | "c" -> `C
1367 | | "n" -> `N
1368 | | v -> err (err_att_val v)
1369 | end
1370 | 
1371 | let i_block v = Block_v begin match v with
1372 | | "ASCII" -> `ASCII
1373 | | "Adlam" -> `Adlam
1374 | | "Aegean_Numbers" -> `Aegean_Numbers
1375 | | "Ahom" -> `Ahom
1376 | | "Alchemical" -> `Alchemical
1377 | | "Alphabetic_PF" -> `Alphabetic_PF
1378 | | "Anatolian_Hieroglyphs" -> `Anatolian_Hieroglyphs
1379 | | "Ancient_Greek_Music" -> `Ancient_Greek_Music
1380 | | "Ancient_Greek_Numbers" -> `Ancient_Greek_Numbers
1381 | | "Ancient_Symbols" -> `Ancient_Symbols
1382 | | "Arabic" -> `Arabic
1383 | | "Arabic_Ext_A" -> `Arabic_Ext_A
1384 | | "Arabic_Ext_B" -> `Arabic_Ext_A
1385 | | "Arabic_Ext_C" -> `Arabic_Ext_C
1386 | | "Arabic_Math" -> `Arabic_Math
1387 | | "Arabic_PF_A" -> `Arabic_PF_A
1388 | | "Arabic_PF_B" -> `Arabic_PF_B
1389 | | "Arabic_Sup" -> `Arabic_Sup
1390 | | "Armenian" -> `Armenian
1391 | | "Arrows" -> `Arrows
1392 | | "Avestan" -> `Avestan
1393 | | "Balinese" -> `Balinese
1394 | | "Bamum" -> `Bamum
1395 | | "Bamum_Sup" -> `Bamum_Sup
1396 | | "Bassa_Vah" -> `Bassa_Vah
1397 | | "Batak" -> `Batak
1398 | | "Bengali" -> `Bengali
1399 | | "Beria_Erfe" -> `Beria_Erfe
1400 | | "Bhaiksuki" -> `Bhaiksuki
1401 | | "Block_Elements" -> `Block_Elements
1402 | | "Bopomofo" -> `Bopomofo
1403 | | "Bopomofo_Ext" -> `Bopomofo_Ext
1404 | | "Box_Drawing" -> `Box_Drawing
1405 | | "Brahmi" -> `Brahmi
1406 | | "Braille" -> `Braille
1407 | | "Buginese" -> `Buginese
1408 | | "Buhid" -> `Buhid
1409 | | "Byzantine_Music" -> `Byzantine_Music
1410 | | "CJK" -> `CJK
1411 | | "CJK_Compat" -> `CJK_Compat
1412 | | "CJK_Compat_Forms" -> `CJK_Compat_Forms
1413 | | "CJK_Compat_Ideographs" -> `CJK_Compat_Ideographs
1414 | | "CJK_Compat_Ideographs_Sup" -> `CJK_Compat_Ideographs_Sup
1415 | | "CJK_Ext_A" -> `CJK_Ext_A
1416 | | "CJK_Ext_B" -> `CJK_Ext_B
1417 | | "CJK_Ext_C" -> `CJK_Ext_C
1418 | | "CJK_Ext_D" -> `CJK_Ext_D
1419 | | "CJK_Ext_E" -> `CJK_Ext_E
1420 | | "CJK_Ext_F" -> `CJK_Ext_F
1421 | | "CJK_Ext_G" -> `CJK_Ext_G
1422 | | "CJK_Ext_H" -> `CJK_Ext_H
1423 | | "CJK_Ext_I" -> `CJK_Ext_I
1424 | | "CJK_Ext_J" -> `CJK_Ext_J
1425 | | "CJK_Radicals_Sup" -> `CJK_Radicals_Sup
1426 | | "CJK_Strokes" -> `CJK_Strokes
1427 | | "CJK_Symbols" -> `CJK_Symbols
1428 | | "Carian" -> `Carian
1429 | | "Caucasian_Albanian" -> `Caucasian_Albanian
1430 | | "Chakma" -> `Chakma
1431 | | "Cham" -> `Cham
1432 | | "Cherokee" -> `Cherokee
1433 | | "Cherokee_Sup" -> `Cherokee_Sup
1434 | | "Chess_Symbols" -> `Chess_Symbols
1435 | | "Chorasmian" -> `Chorasmian
1436 | | "Compat_Jamo" -> `Compat_Jamo
1437 | | "Control_Pictures" -> `Control_Pictures
1438 | | "Coptic" -> `Coptic
1439 | | "Coptic_Epact_Numbers" -> `Coptic_Epact_Numbers
1440 | | "Counting_Rod" -> `Counting_Rod
1441 | | "Cuneiform" -> `Cuneiform
1442 | | "Cuneiform_Numbers" -> `Cuneiform_Numbers
1443 | | "Currency_Symbols" -> `Currency_Symbols
1444 | | "Cypriot_Syllabary" -> `Cypriot_Syllabary
1445 | | "Cypro_Minoan" -> `Cypro_Minoan
1446 | | "Cyrillic" -> `Cyrillic
1447 | | "Cyrillic_Ext_A" -> `Cyrillic_Ext_A
1448 | | "Cyrillic_Ext_B" -> `Cyrillic_Ext_B
1449 | | "Cyrillic_Ext_C" -> `Cyrillic_Ext_C
1450 | | "Cyrillic_Ext_D" -> `Cyrillic_Ext_D
1451 | | "Cyrillic_Sup" -> `Cyrillic_Sup
1452 | | "Deseret" -> `Deseret
1453 | | "Devanagari" -> `Devanagari
1454 | | "Devanagari_Ext" -> `Devanagari_Ext
1455 | | "Devanagari_Ext_A" -> `Devanagari_Ext_A
1456 | | "Diacriticals" -> `Diacriticals
1457 | | "Diacriticals_Ext" -> `Diacriticals_Ext
1458 | | "Diacriticals_For_Symbols" -> `Diacriticals_For_Symbols
1459 | | "Diacriticals_Sup" -> `Diacriticals_Sup
1460 | | "Dingbats" -> `Dingbats
1461 | | "Dives_Akuru" -> `Dives_Akuru
1462 | | "Dogra" -> `Dogra
1463 | | "Domino" -> `Domino
1464 | | "Duployan" -> `Duployan
1465 | | "Early_Dynastic_Cuneiform" -> `Early_Dynastic_Cuneiform
1466 | | "Egyptian_Hieroglyph_Format_Controls" -> `Egyptian_Hieroglyph_Format_Controls
1467 | | "Egyptian_Hieroglyphs" -> `Egyptian_Hieroglyphs
1468 | | "Egyptian_Hieroglyphs_Ext_A" -> `Egyptian_Hieroglyphs_Ext_A
1469 | | "Elbasan" -> `Elbasan
1470 | | "Elymaic" -> `Elymaic
1471 | | "Emoticons" -> `Emoticons
1472 | | "Enclosed_Alphanum" -> `Enclosed_Alphanum
1473 | | "Enclosed_Alphanum_Sup" -> `Enclosed_Alphanum_Sup
1474 | | "Enclosed_CJK" -> `Enclosed_CJK
1475 | | "Enclosed_Ideographic_Sup" -> `Enclosed_Ideographic_Sup
1476 | | "Ethiopic" -> `Ethiopic
1477 | | "Ethiopic_Ext" -> `Ethiopic_Ext
1478 | | "Ethiopic_Ext_A" -> `Ethiopic_Ext_A
1479 | | "Ethiopic_Ext_B" -> `Ethiopic_Ext_B
1480 | | "Ethiopic_Sup" -> `Ethiopic_Sup
1481 | | "Garay" -> `Garay
1482 | | "Geometric_Shapes" -> `Geometric_Shapes
1483 | | "Geometric_Shapes_Ext" -> `Geometric_Shapes_Ext
1484 | | "Georgian" -> `Georgian
1485 | | "Georgian_Ext" -> `Georgian_Ext
1486 | | "Georgian_Sup" -> `Georgian_Sup
1487 | | "Glagolitic" -> `Glagolitic
1488 | | "Glagolitic_Sup" -> `Glagolitic_Sup
1489 | | "Gothic" -> `Gothic
1490 | | "Grantha" -> `Grantha
1491 | | "Greek" -> `Greek
1492 | | "Greek_Ext" -> `Greek_Ext
1493 | | "Gujarati" -> `Gujarati
1494 | | "Gunjala_Gondi" -> `Gunjala_Gondi
1495 | | "Gurmukhi" -> `Gurmukhi
1496 | | "Gurung_Khema" -> `Gurung_Khema
1497 | | "Half_And_Full_Forms" -> `Half_And_Full_Forms
1498 | | "Half_Marks" -> `Half_Marks
1499 | | "Hangul" -> `Hangul
1500 | | "Hanifi_Rohingya" -> `Hanifi_Rohingya
1501 | | "Hanunoo" -> `Hanunoo
1502 | | "Hatran" -> `Hatran
1503 | | "Hebrew" -> `Hebrew
1504 | | "High_PU_Surrogates" -> `High_PU_Surrogates
1505 | | "High_Surrogates" -> `High_Surrogates
1506 | | "Hiragana" -> `Hiragana
1507 | | "IDC" -> `IDC
1508 | | "IPA_Ext" -> `IPA_Ext
1509 | | "Ideographic_Symbols" -> `Ideographic_Symbols
1510 | | "Imperial_Aramaic" -> `Imperial_Aramaic
1511 | | "Indic_Number_Forms" -> `Indic_Number_Forms
1512 | | "Indic_Siyaq_Numbers" -> `Indic_Siyaq_Numbers
1513 | | "Inscriptional_Pahlavi" -> `Inscriptional_Pahlavi
1514 | | "Inscriptional_Parthian" -> `Inscriptional_Parthian
1515 | | "Jamo" -> `Jamo
1516 | | "Jamo_Ext_A" -> `Jamo_Ext_A
1517 | | "Jamo_Ext_B" -> `Jamo_Ext_B
1518 | | "Javanese" -> `Javanese
1519 | | "Kaithi" -> `Kaithi
1520 | | "Kaktovik_Numerals" -> `Kaktovik_Numerals
1521 | | "Kana_Ext_A" -> `Kana_Ext_A
1522 | | "Kana_Ext_B" -> `Kana_Ext_B
1523 | | "Kawi" -> `Kawi
1524 | | "Kana_Sup" -> `Kana_Sup
1525 | | "Kanbun" -> `Kanbun
1526 | | "Kangxi" -> `Kangxi
1527 | | "Kannada" -> `Kannada
1528 | | "Katakana" -> `Katakana
1529 | | "Katakana_Ext" -> `Katakana_Ext
1530 | | "Kayah_Li" -> `Kayah_Li
1531 | | "Kharoshthi" -> `Kharoshthi
1532 | | "Khitan_Small_Script" -> `Khitan_Small_Script
1533 | | "Khmer" -> `Khmer
1534 | | "Khmer_Symbols" -> `Khmer_Symbols
1535 | | "Khojki" -> `Khojki
1536 | | "Khudawadi" -> `Khudawadi
1537 | | "Kirat_Rai" -> `Kirat_Rai
1538 | | "Lao" -> `Lao
1539 | | "Latin_1_Sup" -> `Latin_1_Sup
1540 | | "Latin_Ext_A" -> `Latin_Ext_A
1541 | | "Latin_Ext_Additional" -> `Latin_Ext_Additional
1542 | | "Latin_Ext_B" -> `Latin_Ext_B
1543 | | "Latin_Ext_C" -> `Latin_Ext_C
1544 | | "Latin_Ext_D" -> `Latin_Ext_D
1545 | | "Latin_Ext_E" -> `Latin_Ext_E
1546 | | "Latin_Ext_F" -> `Latin_Ext_F
1547 | | "Latin_Ext_G" -> `Latin_Ext_G
1548 | | "Lepcha" -> `Lepcha
1549 | | "Letterlike_Symbols" -> `Letterlike_Symbols
1550 | | "Limbu" -> `Limbu
1551 | | "Linear_A" -> `Linear_A
1552 | | "Linear_B_Ideograms" -> `Linear_B_Ideograms
1553 | | "Linear_B_Syllabary" -> `Linear_B_Syllabary
1554 | | "Lisu" -> `Lisu
1555 | | "Lisu_Sup" -> `Lisu_Sup
1556 | | "Low_Surrogates" -> `Low_Surrogates
1557 | | "Lycian" -> `Lycian
1558 | | "Lydian" -> `Lydian
1559 | | "Mahajani" -> `Mahajani
1560 | | "Mahjong" -> `Mahjong
1561 | | "Makasar" -> `Makasar
1562 | | "Malayalam" -> `Malayalam
1563 | | "Mandaic" -> `Mandaic
1564 | | "Manichaean" -> `Manichaean
1565 | | "Marchen" -> `Marchen
1566 | | "Masaram_Gondi" -> `Masaram_Gondi
1567 | | "Math_Alphanum" -> `Math_Alphanum
1568 | | "Math_Operators" -> `Math_Operators
1569 | | "Mayan_Numerals" -> `Mayan_Numerals
1570 | | "Medefaidrin" -> `Medefaidrin
1571 | | "Meetei_Mayek" -> `Meetei_Mayek
1572 | | "Meetei_Mayek_Ext" -> `Meetei_Mayek_Ext
1573 | | "Mende_Kikakui" -> `Mende_Kikakui
1574 | | "Meroitic_Cursive" -> `Meroitic_Cursive
1575 | | "Meroitic_Hieroglyphs" -> `Meroitic_Hieroglyphs
1576 | | "Miao" -> `Miao
1577 | | "Misc_Arrows" -> `Misc_Arrows
1578 | | "Misc_Math_Symbols_A" -> `Misc_Math_Symbols_A
1579 | | "Misc_Math_Symbols_B" -> `Misc_Math_Symbols_B
1580 | | "Misc_Pictographs" -> `Misc_Pictographs
1581 | | "Misc_Symbols" -> `Misc_Symbols
1582 | | "Misc_Symbols_Sup" -> `Misc_Symbols_Sup
1583 | | "Misc_Technical" -> `Misc_Technical
1584 | | "Modi" -> `Modi
1585 | | "Modifier_Letters" -> `Modifier_Letters
1586 | | "Modifier_Tone_Letters" -> `Modifier_Tone_Letters
1587 | | "Mongolian" -> `Mongolian
1588 | | "Mongolian_Sup" -> `Mongolian_Sup
1589 | | "Mro" -> `Mro
1590 | | "Multani" -> `Multani
