anil.recoil.org
Punycode (RFC3492) in OCaml
metadata
+17
-1
.gitignore
+17
-1
.gitignore
+1
.ocamlformat
+1
.ocamlformat
···
1
+
version=0.28.1
+53
.tangled/workflows/build.yml
+53
.tangled/workflows/build.yml
···
1
+
when:
2
+
- event: ["push", "pull_request"]
3
+
branch: ["main"]
4
+
5
+
engine: nixery
6
+
7
+
dependencies:
8
+
nixpkgs:
9
+
- shell
10
+
- stdenv
11
+
- findutils
12
+
- binutils
13
+
- libunwind
14
+
- ncurses
15
+
- opam
16
+
- git
17
+
- gawk
18
+
- gnupatch
19
+
- gnum4
20
+
- gnumake
21
+
- gnutar
22
+
- gnused
23
+
- gnugrep
24
+
- diffutils
25
+
- gzip
26
+
- bzip2
27
+
- gcc
28
+
- ocaml
29
+
- pkg-config
30
+
31
+
steps:
32
+
- name: opam
33
+
command: |
34
+
opam init --disable-sandboxing -a -y
35
+
- name: repo
36
+
command: |
37
+
opam repo add aoah https://tangled.org/anil.recoil.org/aoah-opam-repo.git
38
+
- name: switch
39
+
command: |
40
+
opam install . --confirm-level=unsafe-yes --deps-only
41
+
- name: build
42
+
command: |
43
+
opam exec -- dune build -p punycode
44
+
- name: switch-test
45
+
command: |
46
+
opam install . --confirm-level=unsafe-yes --deps-only --with-test
47
+
- name: test
48
+
command: |
49
+
opam exec -- dune runtest --verbose
50
+
- name: doc
51
+
command: |
52
+
opam install -y odoc
53
+
opam exec -- dune build @doc
+15
LICENSE.md
+15
LICENSE.md
···
1
+
ISC License
2
+
3
+
Copyright (c) 2025 Anil Madhavapeddy <anil@recoil.org>
4
+
5
+
Permission to use, copy, modify, and distribute this software for any
6
+
purpose with or without fee is hereby granted, provided that the above
7
+
copyright notice and this permission notice appear in all copies.
8
+
9
+
THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
10
+
WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
11
+
MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
12
+
ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
13
+
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
14
+
ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
15
+
OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+102
README.md
+102
README.md
···
1
+
# puny - RFC 3492 Punycode and IDNA for OCaml
2
+
3
+
High-quality implementation of RFC 3492 (Punycode) with IDNA (Internationalized Domain Names in Applications) support for OCaml. Enables encoding and decoding of internationalized domain names with proper Unicode normalization.
4
+
5
+
## Key Features
6
+
7
+
- **RFC 3492 Punycode**: Complete implementation of the Bootstring algorithm for encoding Unicode in ASCII-compatible form
8
+
- **IDNA Support**: ToASCII and ToUnicode operations per RFC 5891 (IDNA 2008) for internationalized domain names
9
+
- **Unicode Normalization**: Automatic NFC normalization using `uunf` for proper IDNA compliance
10
+
- **Mixed-Case Annotation**: Optional case preservation through Punycode encoding round-trips
11
+
- **Domain Integration**: Native support for the `domain-name` library
12
+
- **Comprehensive Error Handling**: Detailed position tracking and RFC-compliant error reporting
13
+
14
+
## Usage
15
+
16
+
### Basic Punycode Encoding/Decoding
17
+
18
+
```ocaml
19
+
(* Encode a UTF-8 string to Punycode *)
20
+
let encoded = Punycode.encode_utf8 "münchen"
21
+
(* = Ok "mnchen-3ya" *)
22
+
23
+
(* Decode Punycode back to UTF-8 *)
24
+