1591 | | "Music" -> `Music
1592 | | "Myanmar" -> `Myanmar
1593 | | "Myanmar_Ext_A" -> `Myanmar_Ext_A
1594 | | "Myanmar_Ext_B" -> `Myanmar_Ext_B
1595 | | "Myanmar_Ext_C" -> `Myanmar_Ext_C
1596 | | "NB" -> `NB
1597 | | "NKo" -> `NKo
1598 | | "Nabataean" -> `Nabataean
1599 | | "Nag_Mundari" -> `Nag_Mundari
1600 | | "Nandinagari" -> `Nandinagari
1601 | | "New_Tai_Lue" -> `New_Tai_Lue
1602 | | "Newa" -> `Newa
1603 | | "Number_Forms" -> `Number_Forms
1604 | | "Nushu" -> `Nushu
1605 | | "Nyiakeng_Puachue_Hmong" -> `Nyiakeng_Puachue_Hmong
1606 | | "OCR" -> `OCR
1607 | | "Ogham" -> `Ogham
1608 | | "Ol_Chiki" -> `Ol_Chiki
1609 | | "Ol_Onal" -> `Ol_Onal
1610 | | "Old_Hungarian" -> `Old_Hungarian
1611 | | "Old_Italic" -> `Old_Italic
1612 | | "Old_North_Arabian" -> `Old_North_Arabian
1613 | | "Old_Permic" -> `Old_Permic
1614 | | "Old_Persian" -> `Old_Persian
1615 | | "Old_Sogdian" -> `Old_Sogdian
1616 | | "Old_South_Arabian" -> `Old_South_Arabian
1617 | | "Old_Turkic" -> `Old_Turkic
1618 | | "Old_Uyghur" -> `Old_Uyghur
1619 | | "Oriya" -> `Oriya
1620 | | "Ornamental_Dingbats" -> `Ornamental_Dingbats
1621 | | "Osage" -> `Osage
1622 | | "Osmanya" -> `Osmanya
1623 | | "Ottoman_Siyaq_Numbers" -> `Ottoman_Siyaq_Numbers
1624 | | "PUA" -> `PUA
1625 | | "Pahawh_Hmong" -> `Pahawh_Hmong
1626 | | "Palmyrene" -> `Palmyrene
1627 | | "Pau_Cin_Hau" -> `Pau_Cin_Hau
1628 | | "Phags_Pa" -> `Phags_Pa
1629 | | "Phaistos" -> `Phaistos
1630 | | "Phoenician" -> `Phoenician
1631 | | "Phonetic_Ext" -> `Phonetic_Ext
1632 | | "Phonetic_Ext_Sup" -> `Phonetic_Ext_Sup
1633 | | "Playing_Cards" -> `Playing_Cards
1634 | | "Psalter_Pahlavi" -> `Psalter_Pahlavi
1635 | | "Punctuation" -> `Punctuation
1636 | | "Rejang" -> `Rejang
1637 | | "Rumi" -> `Rumi
1638 | | "Runic" -> `Runic
1639 | | "Samaritan" -> `Samaritan
1640 | | "Saurashtra" -> `Saurashtra
1641 | | "Sharada" -> `Sharada
1642 | | "Sharada_Sup" -> `Sharada_Sup
1643 | | "Shavian" -> `Shavian
1644 | | "Shorthand_Format_Controls" -> `Shorthand_Format_Controls
1645 | | "Siddham" -> `Siddham
1646 | | "Sidetic" -> `Sidetic
1647 | | "Sinhala" -> `Sinhala
1648 | | "Sinhala_Archaic_Numbers" -> `Sinhala_Archaic_Numbers
1649 | | "Small_Forms" -> `Small_Forms
1650 | | "Small_Kana_Ext" -> `Small_Kana_Ext
1651 | | "Sogdian" -> `Sogdian
1652 | | "Sora_Sompeng" -> `Sora_Sompeng
1653 | | "Soyombo" -> `Soyombo
1654 | | "Specials" -> `Specials
1655 | | "Sundanese" -> `Sundanese
1656 | | "Sundanese_Sup" -> `Sundanese_Sup
1657 | | "Sunuwar" -> `Sunuwar
1658 | | "Sup_Arrows_A" -> `Sup_Arrows_A
1659 | | "Sup_Arrows_B" -> `Sup_Arrows_B
1660 | | "Sup_Arrows_C" -> `Sup_Arrows_C
1661 | | "Sup_Math_Operators" -> `Sup_Math_Operators
1662 | | "Sup_PUA_A" -> `Sup_PUA_A
1663 | | "Sup_PUA_B" -> `Sup_PUA_B
1664 | | "Sup_Punctuation" -> `Sup_Punctuation
1665 | | "Sup_Symbols_And_Pictographs" -> `Sup_Symbols_And_Pictographs
1666 | | "Super_And_Sub" -> `Super_And_Sub
1667 | | "Sutton_SignWriting" -> `Sutton_SignWriting
1668 | | "Syloti_Nagri" -> `Syloti_Nagri
1669 | | "Symbols_And_Pictographs_Ext_A" -> `Symbols_And_Pictographs_Ext_A
1670 | | "Symbols_For_Legacy_Computing" -> `Symbols_For_Legacy_Computing
1671 | | "Symbols_For_Legacy_Computing_Sup" -> `Symbols_For_Legacy_Computing_Sup
1672 | | "Syriac" -> `Syriac
1673 | | "Syriac_Sup" -> `Syriac_Sup
1674 | | "Tagalog" -> `Tagalog
1675 | | "Tagbanwa" -> `Tagbanwa
1676 | | "Tags" -> `Tags
1677 | | "Tai_Le" -> `Tai_Le
1678 | | "Tai_Tham" -> `Tai_Tham
1679 | | "Tai_Viet" -> `Tai_Viet
1680 | | "Tai_Xuan_Jing" -> `Tai_Xuan_Jing
1681 | | "Tai_Yo" -> `Tai_Yo
1682 | | "Takri" -> `Takri
1683 | | "Tamil" -> `Tamil
1684 | | "Tamil_Sup" -> `Tamil_Sup
1685 | | "Tangsa" -> `Tangsa
1686 | | "Tangut" -> `Tangut
1687 | | "Tangut_Components" -> `Tangut_Components
1688 | | "Tangut_Components_Sup" -> `Tangut_Components_Sup
1689 | | "Tangut_Sup" -> `Tangut_Sup
1690 | | "Telugu" -> `Telugu
1691 | | "Thaana" -> `Thaana
1692 | | "Thai" -> `Thai
1693 | | "Tibetan" -> `Tibetan
1694 | | "Tifinagh" -> `Tifinagh
1695 | | "Tirhuta" -> `Tirhuta
1696 | | "Todhri" -> `Todhri
1697 | | "Tolong_Siki" -> `Tolong_Siki
1698 | | "Toto" -> `Toto
1699 | | "Transport_And_Map" -> `Transport_And_Map
1700 | | "Tulu_Tigalari" -> `Tulu_Tigalari
1701 | | "UCAS" -> `UCAS
1702 | | "UCAS_Ext" -> `UCAS_Ext
1703 | | "UCAS_Ext_A" -> `UCAS_Ext_A
1704 | | "Ugaritic" -> `Ugaritic
1705 | | "VS" -> `VS
1706 | | "VS_Sup" -> `VS_Sup
1707 | | "Vai" -> `Vai
1708 | | "Vedic_Ext" -> `Vedic_Ext
1709 | | "Vertical_Forms" -> `Vertical_Forms
1710 | | "Vithkuqi" -> `Vithkuqi
1711 | | "Wancho" -> `Wancho
1712 | | "Warang_Citi" -> `Warang_Citi
1713 | | "Yezidi" -> `Yezidi
1714 | | "Yi_Radicals" -> `Yi_Radicals
1715 | | "Yi_Syllables" -> `Yi_Syllables
1716 | | "Yijing" -> `Yijing
1717 | | "Zanabazar_Square" -> `Zanabazar_Square
1718 | | "Znamenny_Music" -> `Znamenny_Music
1719 | | v -> err (err_att_val v)
1720 | end
1721 | 
1722 | let i_bool v = Bool_v begin match v with
1723 | | "Y" -> true | "N" -> false
1724 | | v -> err (err_att_val v)
1725 | end
1726 | 
1727 | let i_bool_maybe v = Bool_maybe_v begin match v with
1728 | | "Y" -> `True | "N" -> `False | "M" -> `Maybe
1729 | | v -> err (err_att_val v)
1730 | end
1731 | 
1732 | let i_cp v = Cp_v (cp_of_string v)
1733 | let i_cp_map v =
1734 |   if v = "#" then Cp_map_v `Self else Cp_map_v (`Cp (cp_of_string v))
1735 | 
1736 | let i_cp_opt v =
1737 |   if v = "" then Cp_opt_v None else Cp_opt_v (Some (cp_of_string v))
1738 | 
1739 | let i_cps ?empty v = Cps_v (cps_of_string ?empty v)
1740 | let i_cps_map ?empty v =
1741 |   if v = "#" then Cps_map_v `Self else Cps_map_v (`Cps (cps_of_string ?empty v))
1742 | 
1743 | let i_decomposition_type v = Decomposition_type_v begin match v with
1744 | | "can" -> `Can
1745 | | "com" -> `Com
1746 | | "enc" -> `Enc
1747 | | "fin" -> `Fin
1748 | | "font" -> `Font
1749 | | "fra" -> `Fra
1750 | | "init" -> `Init
1751 | | "iso" -> `Iso
1752 | | "med" -> `Med
1753 | | "nar" -> `Nar
1754 | | "nb" -> `Nb
1755 | | "sml" -> `Sml
1756 | | "sqr" -> `Sqr
1757 | | "sub" -> `Sub
1758 | | "sup" -> `Sup
1759 | | "vert" -> `Vert
1760 | | "wide" -> `Wide
1761 | | "none" -> `None
1762 | | v -> err (err_att_val v)
1763 | end
1764 | 
1765 | let i_east_asian_width v = East_asian_width_v begin match v with
1766 | | "A" -> `A
1767 | | "F" -> `F
1768 | | "H" -> `H
1769 | | "N" -> `N
1770 | | "Na" -> `Na
1771 | | "W" -> `W
1772 | | v -> err (err_att_val v)
1773 | end
1774 | 
1775 | let i_general_category v = General_category_v begin match v with
1776 | | "Lu" -> `Lu
1777 | | "Ll" -> `Ll
1778 | | "Lt" -> `Lt
1779 | | "Lm" -> `Lm
1780 | | "Lo" -> `Lo
1781 | | "Mn" -> `Mn
1782 | | "Mc" -> `Mc
1783 | | "Me" -> `Me
1784 | | "Nd" -> `Nd
1785 | | "Nl" -> `Nl
1786 | | "No" -> `No
1787 | | "Pc" -> `Pc
1788 | | "Pd" -> `Pd
1789 | | "Ps" -> `Ps
1790 | | "Pe" -> `Pe
1791 | | "Pi" -> `Pi
1792 | | "Pf" -> `Pf
1793 | | "Po" -> `Po
1794 | | "Sm" -> `Sm
1795 | | "Sc" ->`Sc
1796 | | "Sk" -> `Sk
1797 | | "So" -> `So
1798 | | "Zs" -> `Zs
1799 | | "Zl" -> `Zl
1800 | | "Zp" -> `Zp
1801 | | "Cc" -> `Cc
1802 | | "Cf" -> `Cf
1803 | | "Cs" -> `Cs
1804 | | "Co" -> `Co
1805 | | "Cn" -> `Cn
1806 | | v -> err (err_att_val v)
1807 | end
1808 | 
1809 | let i_grapheme_cluster_break v = Grapheme_cluster_break_v begin match v with
1810 | | "CN" -> `CN
1811 | | "CR" -> `CR
1812 | | "EB" -> `EB
1813 | | "EBG" -> `EBG
1814 | | "EM" -> `EM
1815 | | "EX" -> `EX
1816 | | "GAZ" -> `GAZ
1817 | | "L" -> `L
1818 | | "LF" -> `LF
1819 | | "LV" -> `LV
1820 | | "LVT" -> `LVT
1821 | | "PP" -> `PP
1822 | | "RI" -> `RI
1823 | | "SM" -> `SM
1824 | | "T" -> `T
1825 | | "V" -> `V
1826 | | "XX" -> `XX
1827 | | "ZWJ" -> `ZWJ
1828 | | v -> err (err_att_val v)
1829 | end
1830 | 
1831 | let i_hangul_syllable_type v = Hangul_syllable_type_v begin match v with
1832 | | "L" -> `L
1833 | | "LV" -> `LV
1834 | | "LVT" -> `LVT
1835 | | "T" -> `T
1836 | | "V" -> `V
1837 | | "NA" -> `NA
1838 | | v -> err (err_att_val v)
1839 | end
1840 | 
1841 | let i_int v = try Int_v (int_of_string v) with Failure _ -> err (err_att_val v)
1842 | let i_indic_conjunct_break v = Indic_conjunct_break_v begin match v with
1843 | | "Consonant" -> `Consonant
1844 | | "Extend" -> `Extend
1845 | | "Linker" -> `Linker
1846 | | "None" -> `None
1847 | | v -> err (err_att_val v)
1848 | end
1849 | 
1850 | let i_indic_syllabic_category v = Indic_syllabic_category_v begin match v with
1851 | | "Avagraha" -> `Avagraha
1852 | | "Bindu" -> `Bindu
1853 | | "Brahmi_Joining_Number" -> `Brahmi_Joining_Number
1854 | | "Cantillation_Mark" -> `Cantillation_Mark
1855 | | "Consonant" -> `Consonant
1856 | | "Consonant_Dead" -> `Consonant_Dead
1857 | | "Consonant_Final" -> `Consonant_Final
1858 | | "Consonant_Head_Letter" -> `Consonant_Head_Letter
1859 | | "Consonant_Initial_Postfixed" -> `Consonant_Initial_Postfixed
1860 | | "Consonant_Killer" -> `Consonant_Killer
1861 | | "Consonant_Medial" -> `Consonant_Medial
1862 | | "Consonant_Placeholder" -> `Consonant_Placeholder
1863 | | "Consonant_Preceding_Repha" -> `Consonant_Preceding_Repha
1864 | | "Consonant_Prefixed" -> `Consonant_Prefixed
1865 | | "Consonant_Repha" -> `Consonant_Repha
1866 | | "Consonant_Subjoined" -> `Consonant_Subjoined
1867 | | "Consonant_Succeeding_Repha" -> `Consonant_Succeeding_Repha
1868 | | "Consonant_With_Stacker" -> `Consonant_With_Stacker
1869 | | "Gemination_Mark" -> `Gemination_Mark
1870 | | "Invisible_Stacker" -> `Invisible_Stacker
1871 | | "Joiner" -> `Joiner
1872 | | "Modifying_Letter" -> `Modifying_Letter
1873 | | "Non_Joiner" -> `Non_Joiner
1874 | | "Nukta" -> `Nukta
1875 | | "Number" -> `Number
1876 | | "Number_Joiner" -> `Number_Joiner
1877 | | "Other" -> `Other
1878 | | "Pure_Killer" -> `Pure_Killer
1879 | | "Reordering_Killer" -> `Reordering_Killer
1880 | | "Register_Shifter" -> `Register_Shifter
1881 | | "Syllable_Modifier" -> `Syllable_Modifier
1882 | | "Tone_Letter" -> `Tone_Letter
1883 | | "Tone_Mark" -> `Tone_Mark
1884 | | "Virama" -> `Virama
1885 | | "Visarga" -> `Visarga
1886 | | "Vowel" -> `Vowel
1887 | | "Vowel_Dependent" -> `Vowel_Dependent
1888 | | "Vowel_Independent" -> `Vowel_Independent
1889 | | v -> err (err_att_val v)
1890 | end
1891 | 
1892 | let i_indic_matra_category v = Indic_matra_category_v begin match v with
1893 | | "Right" -> `Right
1894 | | "Left" -> `Left
1895 | | "Visual_Order_Left" -> `Visual_Order_Left
1896 | | "Left_And_Right" -> `Left_And_Right
1897 | | "Top" -> `Top
1898 | | "Bottom" -> `Bottom
1899 | | "Top_And_Bottom" -> `Top_And_Bottom
1900 | | "Top_And_Right" -> `Top_And_Right
1901 | | "Top_And_Left" -> `Top_And_Left
1902 | | "Top_And_Left_And_Right" -> `Top_And_Left_And_Right
1903 | | "Bottom_And_Right" -> `Bottom_And_Right
1904 | | "Top_And_Bottom_And_Right" -> `Top_And_Bottom_And_Right
1905 | | "Overstruck" -> `Overstruck
1906 | | "Invisible" -> `Invisible
1907 | | "NA" -> `NA
1908 | | v -> err (err_att_val v)
1909 | end
1910 | 
1911 | let i_indic_positional_category v = Indic_positional_category_v
1912 | begin match v with
1913 | | "Bottom" -> `Bottom
1914 | | "Bottom_And_Left" -> `Bottom_And_Right
1915 | | "Bottom_And_Right" -> `Bottom_And_Right
1916 | | "Invisible" -> `Invisible
1917 | | "Left" -> `Left
1918 | | "Left_And_Right" -> `Left_And_Right
1919 | | "NA" -> `NA
1920 | | "Overstruck" -> `Overstruck
1921 | | "Right" -> `Right
1922 | | "Top" -> `Top
1923 | | "Top_And_Bottom" -> `Top_And_Bottom
1924 | | "Top_And_Bottom_And_Left" -> `Top_And_Bottom_And_Left
1925 | | "Top_And_Bottom_And_Right" -> `Top_And_Bottom_And_Right
1926 | | "Top_And_Left" -> `Top_And_Left
1927 | | "Top_And_Left_And_Right" -> `Top_And_Left_And_Right
1928 | | "Top_And_Right" -> `Top_And_Right
1929 | | "Visual_Order_Left" -> `Visual_Order_Left
1930 | | v -> err (err_att_val v)
1931 | end
1932 | 
1933 | let i_joining_group v = Joining_group_v begin match v with
1934 | | "African_Feh" -> `African_Feh
1935 | | "African_Noon" -> `African_Noon
1936 | | "African_Qaf" -> `African_Qaf
1937 | | "Ain" -> `Ain
1938 | | "Alaph" -> `Alaph
1939 | | "Alef" -> `Alef
1940 | | "Alef_Maqsurah" -> `Alef_Maqsurah
1941 | | "Beh" -> `Beh
1942 | | "Beth" -> `Beth
1943 | | "Burushaski_Yeh_Barree" -> `Burushaski_Yeh_Barree
1944 | | "Dal" -> `Dal
1945 | | "Dalath_Rish" -> `Dalath_Rish
1946 | | "E" -> `E
1947 | | "Farsi_Yeh" -> `Farsi_Yeh
1948 | | "Fe" -> `Fe
1949 | | "Feh" -> `Feh
1950 | | "Final_Semkath" -> `Final_Semkath
1951 | | "Gaf" -> `Gaf
1952 | | "Gamal" -> `Gamal
1953 | | "Hah" -> `Hah
1954 | | "Hanifi_Rohingya_Kinna_Ya" -> `Hanifi_Rohingya_Kinna_Ya
1955 | | "Hanifi_Rohingya_Pa" -> `Hanifi_Rohingya_Pa
1956 | | "Hamza_On_Heh_Goal" -> `Hamza_On_Heh_Goal
1957 | | "He" -> `He
1958 | | "Heh" -> `Heh
1959 | | "Heh_Goal" -> `Heh_Goal
1960 | | "Heth" -> `Heth
1961 | | "Kaf" -> `Kaf
1962 | | "Kaph" -> `Kaph
1963 | | "Kashmiri_Yeh" -> `Kashmiri_Yeh
1964 | | "Khaph" -> `Khaph
1965 | | "Knotted_Heh" -> `Knotted_Heh
1966 | | "Lam" -> `Lam
1967 | | "Lamadh" -> `Lamadh
1968 | | "Malayalam_Bha" -> `Malayalam_Bha
1969 | | "Malayalam_Ja" -> `Malayalam_Ja
1970 | | "Malayalam_Lla" -> `Malayalam_Lla
1971 | | "Malayalam_Llla" -> `Malayalam_Llla
1972 | | "Malayalam_Nna" -> `Malayalam_Nna
1973 | | "Malayalam_Nnna" -> `Malayalam_Nnna
1974 | | "Malayalam_Nya" -> `Malayalam_Nya
1975 | | "Malayalam_Ra" -> `Malayalam_Ra
1976 | | "Malayalam_Ssa" -> `Malayalam_Ssa
1977 | | "Malayalam_Tta" -> `Malayalam_Tta
1978 | | "Malayalam_Nga" -> `Malayalam_Nga
1979 | | "Manichaean_Aleph" -> `Manichaean_Aleph
1980 | | "Manichaean_Ayin" -> `Manichaean_Ayin
1981 | | "Manichaean_Beth" -> `Manichaean_Beth
1982 | | "Manichaean_Daleth" -> `Manichaean_Daleth
1983 | | "Manichaean_Dhamedh" -> `Manichaean_Dhamedh
1984 | | "Manichaean_Five" -> `Manichaean_Five
1985 | | "Manichaean_Gimel" -> `Manichaean_Gimel
1986 | | "Manichaean_Heth" -> `Manichaean_Heth
1987 | | "Manichaean_Hundred" -> `Manichaean_Hundred
1988 | | "Manichaean_Kaph" -> `Manichaean_Kaph
1989 | | "Manichaean_Lamedh" -> `Manichaean_Lamedh
1990 | | "Manichaean_Mem" -> `Manichaean_Mem
1991 | | "Manichaean_Nun" -> `Manichaean_Nun
1992 | | "Manichaean_One" -> `Manichaean_One
1993 | | "Manichaean_Pe" -> `Manichaean_Pe
1994 | | "Manichaean_Qoph" -> `Manichaean_Qoph
1995 | | "Manichaean_Resh" -> `Manichaean_Resh
1996 | | "Manichaean_Sadhe" -> `Manichaean_Sadhe
1997 | | "Manichaean_Samekh" -> `Manichaean_Samekh
1998 | | "Manichaean_Taw" -> `Manichaean_Taw
1999 | | "Manichaean_Ten" -> `Manichaean_Ten
2000 | | "Manichaean_Teth" -> `Manichaean_Teth
2001 | | "Manichaean_Thamedh" -> `Manichaean_Thamedh
2002 | | "Manichaean_Twenty" -> `Manichaean_Twenty
2003 | | "Manichaean_Waw" -> `Manichaean_Waw
2004 | | "Manichaean_Yodh" -> `Manichaean_Yodh
2005 | | "Manichaean_Zayin" -> `Manichaean_Zayin
2006 | | "Meem" -> `Meem
2007 | | "Mim" -> `Mim
2008 | | "No_Joining_Group" -> `No_Joining_Group
2009 | | "Noon" -> `Noon
2010 | | "Nun" -> `Nun
2011 | | "Nya" -> `Nya
2012 | | "Pe" -> `Pe
2013 | | "Qaf" -> `Qaf
2014 | | "Qaph" -> `Qaph
2015 | | "Reh" -> `Reh
2016 | | "Reversed_Pe" -> `Reversed_Pe
2017 | | "Rohingya_Yeh" -> `Rohingya_Yeh
2018 | | "Sad" -> `Sad
2019 | | "Sadhe" -> `Sadhe
2020 | | "Seen" -> `Seen
2021 | | "Semkath" -> `Semkath
2022 | | "Shin" -> `Shin
2023 | | "Straight_Waw" -> `Straight_Waw
2024 | | "Swash_Kaf" -> `Swash_Kaf
2025 | | "Syriac_Waw" -> `Syriac_Waw
2026 | | "Tah" -> `Tah
2027 | | "Taw" -> `Taw
2028 | | "Teh_Marbuta" -> `Teh_Marbuta
2029 | | "Teh_Marbuta_Goal" -> `Teh_Marbuta_Goal
2030 | | "Teth" -> `Teth
2031 | | "Thin_Noon" -> `Thin_Noon
2032 | | "Thin_Yeh" -> `Thin_Yeh
2033 | | "Vertical_Tail" -> `Vertical_Tail
2034 | | "Waw" -> `Waw
2035 | | "Yeh" -> `Yeh
2036 | | "Yeh_Barree" -> `Yeh_Barree
2037 | | "Yeh_With_Tail" -> `Yeh_With_Tail
2038 | | "Yudh" -> `Yudh
2039 | | "Yudh_He" -> `Yudh_He
2040 | | "Zain" -> `Zain
2041 | | "Zhain" -> `Zhain
2042 | | "BAA" -> `BAA
2043 | | "FA" -> `FA
2044 | | "HAA" -> `HAA
2045 | | "HA_GOAL" -> `HA_GOAL
2046 | | "HA" -> `HA
2047 | | "CAF" -> `CAF
2048 | | "KNOTTED_HA" -> `KNOTTED_HA
2049 | | "RA" -> `RA
2050 | | "SWASH_CAF" -> `SWASH_CAF
2051 | | "HAMZAH_ON_HA_GOAL" -> `HAMZAH_ON_HA_GOAL
2052 | | "TAA_MARBUTAH" -> `TAA_MARBUTAH
2053 | | "YA_BARREE" -> `YA_BARREE
2054 | | "YA" -> `YA
2055 | | "ALEF_MAQSURAH " -> `ALEF_MAQSURAH
2056 | | v -> err (err_att_val v)
2057 | end
2058 | 
2059 | let i_joining_type v = Joining_type_v begin match v with
2060 | | "U" -> `U
2061 | | "C" -> `C
2062 | | "T" -> `T
2063 | | "D" -> `D
2064 | | "L" -> `L
2065 | | "R" -> `R
2066 | | v -> err (err_att_val v)
2067 | end
2068 | 
2069 | let i_line_break v = Line_break_v begin match v with
2070 | | "AI" -> `AI
2071 | | "AK" -> `AK
2072 | | "AL" -> `AL
2073 | | "AP" -> `AP
2074 | | "AS" -> `AS
2075 | | "B2" -> `B2
2076 | | "BA" -> `BA
2077 | | "BB" -> `BB
2078 | | "BK" -> `BK
2079 | | "CB" -> `CB
2080 | | "CJ" -> `CJ
2081 | | "CL" -> `CL
2082 | | "CM" -> `CM
2083 | | "CP" -> `CP
2084 | | "CR" -> `CR
2085 | | "EB" -> `EB
2086 | | "EM" -> `EM
2087 | | "EX" -> `EX
2088 | | "GL" -> `GL
2089 | | "H2" -> `H2
2090 | | "H3" -> `H3
2091 | | "HH" -> `HH
2092 | | "HL" -> `HL
2093 | | "HY" -> `HY
2094 | | "ID" -> `ID
2095 | | "IN" -> `IN
2096 | | "IS" -> `IS
2097 | | "JL" -> `JL
2098 | | "JT" -> `JT
2099 | | "JV" -> `JV
2100 | | "LF" -> `LF
2101 | | "NL" -> `NL
2102 | | "NS" -> `NS
2103 | | "NU" -> `NU
2104 | | "OP" -> `OP
2105 | | "PO" -> `PO
2106 | | "PR" -> `PR
2107 | | "QU" -> `QU
2108 | | "RI" -> `RI
2109 | | "SA" -> `SA
2110 | | "SG" -> `SG
2111 | | "SP" -> `SP
2112 | | "SY" -> `SY
2113 | | "VF" -> `VF
2114 | | "VI" -> `VI
2115 | | "WJ" -> `WJ
2116 | | "XX" -> `XX
2117 | | "ZW" -> `ZW
2118 | | "ZWJ" -> `ZWJ
2119 | | v -> err (err_att_val v)
2120 | end
2121 | 
2122 | let i_name v = Name_v (if String.contains v '#' then `Pattern v else `Name v)