let decoded = Punycode.decode_utf8 "mnchen-3ya"
25
+
(* = Ok "münchen" *)
26
+
```
27
+
28
+
### Domain Label Operations
29
+
30
+
```ocaml
31
+
(* Encode a domain label with ACE prefix *)
32
+
let label = Punycode.encode_label "münchen"
33
+
(* = Ok "xn--mnchen-3ya" *)
34
+
35
+
(* Decode an ACE-prefixed label *)
36
+
let original = Punycode.decode_label "xn--mnchen-3ya"
37
+
(* = Ok "münchen" *)
38
+
```
39
+
40
+
### IDNA Domain Name Conversion
41
+
42
+
```ocaml
43
+
(* Convert internationalized domain to ASCII for DNS lookup *)
44
+
let ascii_domain = Punycode_idna.to_ascii "münchen.example.com"
45
+
(* = Ok "xn--mnchen-3ya.example.com" *)
46
+
47
+
(* Convert ASCII domain back to Unicode for display *)
48
+
let unicode_domain = Punycode_idna.to_unicode "xn--mnchen-3ya.example.com"
49
+
(* = Ok "münchen.example.com" *)
50
+
```
51
+
52
+
### Working with Unicode Code Points
53
+
54
+
```ocaml
55
+
(* Encode an array of Unicode code points *)
56
+
let codepoints = [| Uchar.of_int 0x4ED6; Uchar.of_int 0x4EEC |]
57
+
let encoded = Punycode.encode codepoints
58
+
(* Result is Punycode string *)
59
+
60
+
(* Decode to code points *)
61
+
let decoded = Punycode.decode "ihqwcrb4cv8a8dqg056pqjye"
62
+
(* Result is Uchar.t array *)
63
+
```
64
+
65
+
### Integration with domain-name Library
66
+
67
+
```ocaml
68
+
(* Convert a Domain_name.t to ASCII *)
69
+
let domain = Domain_name.of_string_exn "münchen.example.com" in
70
+
let ascii = Punycode_idna.domain_to_ascii domain
71
+
(* = Ok (Domain_name for "xn--mnchen-3ya.example.com") *)
72
+
73
+
(* Convert back to Unicode *)
74
+
let unicode = Punycode_idna.domain_to_unicode ascii
75
+
(* = Ok (original domain) *)
76
+
```
77
+
78
+
## Installation
79
+
80
+
```
81
+
opam install puny
82
+
```
83
+
84
+
## Documentation
85
+
86
+
API documentation is available at https://tangled.org/@anil.recoil.org/ocaml-punycode or via:
87
+
88
+
```
89
+
opam install puny
90
+
odig doc puny
91
+
```
92
+
93
+
## References
94
+
95
+
- [RFC 3492](https://datatracker.ietf.org/doc/html/rfc3492) - Punycode: A Bootstring encoding of Unicode for IDNA
96
+
- [RFC 5891](https://datatracker.ietf.org/doc/html/rfc5891) - Internationalized Domain Names in Applications (IDNA): Protocol
97
+
- [RFC 5892](https://datatracker.ietf.org/doc/html/rfc5892) - Unicode Code Points and IDNA
98
+
- [RFC 1035](https://datatracker.ietf.org/doc/html/rfc1035) - Domain Names Implementation and Specification
99
+
100
+
## License
101
+
102
+
ISC
+4
dune
+4
dune
+10
-7
dune-project
+10
-7
dune-project
···
1
-
(lang dune 3.0)
2
-
(name puny)
3
-
(version 0.1.0)
1
+
(lang dune 3.20)
2
+
3
+
(name punycode)
4
4
5
5
(generate_opam_files true)
6
6
7
-
(source (github username/puny))
8
7
(license ISC)
9
-
(authors "Author Name")
10
-
(maintainers "maintainer@example.com")
8
+
(authors "Anil Madhavapeddy")
9
+
(homepage "https://tangled.org/@anil.recoil.org/ocaml-punycode")
10
+
(maintainers "Anil Madhavapeddy <anil@recoil.org>")
11
+
(bug_reports "https://tangled.org/@anil.recoil.org/ocaml-punycode/issues")
12
+
(maintenance_intent "(latest)")
11
13
12
14
(package
13
-
(name puny)
15
+
(name punycode)
14
16
(synopsis "RFC 3492 Punycode and IDNA implementation for OCaml")
15
17
(description
16
18
"A high-quality implementation of RFC 3492 (Punycode) with IDNA support.