2123 | let i_name_alias_type = function
2124 | | "abbreviation" -> `Abbreviation
2125 | | "alternate" -> `Alternate
2126 | | "control" -> `Control
2127 | | "correction" -> `Correction
2128 | | "figment" -> `Figment
2129 | | v -> err (err_att_val v)
2130 | 
2131 | let i_numeric_type v = Numeric_type_v begin match v with
2132 | | "None" -> `None
2133 | | "De" -> `De
2134 | | "Di" -> `Di
2135 | | "Nu" -> `Nu
2136 | | v -> err (err_att_val v)
2137 | end
2138 | 
2139 | let i_numeric_value v = Numeric_value_v begin try match String.trim v with
2140 | |  "NaN" -> `NaN
2141 | | s ->
2142 |     let base s = match split_string (String.trim s) '/' with
2143 |     | [num; denom] -> `Frac (int_of_string num, int_of_string denom)
2144 |     | [num] -> `Num (Int64.of_string num)
2145 |     | _ -> failwith ""
2146 |     in
2147 |     `Nums (List.map base (split_string s ' '))
2148 |   with Failure _ -> err (err_att_val v)
2149 | end
2150 | 
2151 | let i_script v = Script_v begin match v with
2152 | | "Adlm" -> `Adlm
2153 | | "Aghb" -> `Aghb
2154 | | "Ahom" -> `Ahom
2155 | | "Arab" -> `Arab
2156 | | "Armi" -> `Armi
2157 | | "Armn" -> `Armn
2158 | | "Avst" -> `Avst
2159 | | "Bali" -> `Bali
2160 | | "Bamu" -> `Bamu
2161 | | "Bass" -> `Bass
2162 | | "Batk" -> `Batk
2163 | | "Beng" -> `Beng
2164 | | "Berf" -> `Berf
2165 | | "Bhks" -> `Bhks
2166 | | "Bopo" -> `Bopo
2167 | | "Brah" -> `Brah
2168 | | "Brai" -> `Brai
2169 | | "Bugi" -> `Bugi
2170 | | "Buhd" -> `Buhd
2171 | | "Cakm" -> `Cakm
2172 | | "Cans" -> `Cans
2173 | | "Cari" -> `Cari
2174 | | "Cham" -> `Cham
2175 | | "Cher" -> `Cher
2176 | | "Chrs" -> `Chrs
2177 | | "Copt" -> `Copt
2178 | | "Cpmn" -> `Cpmn
2179 | | "Cprt" -> `Cprt
2180 | | "Cyrl" -> `Cyrl
2181 | | "Deva" -> `Deva
2182 | | "Diak" -> `Diak
2183 | | "Dogr" -> `Dogr
2184 | | "Dsrt" -> `Dsrt
2185 | | "Dupl" -> `Dupl
2186 | | "Egyp" -> `Egyp
2187 | | "Elba" -> `Elba
2188 | | "Elym" -> `Elym
2189 | | "Ethi" -> `Ethi
2190 | | "Gara" -> `Gara
2191 | | "Geor" -> `Geor
2192 | | "Glag" -> `Glag
2193 | | "Gong" -> `Gong
2194 | | "Gonm" -> `Gonm
2195 | | "Goth" -> `Goth
2196 | | "Gran" -> `Gran
2197 | | "Grek" -> `Grek
2198 | | "Gujr" -> `Gujr
2199 | | "Gukh" -> `Gukh
2200 | | "Guru" -> `Guru
2201 | | "Hang" -> `Hang
2202 | | "Hani" -> `Hani
2203 | | "Hano" -> `Hano
2204 | | "Hatr" -> `Hatr
2205 | | "Hebr" -> `Hebr
2206 | | "Hira" -> `Hira
2207 | | "Hluw" -> `Hluw
2208 | | "Hmng" -> `Hmng
2209 | | "Hmnp" -> `Hmnp
2210 | | "Hrkt" -> `Hrkt
2211 | | "Hung" -> `Hung
2212 | | "Ital" -> `Ital
2213 | | "Java" -> `Java
2214 | | "Kali" -> `Kali
2215 | | "Kana" -> `Kana
2216 | | "Kawi" -> `Kawi
2217 | | "Khar" -> `Khar
2218 | | "Khmr" -> `Khmr
2219 | | "Khoj" -> `Khoj
2220 | | "Knda" -> `Knda
2221 | | "Krai" -> `Krai
2222 | | "Kthi" -> `Kthi
2223 | | "Kits" -> `Kits
2224 | | "Lana" -> `Lana
2225 | | "Laoo" -> `Laoo
2226 | | "Latn" -> `Latn
2227 | | "Lepc" -> `Lepc
2228 | | "Limb" -> `Limb
2229 | | "Lina" -> `Lina
2230 | | "Linb" -> `Linb
2231 | | "Lisu" -> `Lisu
2232 | | "Lyci" -> `Lyci
2233 | | "Lydi" -> `Lydi
2234 | | "Mahj" -> `Mahj
2235 | | "Maka" -> `Maka
2236 | | "Mand" -> `Mand
2237 | | "Mani" -> `Mani
2238 | | "Marc" -> `Marc
2239 | | "Medf" -> `Medf
2240 | | "Mend" -> `Mend
2241 | | "Merc" -> `Merc
2242 | | "Mero" -> `Mero
2243 | | "Mlym" -> `Mlym
2244 | | "Modi" -> `Modi
2245 | | "Mong" -> `Mong
2246 | | "Mroo" -> `Mroo
2247 | | "Mtei" -> `Mtei
2248 | | "Mult" -> `Mult
2249 | | "Mymr" -> `Mymr
2250 | | "Nagm" -> `Nagm
2251 | | "Nand" -> `Nand
2252 | | "Narb" -> `Narb
2253 | | "Nbat" -> `Nbat
2254 | | "Newa" -> `Newa
2255 | | "Nkoo" -> `Nkoo
2256 | | "Nshu" -> `Nshu
2257 | | "Ogam" -> `Ogam
2258 | | "Olck" -> `Olck
2259 | | "Onao" -> `Onao
2260 | | "Orkh" -> `Orkh
2261 | | "Orya" -> `Orya
2262 | | "Osge" -> `Osge
2263 | | "Osma" -> `Osma
2264 | | "Ougr" -> `Ougr
2265 | | "Palm" -> `Palm
2266 | | "Pauc" -> `Pauc
2267 | | "Perm" -> `Perm
2268 | | "Phag" -> `Phag
2269 | | "Phli" -> `Phli
2270 | | "Phlp" -> `Phlp
2271 | | "Phnx" -> `Phnx
2272 | | "Plrd" -> `Plrd
2273 | | "Prti" -> `Prti
2274 | | "Qaai" -> `Qaai
2275 | | "Rjng" -> `Rjng
2276 | | "Rohg" -> `Rohg
2277 | | "Runr" -> `Runr
2278 | | "Samr" -> `Samr
2279 | | "Sarb" -> `Sarb
2280 | | "Saur" -> `Saur
2281 | | "Sgnw" -> `Sgnw
2282 | | "Shaw" -> `Shaw
2283 | | "Shrd" -> `Shrd
2284 | | "Sidd" -> `Sidd
2285 | | "Sidt" -> `Sidt
2286 | | "Sind" -> `Sind
2287 | | "Sinh" -> `Sinh
2288 | | "Sogd" -> `Sogd
2289 | | "Sogo" -> `Sogo
2290 | | "Sora" -> `Sora
2291 | | "Soyo" -> `Soyo
2292 | | "Sund" -> `Sund
2293 | | "Sunu" -> `Sunu
2294 | | "Sylo" -> `Sylo
2295 | | "Syrc" -> `Syrc
2296 | | "Tagb" -> `Tagb
2297 | | "Takr" -> `Takr
2298 | | "Tale" -> `Tale
2299 | | "Talu" -> `Talu
2300 | | "Taml" -> `Taml
2301 | | "Tang" -> `Tang
2302 | | "Tavt" -> `Tavt
2303 | | "Tayo" -> `Tayo
2304 | | "Telu" -> `Telu
2305 | | "Tfng" -> `Tfng
2306 | | "Tglg" -> `Tglg
2307 | | "Thaa" -> `Thaa
2308 | | "Thai" -> `Thai
2309 | | "Tibt" -> `Tibt
2310 | | "Tirh" -> `Tirh
2311 | | "Tnsa" -> `Tnsa
2312 | | "Todr" -> `Todr
2313 | | "Tols" -> `Tols
2314 | | "Toto" -> `Toto
2315 | | "Tutg" -> `Tutg
2316 | | "Ugar" -> `Ugar
2317 | | "Vaii" -> `Vaii
2318 | | "Vith" -> `Vith
2319 | | "Wara" -> `Wara
2320 | | "Wcho" -> `Wcho
2321 | | "Xpeo" -> `Xpeo
2322 | | "Xsux" -> `Xsux
2323 | | "Yezi" -> `Yezi
2324 | | "Yiii" -> `Yiii
2325 | | "Zanb" -> `Zanb
2326 | | "Zinh" -> `Zinh
2327 | | "Zyyy" -> `Zyyy
2328 | | "Zzzz" -> `Zzzz
2329 | | v -> err (err_att_val v)
2330 | end
2331 | 
2332 | let i_script_seq v =
2333 |   let script v = o_script (i_script v) in
2334 |   Script_extensions_v (List.map script (split_string v ' '))
2335 | 
2336 | let i_sentence_break v = Sentence_break_v begin match v with
2337 | | "AT" -> `AT
2338 | | "CL" -> `CL
2339 | | "CR" -> `CR
2340 | | "EX" -> `EX
2341 | | "FO" -> `FO
2342 | | "LE" -> `LE
2343 | | "LF" -> `LF
2344 | | "LO" -> `LO
2345 | | "NU" -> `NU
2346 | | "SC" -> `SC
2347 | | "SE" -> `SE
2348 | | "SP" -> `SP
2349 | | "ST" -> `ST
2350 | | "UP" -> `UP
2351 | | "XX" -> `XX
2352 | | v -> err (err_att_val v)
2353 | end
2354 | 
2355 | let i_string v = String_v v
2356 | let i_uax_42_element v = UAX_42_element_v begin match v with
2357 | | "reserved" -> `Reserved
2358 | | "noncharacter" -> `Noncharacter
2359 | | "surrogate" -> `Surrogate
2360 | | "char" -> `Char
2361 | | s -> err (err_att_val s)
2362 | end
2363 | 
2364 | let i_vertical_orientation v = Vertical_orientation_v begin match v with
2365 | | "U" -> `U
2366 | | "R" -> `R
2367 | | "Tu" -> `Tu
2368 | | "Tr" -> `Tr
2369 | | s -> err (err_att_val s)
2370 | end
2371 | 
2372 | let i_word_break v = Word_break_v begin match v with
2373 | | "CR" -> `CR
2374 | | "DQ" -> `DQ
2375 | | "EB" -> `EB
2376 | | "EBG" -> `EBG
2377 | | "EM" -> `EM
2378 | | "EX" -> `EX
2379 | | "Extend" -> `Extend
2380 | | "FO" -> `FO
2381 | | "GAZ" -> `GAZ
2382 | | "HL" -> `HL
2383 | | "KA" -> `KA
2384 | | "LE" -> `LE
2385 | | "LF" -> `LF
2386 | | "MB" -> `MB
2387 | | "ML" -> `ML
2388 | | "MN" -> `MN
2389 | | "NL" -> `NL
2390 | | "NU" -> `NU
2391 | | "RI" -> `RI
2392 | | "SQ" -> `SQ
2393 | | "WSegSpace" -> `WSegSpace
2394 | | "XX" -> `XX
2395 | | "ZWJ" -> `ZWJ
2396 | | v -> err (err_att_val v)
2397 | end
2398 | 
2399 | module Pkey = struct type t = key let compare : key -> key -> int = compare end
2400 | module Pmap = Map.Make (Pkey)
2401 | type props = value Pmap.t
2402 | type 'a prop = key * (value -> 'a)     (* property key and value projection. *)
2403 | 
2404 | let find props (k, o) = try Some (o (Pmap.find k props)) with Not_found -> None
2405 | let unknown_prop name = (Other name), o_string
2406 | 
2407 | 
2408 | (* non hunihan and unikemet properties *)
2409 | 
2410 | let uax_42_element = UAX_42_element, o_uax_42_element    (* artefact of Uucd *)
2411 | 
2412 | let age = Age, o_age
2413 | let alphabetic = Alphabetic, o_bool
2414 | let ascii_hex_digit = Ascii_hex_digit, o_bool
2415 | let bidi_class = Bidi_class, o_bidi_class
2416 | let bidi_control = Bidi_control, o_bool
2417 | let bidi_mirrored = Bidi_mirrored, o_bool
2418 | let bidi_mirroring_glyph = Bidi_mirroring_glyph, o_cp_opt
2419 | let bidi_paired_bracket = Bidi_paired_bracket, o_cp_map
2420 | let bidi_paired_bracket_type =
2421 |   Bidi_paired_bracket_type, o_bidi_paired_bracket_type
2422 | 
2423 | let block = Block, o_block
2424 | let canonical_combining_class = Canonical_combining_class, o_int
2425 | let cased = Cased, o_bool
2426 | let case_folding = Case_folding, o_cps_map
2427 | let case_ignorable = Case_ignorable, o_bool
2428 | let changes_when_casefolded = Changes_when_casefolded, o_bool
2429 | let changes_when_casemapped = Changes_when_casemapped, o_bool
2430 | let changes_when_lowercased = Changes_when_lowercased, o_bool
2431 | let changes_when_nfkc_casefolded = Changes_when_nfkc_casefolded, o_bool
2432 | let changes_when_titlecased = Changes_when_titlecased, o_bool
2433 | let changes_when_uppercased = Changes_when_uppercased, o_bool
2434 | let composition_exclusion = Composition_exclusion, o_bool
2435 | let dash = Dash, o_bool
2436 | let decomposition_mapping = Decomposition_mapping, o_cps_map
2437 | let decomposition_type = Decomposition_type, o_decomposition_type
2438 | let default_ignorable_code_point = Default_ignorable_code_point, o_bool
2439 | let deprecated = Deprecated, o_bool
2440 | let diacritic = Diacritic, o_bool
2441 | let east_asian_width = East_asian_width, o_east_asian_width
2442 | let emoji = Emoji, o_bool
2443 | let emoji_presentation = Emoji_presentation, o_bool
2444 | let emoji_modifier = Emoji_modifier, o_bool
2445 | let emoji_modifier_base = Emoji_modifier_base, o_bool
2446 | let emoji_component = Emoji_component, o_bool
2447 | let equivalent_unified_ideograph = Equivalent_unified_ideograph, o_cp_opt
2448 | let extended_pictographic = Extended_pictographic, o_bool
2449 | let extender = Extender, o_bool
2450 | let full_composition_exclusion = Full_composition_exclusion, o_bool
2451 | let general_category = General_category, o_general_category
2452 | let grapheme_base = Grapheme_base, o_bool
2453 | let grapheme_cluster_break = Grapheme_cluster_break, o_grapheme_cluster_break
2454 | let grapheme_extend = Grapheme_extend, o_bool
2455 | let hangul_syllable_type = Hangul_syllable_type, o_hangul_syllable_type
2456 | let hex_digit = Hex_digit, o_bool
2457 | let id_continue = Id_continue, o_bool
2458 | let id_compat_math_continue = Id_compat_math_continue, o_bool
2459 | let id_compat_math_start = Id_compat_math_start, o_bool
2460 | let id_start = Id_start, o_bool
2461 | let ideographic = Ideographic, o_bool
2462 | let ids_binary_operator = Ids_binary_operator, o_bool
2463 | let ids_trinary_operator = Ids_trinary_operator, o_bool
2464 | let ids_unary_operator = Ids_unary_operator, o_bool
2465 | let indic_conjunct_break = Indic_conjunct_break, o_indic_conjunct_break
2466 | let indic_syllabic_category = Indic_syllabic_category, o_indic_syllabic_category
2467 | let indic_matra_category = Indic_matra_category, o_indic_matra_category
2468 | let indic_positional_category =
2469 |   Indic_positional_category, o_indic_positional_category
2470 | let jamo_short_name = Jamo_short_name, o_string
2471 | let join_control = Join_control, o_bool
2472 | let joining_group = Joining_group, o_joining_group
2473 | let joining_type = Joining_type, o_joining_type
2474 | let line_break = Line_break, o_line_break
2475 | let logical_order_exception = Logical_order_exception, o_bool
2476 | let lowercase = Lowercase, o_bool
2477 | let lowercase_mapping = Lowercase_mapping, o_cps_map
2478 | let math = Math, o_bool
2479 | let modifier_combining_mark = Modifier_combining_mark, o_bool
2480 | let name = Name, o_name
2481 | let name_alias = Name_alias, o_name_alias
2482 | let nfc_quick_check = Nfc_quick_check, o_bool_maybe
2483 | let nfd_quick_check = Nfd_quick_check, o_bool_maybe
2484 | let nfkc_quick_check = Nfkc_quick_check, o_bool_maybe
2485 | let nfkc_casefold = Nfkc_casefold, o_cps_map
2486 | let nfkc_simple_casefold = Nfkc_simple_casefold, o_cps_map
2487 | let nfkd_quick_check = Nfkd_quick_check, o_bool_maybe
2488 | let noncharacter_code_point = Noncharacter_code_point, o_bool
2489 | let numeric_type = Numeric_type, o_numeric_type
2490 | let numeric_value = Numeric_value, o_numeric_value
2491 | let other_alphabetic = Other_alphabetic, o_bool
2492 | let other_default_ignorable_code_point =
2493 |   Other_default_ignorable_code_point, o_bool
2494 | 
2495 | let other_grapheme_extend = Other_grapheme_extend, o_bool
2496 | let other_id_continue = Other_id_continue, o_bool
2497 | let other_id_start = Other_id_start, o_bool
2498 | let other_lowercase = Other_lowercase, o_bool
2499 | let other_math = Other_math, o_bool
2500 | let other_uppercase = Other_uppercase, o_bool
2501 | let pattern_syntax = Pattern_syntax, o_bool
2502 | let pattern_white_space = Pattern_white_space, o_bool
2503 | let prepended_concatenation_mark = Prepended_concatenation_mark, o_bool
2504 | let quotation_mark = Quotation_mark, o_bool
2505 | let radical = Radical, o_bool
2506 | let regional_indicator = Regional_indicator, o_bool
2507 | let script = Script, o_script
2508 | let script_extensions = Script_extensions, o_script_extensions
2509 | let sentence_break = Sentence_break, o_sentence_break
2510 | let simple_case_folding = Simple_case_folding, o_cp_map
2511 | let simple_lowercase_mapping = Simple_lowercase_mapping, o_cp_map
2512 | let simple_titlecase_mapping = Simple_titlecase_mapping, o_cp_map
2513 | let simple_uppercase_mapping = Simple_uppercase_mapping, o_cp_map
2514 | let soft_dotted = Soft_dotted, o_bool
2515 | let sterm = Sterm, o_bool
2516 | let terminal_punctuation = Terminal_punctuation, o_bool
2517 | let titlecase_mapping = Titlecase_mapping, o_cps_map
2518 | let unicode_1_name = Unicode_1_name, o_string
2519 | let unified_ideograph = Unified_ideograph, o_bool
2520 | let uppercase = Uppercase, o_bool
2521 | let uppercase_mapping = Uppercase_mapping, o_cps_map
2522 | let variation_selector = Variation_selector, o_bool
2523 | let vertical_orientation = Vertical_orientation, o_vertical_orientation
2524 | let white_space = White_space, o_bool
2525 | let word_break = Word_break, o_word_break
2526 | let xid_continue = Xid_continue, o_bool
2527 | let xid_start = Xid_start, o_bool
2528 | 
2529 | (* unihan properties *)
2530 | 
2531 | let kAccountingNumeric = KAccountingNumeric, o_string
2532 | let kAlternateHanYu = KAlternateHanYu, o_string
2533 | let kAlternateJEF = KAlternateJEF, o_string
2534 | let kAlternateKangXi = KAlternateKangXi, o_string
2535 | let kAlternateMorohashi = KAlternateMorohashi, o_string
2536 | let kAlternateTotalStrokes = KAlternateTotalStrokes, o_string
2537 | let kBigFive = KBigFive, o_string
2538 | let kCCCII = KCCCII, o_string
2539 | let kCNS1986 = KCNS1986, o_string
2540 | let kCNS1992 = KCNS1992, o_string
2541 | let kCangjie = KCangjie, o_string
2542 | let kCantonese = KCantonese, o_string
2543 | let kCheungBauer = KCheungBauer, o_string
2544 | let kCheungBauerIndex = KCheungBauerIndex, o_string
2545 | let kCihaiT = KCihaiT, o_string
2546 | let kCompatibilityVariant = KCompatibilityVariant, o_string
2547 | let kCowles = KCowles, o_string
2548 | let kDaeJaweon = KDaeJaweon, o_string
2549 | let kDefinition = KDefinition, o_string
2550 | let kEACC = KEACC, o_string
2551 | let kFanqie = KFanqie, o_string
2552 | let kFenn = KFenn, o_string
2553 | let kFennIndex = KFennIndex, o_string
2554 | let kFourCornerCode = KFourCornerCode, o_string
2555 | let kFrequency = KFrequency, o_string
2556 | let kGB0 = KGB0, o_string
2557 | let kGB1 = KGB1, o_string
2558 | let kGB3 = KGB3, o_string
2559 | let kGB5 = KGB5, o_string
2560 | let kGB8 = KGB8, o_string
2561 | let kGSR = KGSR, o_string
2562 | let kGradeLevel = KGradeLevel, o_string
2563 | let kHDZRadBreak = KHDZRadBreak, o_string
2564 | let kHKGlyph = KHKGlyph, o_string
2565 | let kHKSCS = KHKSCS, o_string
2566 | let kHanYu = KHanYu, o_string
2567 | let kHangul = KHangul, o_string
2568 | let kHanyuPinlu = KHanyuPinlu, o_string
2569 | let kHanyuPinyin = KHanyuPinyin, o_string
2570 | let kIBMJapan = KIBMJapan, o_string
2571 | let kIICore = KIICore, o_string
2572 | let kIRGDaeJaweon = KIRGDaeJaweon, o_string
2573 | let kIRGDaiKanwaZiten = KIRGDaiKanwaZiten, o_string
2574 | let kIRGHanyuDaZidian = KIRGHanyuDaZidian, o_string
2575 | let kIRGKangXi = KIRGKangXi, o_string
2576 | let kIRG_GSource = KIRG_GSource, o_string
2577 | let kIRG_HSource = KIRG_HSource, o_string
2578 | let kIRG_JSource = KIRG_JSource, o_string
2579 | let kIRG_KPSource = KIRG_KPSource, o_string
2580 | let kIRG_KSource = KIRG_KSource, o_string
2581 | let kIRG_MSource = KIRG_MSource, o_string
2582 | let kIRG_SSource = KIRG_SSource, o_string
2583 | let kIRG_TSource = KIRG_TSource, o_string
2584 | let kIRG_USource = KIRG_USource, o_string
2585 | let kIRG_UKSource = KIRG_UKSource, o_string
2586 | let kIRG_VSource = KIRG_VSource, o_string
2587 | let kJHJ = KJHJ, o_string
2588 | let kJIS0213 = KJIS0213, o_string
2589 | let kJapanese = KJapanese, o_string
2590 | let kJapaneseKun = KJapaneseKun, o_string
2591 | let kJapaneseOn = KJapaneseOn, o_string
2592 | let kJinmeiyoKanji = KJinmeiyoKanji, o_string
2593 | let kJis0 = KJis0, o_string
2594 | let kJis1 = KJis1, o_string
2595 | let kJoyoKanji = KJoyoKanji, o_string
2596 | let kKPS0 = KKPS0, o_string
2597 | let kKPS1 = KKPS1, o_string
2598 | let kKSC0 = KKSC0, o_string
2599 | let kKSC1 = KKSC1, o_string
2600 | let kKangXi = KKangXi, o_string
2601 | let kKarlgren = KKarlgren, o_string
2602 | let kKorean = KKorean, o_string
2603 | let kKoreanEducationHanja = KKoreanEducationHanja, o_string
2604 | let kKoreanName = KKoreanName, o_string
2605 | let kLau = KLau, o_string
2606 | let kMainlandTelegraph = KMainlandTelegraph, o_string
2607 | let kMandarin = KMandarin, o_string
2608 | let kMatthews = KMatthews, o_string
2609 | let kMeyerWempe = KMeyerWempe, o_string
2610 | let kMojiJoho = KMojiJoho, o_string
2611 | let kMorohashi = KMorohashi, o_string
2612 | let kNelson = KNelson, o_string
2613 | let kNSHU_DubenSrc = KNSHU_DubenSrc, o_string
2614 | let kNSHU_Reading = KNSHU_Reading, o_string
2615 | let kOtherNumeric = KOtherNumeric, o_string
2616 | let kPhonetic = KPhonetic, o_string
2617 | let kPrimaryNumeric = KPrimaryNumeric, o_string
2618 | let kPseudoGB1 = KPseudoGB1, o_string
2619 | let kRSAdobe_Japan1_6 = KRSAdobe_Japan1_6, o_string
2620 | let kRSJapanese = KRSJapanese, o_string
2621 | let kRSKanWa = KRSKanWa, o_string
2622 | let kRSKangXi = KRSKangXi, o_string
2623 | let kRSKorean = KRSKorean, o_string
2624 | let kRSMerged = KRSMerged, o_string
2625 | let kRSUnicode = KRSUnicode, o_string
2626 | let kSBGY = KSBGY, o_string
2627 | let kSemanticVariant = KSemanticVariant, o_string
2628 | let kSimplifiedVariant = KSimplifiedVariant, o_string
2629 | let kSMSZD2003Index = KSMSZD2003Index, o_string
2630 | let kSMSZD2003Readings = KSMSZD2003Readings, o_string
2631 | let kSpecializedSemanticVariant = KSpecializedSemanticVariant, o_string
2632 | let kSpoofingVariant = KSpoofingVariant, o_string
2633 | let kStrange = KStrange, o_string
2634 | let kTGH = KTGH, o_string
2635 | let kTGHZ2013 = KTGHZ2013, o_string
2636 | let kTGT_MergedSrc = KTGT_MergedSrc, o_string
2637 | let kTGT_RSUnicode = KTGT_RSUnicode, o_string
2638 | let kTaiwanTelegraph = KTaiwanTelegraph, o_string
2639 | let kTang = KTang, o_string
2640 | let kTayNumeric = KTayNumeric, o_string
2641 | let kTotalStrokes = KTotalStrokes, o_string
2642 | let kTraditionalVariant = KTraditionalVariant, o_string
2643 | let kUnihanCore2020 = KUnihanCore2020, o_string
2644 | let kVietnamese = KVietnamese, o_string
2645 | let kVietnameseNumeric = KVietnameseNumeric, o_string
2646 | let kWubi = KWubi, o_string
2647 | let kXHC1983 = KXHC1983, o_string
2648 | let kXerox = KXerox, o_string
2649 | let kZhuang = KZhuang, o_string
2650 | let kZhuangNumeric = KZhuangNumeric, o_string
2651 | let kZVariant = KZVariant, o_string
2652 | 
2653 | (* Unikemet properties *)
2654 | 
2655 | let kEH_Cat = KEH_Cat, o_string
2656 | let kEH_Core = KEH_Core, o_string
2657 | let kEH_Desc = KEH_Desc, o_string
2658 | let kEH_Func = KEH_Func, o_string
2659 | let kEH_FVal = KEH_FVal, o_string
2660 | let kEH_UniK = KEH_UniK, o_string
2661 | let kEH_JSesh = KEH_JSesh, o_string
2662 | let kEH_HG = KEH_HG, o_string
2663 | let kEH_IFAO = KEH_IFAO, o_string
2664 | let kEH_NoMirror = KEH_NoMirror, o_bool
2665 | let kEH_NoRotate = KEH_NoRotate, o_bool
2666 | let kEH_AltSeq = KEH_AltSeq, o_string
2667 | 
2668 | 
2669 | (* Unicode Character Databases *)
2670 | 
2671 | type block = (cp * cp) * string
2672 | type named_sequence = string * cp list
2673 | type standardized_variant =
2674 |   cp list * string * [ `Isolate | `Initial | `Medial | `Final ] list
2675 | 
2676 | type cjk_radical = string * cp * cp
2677 | type do_not_emit = { instead_of : cp list; use : cp list; because : string; }
2678 | 
2679 | type t =
2680 |   { description : string;
2681 |     repertoire : props Cpmap.t;
2682 |     blocks : block list;
2683 |     named_sequences : named_sequence list;
2684 |     provisional_named_sequences : named_sequence list;
2685 |     standardized_variants : standardized_variant list;
2686 |     cjk_radicals : cjk_radical list;
2687 |     do_not_emit : do_not_emit list; }
2688 | 
2689 | let cp_props db cp =
2690 |   try Some (Cpmap.find cp db.repertoire) with Not_found -> None
2691 | 
2692 | let cp_prop db cp p = try find (Cpmap.find cp db.repertoire) p
2693 | with Not_found -> None
2694 | 
2695 | (* Decode *)
2696 | 
2697 | (* Xml names *)
2698 | 
2699 | let ns_ucd = "http://www.unicode.org/ns/2003/ucd/1.0"
2700 | let n_block = (ns_ucd, "block")
2701 | let n_blocks = (ns_ucd, "blocks")
2702 | let n_char = (ns_ucd, "char")
2703 | let n_cjk_radical = (ns_ucd, "cjk-radical")
2704 | let n_cjk_radicals = (ns_ucd, "cjk-radicals")
2705 | let n_do_not_emit = (ns_ucd, "do-not-emit")
2706 | let n_description = (ns_ucd, "description")
2707 | let n_group = (ns_ucd, "group")
2708 | let n_instead = (ns_ucd, "instead")
2709 | let n_name_alias = (ns_ucd, "name-alias")
2710 | let n_named_sequence = (ns_ucd, "named-sequence")
2711 | let n_named_sequences = (ns_ucd, "named-sequences")
2712 | let n_noncharacter = (ns_ucd, "noncharacter")
2713 | let n_provisional_named_sequences = (ns_ucd, "provisional-named-sequences")
2714 | let n_repertoire = (ns_ucd, "repertoire")
2715 | let n_reserved = (ns_ucd, "reserved")
2716 | let n_standardized_variant = (ns_ucd, "standardized-variant")
2717 | let n_standardized_variants = (ns_ucd, "standardized-variants")
2718 | let n_surrogate = (ns_ucd, "surrogate")
2719 | let n_ucd = (ns_ucd, "ucd")
2720 | 
2721 | (* Attribute parsing *)
2722 | 
2723 | let add_prop : value Pmap.t -> Xmlm.attribute -> value Pmap.t =
2724 |   let h = Hashtbl.create 500 in
2725 |   let map = Hashtbl.add h in
2726 |   map "AHex" (Ascii_hex_digit, i_bool);
2727 |   map "Alpha" (Alphabetic, i_bool);
2728 |   map "Bidi_C" (Bidi_control, i_bool);
2729 |   map "Bidi_M" (Bidi_mirrored, i_bool);
2730 |   map "Cased" (Cased, i_bool);
2731 |   map "CI" (Case_ignorable, i_bool);
2732 |   map "CE" (Composition_exclusion, i_bool);
2733 |   map "CWCF" (Changes_when_casefolded, i_bool);
2734 |   map "CWCM" (Changes_when_casemapped, i_bool);
2735 |   map "CWL" (Changes_when_lowercased, i_bool);
2736 |   map "CWKCF" (Changes_when_nfkc_casefolded, i_bool);
2737 |   map "CWT" (Changes_when_titlecased, i_bool);
2738 |   map "CWU" (Changes_when_uppercased, i_bool);
2739 |   map "Comp_Ex" (Full_composition_exclusion, i_bool);
2740 |   map "DI" (Default_ignorable_code_point, i_bool);
2741 |   map "Dash" (Dash, i_bool);
2742 |   map "Dep" (Deprecated, i_bool);
2743 |   map "Dia" (Diacritic, i_bool);
2744 |   map "EqUIdeo" (Equivalent_unified_ideograph, i_cp_opt);
2745 |   map "Ext" (Extender, i_bool);
2746 |   map "GCB" (Grapheme_cluster_break, i_grapheme_cluster_break);
2747 |   map "Gr_Base" (Grapheme_base, i_bool);
2748 |   map "Gr_Ext" (Grapheme_extend, i_bool);
2749 |   map "Hex" (Hex_digit, i_bool);
2750 |   map "ID_Compat_Math_Continue" (Id_compat_math_continue, i_bool);
2751 |   map "ID_Compat_Math_Start" (Id_compat_math_start, i_bool);
2752 |   map "IDC" (Id_continue, i_bool);
2753 |   map "IDS" (Id_start, i_bool);
2754 |   map "IDSB" (Ids_binary_operator, i_bool);
2755 |   map "IDST" (Ids_trinary_operator, i_bool);
2756 |   map "IDSU" (Ids_unary_operator, i_bool);
2757 |   map "Ideo" (Ideographic, i_bool);
2758 |   map "InCB" (Indic_conjunct_break, i_indic_conjunct_break);
2759 |   map "InSC" (Indic_syllabic_category, i_indic_syllabic_category);
2760 |   map "InMC" (Indic_matra_category, i_indic_matra_category);
2761 |   map "InPC" (Indic_positional_category, i_indic_positional_category);
2762 |   map "JSN" (Jamo_short_name, i_string);
2763 |   map "Join_C" (Join_control, i_bool);
2764 |   map "LOE" (Logical_order_exception, i_bool);
2765 |   map "Lower" (Lowercase, i_bool);
2766 |   map "Math" (Math, i_bool);
2767 |   map "MCM" (Modifier_combining_mark, i_bool);
2768 |   map "NChar" (Noncharacter_code_point, i_bool);
2769 |   map "NFC_QC" (Nfc_quick_check, i_bool_maybe);
2770 |   map "NFD_QC" (Nfd_quick_check, i_bool_maybe);
2771 |   map "NFKC_QC" (Nfkc_quick_check, i_bool_maybe);
2772 |   map "NFKC_CF" (Nfkc_casefold, i_cps_map ~empty:true);
2773 |   map "NFKC_SCF" (Nfkc_simple_casefold, i_cps_map ~empty:true);
2774 |   map "NFKD_QC" (Nfkd_quick_check, i_bool_maybe);
2775 |   map "OAlpha" (Other_alphabetic, i_bool);
2776 |   map "ODI" (Other_default_ignorable_code_point, i_bool);
2777 |   map "OGr_Ext" (Other_grapheme_extend, i_bool);
2778 |   map "OIDC" (Other_id_continue, i_bool);
2779 |   map "OIDS" (Other_id_start, i_bool);
2780 |   map "OLower" (Other_lowercase, i_bool);
2781 |   map "OMath" (Other_math, i_bool);
2782 |   map "OUpper" (Other_uppercase, i_bool);
2783 |   map "Pat_Syn" (Pattern_syntax, i_bool);
2784 |   map "Pat_WS" (Pattern_white_space, i_bool);
2785 |   map "PCM" (Prepended_concatenation_mark, i_bool);
2786 |   map "QMark" (Quotation_mark, i_bool);
2787 |   map "Radical" (Radical, i_bool);
2788 |   map "RI" (Regional_indicator, i_bool);
2789 |   map "SB" (Sentence_break, i_sentence_break);
2790 |   map "SD" (Soft_dotted, i_bool);
2791 |   map "STerm" (Sterm, i_bool);
2792 |   map "Term" (Terminal_punctuation, i_bool);
2793 |   map "UIdeo" (Unified_ideograph, i_bool);
2794 |   map "Upper" (Uppercase, i_bool);
2795 |   map "VS" (Variation_selector, i_bool);
2796 |   map "vo" (Vertical_orientation, i_vertical_orientation);
2797 |   map "WB" (Word_break, i_word_break);
2798 |   map "WSpace" (White_space, i_bool);
2799 |   map "XIDC" (Xid_continue, i_bool);
2800 |   map "XIDS" (Xid_start, i_bool);
2801 |   map "age" (Age, i_age);
2802 |   map "bc" (Bidi_class, i_bidi_class);
2803 |   map "blk" (Block, i_block);
2804 |   map "bmg" (Bidi_mirroring_glyph, i_cp_opt);
2805 |   map "bpb" (Bidi_paired_bracket, i_cp_map);
2806 |   map "bpt" (Bidi_paired_bracket_type, i_bidi_paired_bracket_type);
2807 |   map "ccc" (Canonical_combining_class, i_int);
2808 |   map "cf" (Case_folding, i_cps_map ~empty:false);
2809 |   map "dm" (Decomposition_mapping,  (i_cps_map ~empty:true));
2810 |   map "dt" (Decomposition_type, i_decomposition_type);
2811 |   map "ea" (East_asian_width, i_east_asian_width);
2812 |   map "Emoji" (Emoji, i_bool);
2813 |   map "EPres" (Emoji_presentation, i_bool);
2814 |   map "EMod" (Emoji_modifier, i_bool);
2815 |   map "EBase" (Emoji_modifier_base, i_bool);
2816 |   map "EComp" (Emoji_component, i_bool);
2817 |   map "ExtPict" (Extended_pictographic, i_bool);
2818 |   map "gc" (General_category, i_general_category);
2819 |   map "hst" (Hangul_syllable_type, i_hangul_syllable_type);
2820 |   map "jg" (Joining_group, i_joining_group);
2821 |   map "jt" (Joining_type, i_joining_type);
2822 |   map "lb" (Line_break, i_line_break);
2823 |   map "lc" (Lowercase_mapping, i_cps_map ~empty:false);
2824 |   map "na" (Name, i_name);
2825 |   map "na1" (Unicode_1_name, i_string);
2826 |   map "nt" (Numeric_type, i_numeric_type);
2827 |   map "nv" (Numeric_value, i_numeric_value);
2828 |   map "sc" (Script, i_script);
2829 |   map "scf" (Simple_case_folding, i_cp_map);
2830 |   map "scx" (Script_extensions, i_script_seq);
2831 |   map "slc" (Simple_lowercase_mapping, i_cp_map);
2832 |   map "stc" (Simple_titlecase_mapping, i_cp_map);
2833 |   map "suc" (Simple_uppercase_mapping, i_cp_map);
2834 |   map "tc" (Titlecase_mapping, i_cps_map ~empty:false);
2835 |   map "uax_42_element" (UAX_42_element, i_uax_42_element);       (* artefact *)
2836 |   map "uc" (Uppercase_mapping, i_cps_map ~empty:false);
2837 |   map "kAccountingNumeric" (KAccountingNumeric, i_string);
2838 |   map "kAlternateHanYu" (KAlternateHanYu, i_string);
2839 |   map "kAlternateJEF" (KAlternateJEF, i_string);
2840 |   map "kAlternateKangXi" (KAlternateKangXi, i_string);
2841 |   map "kAlternateMorohashi" (KAlternateMorohashi, i_string);
2842 |   map "kBigFive" (KBigFive, i_string);
2843 |   map "kCCCII" (KCCCII, i_string);
2844 |   map "kCNS1986" (KCNS1986, i_string);
2845 |   map "kCNS1992" (KCNS1992, i_string);
2846 |   map "kCangjie" (KCangjie, i_string);
2847 |   map "kCantonese" (KCantonese, i_string);
2848 |   map "kCheungBauer" (KCheungBauer, i_string);
2849 |   map "kCheungBauerIndex" (KCheungBauerIndex, i_string);
2850 |   map "kCihaiT" (KCihaiT, i_string);
2851 |   map "kCompatibilityVariant" (KCompatibilityVariant, i_string);
2852 |   map "kCowles" (KCowles, i_string);
2853 |   map "kDaeJaweon" (KDaeJaweon, i_string);
2854 |   map "kDefinition" (KDefinition, i_string);
2855 |   map "kEACC" (KEACC, i_string);
2856 |   map "kFanqie" (KFanqie, i_string);
2857 |   map "kFenn" (KFenn, i_string);
2858 |   map "kFennIndex" (KFennIndex, i_string);
2859 |   map "kFourCornerCode" (KFourCornerCode, i_string);
2860 |   map "kFrequency" (KFrequency, i_string);
2861 |   map "kGB0" (KGB0, i_string);
2862 |   map "kGB1" (KGB1, i_string);
2863 |   map "kGB3" (KGB3, i_string);
2864 |   map "kGB5" (KGB5, i_string);
2865 |   map "kGB8" (KGB8, i_string);
2866 |   map "kGSR" (KGSR, i_string);
2867 |   map "kGradeLevel" (KGradeLevel, i_string);
2868 |   map "kHDZRadBreak" (KHDZRadBreak, i_string);
2869 |   map "kHKGlyph" (KHKGlyph, i_string);
2870 |   map "kHKSCS" (KHKSCS, i_string);
2871 |   map "kHanYu" (KHanYu, i_string);
2872 |   map "kHangul" (KHangul, i_string);
2873 |   map "kHanyuPinlu" (KHanyuPinlu, i_string);
2874 |   map "kHanyuPinyin" (KHanyuPinyin, i_string);
2875 |   map "kIBMJapan" (KIBMJapan, i_string);
2876 |   map "kIICore" (KIICore, i_string);
2877 |   map "kIRGDaeJaweon" (KIRGDaeJaweon, i_string);
2878 |   map "kIRGDaiKanwaZiten" (KIRGDaiKanwaZiten, i_string);
2879 |   map "kIRGHanyuDaZidian" (KIRGHanyuDaZidian, i_string);
2880 |   map "kIRGKangXi" (KIRGKangXi, i_string);
2881 |   map "kIRG_GSource" (KIRG_GSource, i_string);
2882 |   map "kIRG_HSource" (KIRG_HSource, i_string);
2883 |   map "kIRG_JSource" (KIRG_JSource, i_string);
2884 |   map "kIRG_KPSource" (KIRG_KPSource, i_string);
2885 |   map "kIRG_KSource" (KIRG_KSource, i_string);
2886 |   map "kIRG_MSource" (KIRG_MSource, i_string);
2887 |   map "kIRG_SSource" (KIRG_SSource, i_string);
2888 |   map "kIRG_TSource" (KIRG_TSource, i_string);
2889 |   map "kIRG_USource" (KIRG_USource, i_string);
2890 |   map "kIRG_UKSource" (KIRG_UKSource, i_string);
2891 |   map "kIRG_VSource" (KIRG_VSource, i_string);
2892 |   map "kJapanese" (KJapanese, i_string);
2893 |   map "kJHJ" (KJHJ, i_string);
2894 |   map "kJIS0213" (KJIS0213, i_string);
2895 |   map "kJapaneseKun" (KJapaneseKun, i_string);
2896 |   map "kJapaneseOn" (KJapaneseOn, i_string);
2897 |   map "kJinmeiyoKanji" (KJinmeiyoKanji, i_string);
2898 |   map "kJis0" (KJis0, i_string);
2899 |   map "kJis1" (KJis1, i_string);
2900 |   map "kJoyoKanji"  (KJoyoKanji, i_string);
2901 |   map "kKPS0" (KKPS0, i_string);
2902 |   map "kKPS1" (KKPS1, i_string);
2903 |   map "kKSC0" (KKSC0, i_string);
2904 |   map "kKSC1" (KKSC1, i_string);
2905 |   map "kKangXi" (KKangXi, i_string);
2906 |   map "kKarlgren" (KKarlgren, i_string);
2907 |   map "kKorean" (KKorean, i_string);
2908 |   map "kKoreanEducationHanja" (KKoreanEducationHanja, i_string);
2909 |   map "kKoreanName" (KKoreanName, i_string);
2910 |   map "kLau" (KLau, i_string);
2911 |   map "kMainlandTelegraph" (KMainlandTelegraph, i_string);
2912 |   map "kMandarin" (KMandarin, i_string);
2913 |   map "kMatthews" (KMatthews, i_string);
2914 |   map "kMeyerWempe" (KMeyerWempe, i_string);
2915 |   map "kMorohashi" (KMorohashi, i_string);
2916 |   map "kNelson" (KNelson, i_string);
2917 |   map "kNSHU_DubenSrc" (KNSHU_DubenSrc, i_string);
2918 |   map "kNSHU_Reading" (KNSHU_Reading, i_string);
2919 |   map "kOtherNumeric" (KOtherNumeric, i_string);
2920 |   map "kPhonetic" (KPhonetic, i_string);
2921 |   map "kPrimaryNumeric" (KPrimaryNumeric, i_string);
2922 |   map "kPseudoGB1" (KPseudoGB1, i_string);
2923 |   map "kRSAdobe_Japan1_6" (KRSAdobe_Japan1_6, i_string);
2924 |   map "kRSJapanese" (KRSJapanese, i_string);
2925 |   map "kRSKanWa" (KRSKanWa, i_string);
2926 |   map "kRSKangXi" (KRSKangXi, i_string);
2927 |   map "kRSKorean" (KRSKorean, i_string);
2928 |   map "kRSMerged" (KRSMerged, i_string);
2929 |   map "kRSUnicode" (KRSUnicode, i_string);
2930 |   map "kSBGY" (KSBGY, i_string);
2931 |   map "kSemanticVariant" (KSemanticVariant, i_string);
2932 |   map "kSimplifiedVariant" (KSimplifiedVariant, i_string);
2933 |   map "kSMSZD2003Index" (KSMSZD2003Index, i_string);
2934 |   map "kSMSZD2003Readings" (KSMSZD2003Readings, i_string);
2935 |   map "kSpecializedSemanticVariant" (KSpecializedSemanticVariant, i_string);
2936 |   map "kSpoofingVariant" (KSpoofingVariant, i_string);
2937 |   map "kTGH" (KTGH, i_string);
2938 |   map "kTGHZ2013" (KTGHZ2013, i_string);
2939 |   map "kTGT_MergedSrc" (KTGT_MergedSrc, i_string);
2940 |   map "kTGT_RSUnicode" (KTGT_RSUnicode, i_string);
2941 |   map "kTaiwanTelegraph" (KTaiwanTelegraph, i_string);
2942 |   map "kTang" (KTang, i_string);
2943 |   map "kTayNumeric" (KTayNumeric, i_string);
2944 |   map "kTotalStrokes" (KTotalStrokes, i_string);
2945 |   map "kTraditionalVariant" (KTraditionalVariant, i_string);
2946 |   map "kVietnamese" (KVietnamese, i_string);
2947 |   map "kVietnameseNumeric" (KVietnameseNumeric, i_string);
2948 |   map "kWubi" (KWubi, i_string);
2949 |   map "kXHC1983" (KXHC1983, i_string);
2950 |   map "kXerox" (KXerox, i_string);
2951 |   map "kZhuang" (KZhuang, i_string);
2952 |   map "kZhuangNumeric" (KZhuangNumeric, i_string);
2953 |   map "kZVariant" (KZVariant, i_string);
2954 |   map "kEH_Cat" (KEH_Cat, i_string);
2955 |   map "kEH_Core" (KEH_Core, i_string);
2956 |   map "kEH_Desc" (KEH_Desc, i_string);
2957 |   map "kEH_Func" (KEH_Func, i_string);
2958 |   map "kEH_FVal" (KEH_FVal, i_string);
2959 |   map "kEH_UniK" (KEH_UniK, i_string);
2960 |   map "kEH_JSesh" (KEH_JSesh, i_string);
2961 |   map "kEH_HG" (KEH_HG, i_string);
2962 |   map "kEH_IFAO" (KEH_IFAO, i_string);
2963 |   map "kEH_NoMirror" (KEH_NoMirror, i_bool);
2964 |   map "kEH_NoRotate" (KEH_NoRotate, i_bool);
2965 |   map "kEH_AltSeq" (KEH_AltSeq, i_string);
2966 |   fun m (n, v) ->
2967 |     try match n with
2968 |     | ("", p) ->
2969 |         let k, conv = Hashtbl.find h p in
2970 |         Pmap.add k (conv v) m
2971 |     | _ -> raise Not_found
2972 |     with Not_found -> Pmap.add (Other n) (i_string v) m
2973 | 
2974 | let attv n atts =               (* value of attribute [n] in atts or raises. *)
2975 |   try snd (List.find (fun (en, v) -> en = ("", n)) atts) with
2976 |   | Not_found -> err_miss_att n
2977 | 
2978 | let rec skip_el d =             (* skips an element, start signal was input. *)
2979 |   let rec loop d depth = match Xmlm.input d with
2980 |   | `El_start _ -> loop d (depth + 1)
2981 |   | `El_end -> if depth = 0 then () else loop d (depth - 1)
2982 |   | s -> loop d depth
2983 |   in
2984 |   loop d 0
2985 | 
2986 | (* Parses a sequence of empty elements named n and a El_end. *)
2987 | let p_seq n p_atts d =
2988 |   let rec aux n p_atts d acc = match Xmlm.input d with
2989 |   | `El_start (n', atts) when n' = n ->
2990 |       if Xmlm.input d <> `El_end then err err_exp_el_end else
2991 |       aux n p_atts d ((p_atts atts) :: acc);
2992 |   | `El_start _ -> skip_el d; aux n p_atts d acc
2993 |   | `El_end -> List.rev acc
2994 |   | `Data _ -> err err_data
2995 |   | _ -> assert false
2996 |   in
2997 |   aux n p_atts d []
2998 | 
2999 | let p_description d = match (Xmlm.input d) with
3000 | | `Data desc -> if (Xmlm.input d <> `El_end) then err err_exp_el_end else desc
3001 | | `El_end -> ""
3002 | | _ -> err err_exp_data
3003 | 
3004 | let p_name_aliases d =
3005 |   let rec loop d depth acc = match Xmlm.peek d with
3006 |   | `El_start (n, atts) when n = n_name_alias ->
3007 |       ignore (Xmlm.input d);
3008 |       let alias = ref "" in
3009 |       let atype = ref None in
3010 |       let p_alias_atts = function
3011 |       | ("", "alias"), v -> alias := v
3012 |       | ("", "type"), v -> atype := Some (i_name_alias_type v)
3013 |       | _ -> ()
3014 |       in
3015 |       List.iter p_alias_atts atts;
3016 |       begin match !atype with None -> err err_invalid_name_alias_spec
3017 |       | Some t -> loop d (depth + 1) ((!alias, t) :: acc)
3018 |       end
3019 |   | `El_start (n, atts) -> ignore (Xmlm.input d); skip_el d; loop d depth acc
3020 |   | `El_end ->
3021 |       if depth = 0 then List.rev acc else
3022 |       (ignore (Xmlm.input d); loop d (depth - 1) acc)
3023 |   | `Data _ -> err err_data
3024 |   | _ -> assert false
3025 |   in
3026 |   loop d 0 []
3027 | 
3028 | let p_cp d rep atts g_props =
3029 |   let cp = ref None in
3030 |   let cp_first = ref None in
3031 |   let cp_last = ref None in
3032 |   let add acc ((n, v) as a) = match n with
3033 |   | ("", "cp") -> cp := Some (cp_of_string v); acc
3034 |   | ("", "first-cp") -> cp_first := Some (cp_of_string v); acc
3035 |   | ("", "last-cp") -> cp_last := Some (cp_of_string v); acc
3036 |   | _ -> add_prop acc a
3037 |   in
3038 |   let props = List.fold_left add g_props atts in
3039 |   let props = Pmap.add Name_alias (Name_alias_v (p_name_aliases d)) props in
3040 |   match !cp with
3041 |   | Some cp -> Cpmap.add cp props rep
3042 |   | None -> match !cp_first, !cp_last with
3043 |     | Some f, Some l ->
3044 |         let rep = ref rep in
3045 |         for cp = f to l do rep := Cpmap.add cp props !rep done;
3046 |         !rep
3047 |     | _ -> err err_invalid_cp_spec
3048 | 
3049 | let p_repertoire d =
3050 |   let eatt t = ("","uax_42_element"), t in (* fake attribute for uniformity *)
3051 |   let rec loop d depth rep g_atts = match Xmlm.input d with
3052 |   | `El_start (n, atts) when n = n_reserved ->
3053 |       loop d (depth + 1) (p_cp d rep (eatt "reserved" :: atts) g_atts) g_atts
3054 |   | `El_start (n, atts) when n = n_noncharacter ->
3055 |       loop d (depth + 1) (p_cp d rep (eatt "noncharacter":: atts) g_atts) g_atts
3056 |   | `El_start (n, atts) when n = n_surrogate ->
3057 |       loop d (depth + 1) (p_cp d rep (eatt "surrogate" :: atts) g_atts) g_atts
3058 |   | `El_start (n, atts) when n = n_char ->
3059 |       loop d (depth + 1) (p_cp d rep (eatt "char" :: atts) g_atts) g_atts
3060 |   | `El_start (n, atts) when n = n_group ->
3061 |       let atts = List.fold_left add_prop Pmap.empty atts in
3062 |       let rep = loop d 0 rep atts in   (* ^ empty: no group hierarchy *)
3063 |       loop d depth rep Pmap.empty
3064 |   | `El_start (n, atts) -> skip_el d; loop d depth rep g_atts (* skip foreign *)
3065 |   | `El_end -> if depth = 0 then rep else loop d (depth - 1) rep g_atts
3066 |   | `Data _ -> err err_data
3067 |   | _ -> assert false
3068 |   in
3069 |   loop d 0 Cpmap.empty Pmap.empty
3070 | 
3071 | let p_blocks d =
3072 |   let b_atts atts =
3073 |     (cp_of_string (attv "first-cp" atts), cp_of_string (attv "last-cp" atts)),
3074 |     attv "name" atts
3075 |   in
3076 |   p_seq n_block b_atts d
3077 | 
3078 | let p_named_sequences d =
3079 |   let ns_atts atts = attv "name" atts, cps_of_string (attv "cps" atts) in
3080 |   p_seq n_named_sequence ns_atts d
3081 | 
3082 | let p_standardized_variants d =
3083 |   let when_of_string v =
3084 |     let w s = match s with
3085 |     | "isolate" -> `Isolate
3086 |     | "initial" -> `Initial
3087 |     | "medial" -> `Medial
3088 |     | "final" -> `Final
3089 |     | s -> err (err_att_val s)
3090 |     in
3091 |     List.map w (split_string v ' ')
3092 |   in
3093 |   let sv_atts atts =
3094 |     cps_of_string (attv "cps" atts),
3095 |     attv "desc" atts,
3096 |     when_of_string (attv "when" atts)
3097 |   in
3098 |   p_seq n_standardized_variant sv_atts d
3099 | 
3100 | let p_cjk_radicals d =
3101 |   let cjk_r_atts atts =
3102 |     attv "number" atts,
3103 |     cp_of_string (attv "radical" atts),
3104 |     cp_of_string (attv "ideograph" atts)
3105 |   in
3106 |   p_seq n_cjk_radical cjk_r_atts d
3107 | 
3108 | let p_do_not_emit d =
3109 |   let instead_atts atts =
3110 |     let instead_of = cps_of_string (attv "of" atts) in
3111 |     let use = cps_of_string (attv "use" atts) in
3112 |     let because = attv "because" atts in
3113 |     { instead_of; use; because }
3114 |   in
3115 |   p_seq n_instead instead_atts d
3116 | 
3117 | let p_ucd d =
3118 |   let description = ref None in
3119 |   let repertoire = ref None in
3120 |   let blocks = ref None in
3121 |   let named_sequences = ref None in
3122 |   let provisional_named_sequences = ref None in
3123 |   let standardized_variants = ref None in
3124 |   let cjk_radicals = ref None in
3125 |   let do_not_emit = ref None in
3126 |   let set n r p d = if !r <> None then err (err_dup n) else r := Some (p d) in
3127 |   while (Xmlm.peek d <> `El_end) do match Xmlm.input d with
3128 |   | `El_start (n, _) when n = n_description ->
3129 |       set n description p_description d
3130 |   | `El_start (n, _) when n = n_repertoire ->
3131 |       set n repertoire p_repertoire d
3132 |   | `El_start (n, _) when n = n_blocks ->
3133 |       set n blocks p_blocks d
3134 |   | `El_start (n, _) when n = n_named_sequences ->
3135 |       set n named_sequences p_named_sequences d
3136 |   | `El_start (n, _) when n = n_provisional_named_sequences ->
3137 |       set n provisional_named_sequences p_named_sequences d
3138 |   | `El_start (n, _) when n = n_standardized_variants ->
3139 |       set n standardized_variants p_standardized_variants d
3140 |   | `El_start (n, _) when n = n_cjk_radicals ->
3141 |       set n cjk_radicals p_cjk_radicals d
3142 |   | `El_start (n, _) when n = n_do_not_emit ->
3143 |       set n do_not_emit p_do_not_emit d
3144 |   | `El_start (n, _) -> skip_el d                        (* foreign markup *)
3145 |   | `Data _ -> err err_data
3146 |   | _ -> assert false
3147 |   done;
3148 |   ignore (Xmlm.input d);
3149 |   if not (Xmlm.eoi d) then err err_wf;
3150 |   let some v default = match v with Some v -> v | None -> default in
3151 |   { description = some !description "";
3152 |     repertoire = some !repertoire Cpmap.empty;
3153 |     blocks = some !blocks [];
3154 |     named_sequences = some !named_sequences [];
3155 |     provisional_named_sequences = some !provisional_named_sequences [];
3156 |     standardized_variants = some !standardized_variants [];
3157 |     cjk_radicals = some !cjk_radicals [];
3158 |     do_not_emit = some !do_not_emit []; }
3159 | 
3160 | type src = [ `Channel of in_channel | `String of string ]
3161 | type decoder = Xmlm.input
3162 | 
3163 | let decoder src =
3164 |   let src = match src with `String s -> `String (0, s) | `Channel _ as s -> s in
3165 |   Xmlm.make_input ~strip:true src
3166 | 
3167 | let decoded_range d = Xmlm.pos d, Xmlm.pos d
3168 | let decode d = try
3169 |   ignore (Xmlm.input d); (* `Dtd *)
3170 |   begin match Xmlm.input d with
3171 |   | `El_start (n, _) when n = n_ucd -> `Ok (p_ucd d)
3172 |   | `El_start (n, _) -> err (err_exp_ucd n)
3173 |   | _ -> assert false
3174 |   end;
3175 | with
3176 | | Failure e -> `Error e | Xmlm.Error (_, e) -> `Error (Xmlm.error_message e)
3177 | 


--------------------------------------------------------------------------------