···
22
24
(uutf (>= 1.0.0))
23
25
(uunf (>= 15.0.0))
24
26
(domain-name (>= 0.4.0))
27
+
(odoc :with-doc)
25
28
(alcotest :with-test)))
+10
-4
lib/dune
+10
-4
lib/dune
···
1
1
(library
2
-
(name puny)
3
-
(public_name puny)
4
-
(modules punycode punycode_idna)
5
-
(libraries uutf uunf uunf.string domain-name))
2
+
(name punycode)
3
+
(public_name punycode)
4
+
(modules punycode)
5
+
(libraries uutf))
6
+
7
+
(library
8
+
(name punycode_idna)
9
+
(public_name punycode.idna)
10
+
(modules punycode_idna)
11
+
(libraries punycode uunf domain-name))
+5
lib/punycode.ml
+5
lib/punycode.ml
···
1
+
(*---------------------------------------------------------------------------
2
+
Copyright (c) 2025 Anil Madhavapeddy <anil@recoil.org>. All rights reserved.
3
+
SPDX-License-Identifier: ISC
4
+
---------------------------------------------------------------------------*)
5
+
1
6
(* RFC 3492 Punycode Implementation *)
2
7
3
8
(* {1 Bootstring Parameters for Punycode (RFC 3492 Section 5)} *)
+5
lib/punycode.mli
+5
lib/punycode.mli
···
1
+
(*---------------------------------------------------------------------------
2
+
Copyright (c) 2025 Anil Madhavapeddy <anil@recoil.org>. All rights reserved.
3
+
SPDX-License-Identifier: ISC
4
+
---------------------------------------------------------------------------*)
5
+
1
6
(** RFC 3492 Punycode: A Bootstring encoding of Unicode for IDNA.
2
7
3
8
This module implements the Punycode algorithm as specified in
+5
lib/punycode_idna.ml
+5
lib/punycode_idna.ml
···
1
+
(*---------------------------------------------------------------------------
2
+
Copyright (c) 2025 Anil Madhavapeddy <anil@recoil.org>. All rights reserved.
3
+
SPDX-License-Identifier: ISC
4
+
---------------------------------------------------------------------------*)
5
+
1
6
(* IDNA (Internationalized Domain Names in Applications) Implementation *)
2
7
3
8
let max_domain_length = 253
+5
lib/punycode_idna.mli
+5
lib/punycode_idna.mli
···
1
+
(*---------------------------------------------------------------------------
2
+
Copyright (c) 2025 Anil Madhavapeddy <anil@recoil.org>. All rights reserved.
3
+
SPDX-License-Identifier: ISC
4
+
---------------------------------------------------------------------------*)
5
+
1
6
(** IDNA (Internationalized Domain Names in Applications) support.
2
7
3
8
This module provides ToASCII and ToUnicode operations as specified
+7
-8
puny.opam
punycode.opam
+7
-8
puny.opam
punycode.opam
···
1
1
# This file is generated by dune, edit dune-project instead
2
2
opam-version: "2.0"
3
-
version: "0.1.0"
4
3
synopsis: "RFC 3492 Punycode and IDNA implementation for OCaml"
5
4
description: """
6
5
A high-quality implementation of RFC 3492 (Punycode) with IDNA support.
7
6
Provides encoding and decoding of internationalized domain names,
8
7
with proper Unicode normalization and mixed-case annotation support."""
9
-
maintainer: ["maintainer@example.com"]
10
-
authors: ["Author Name"]
8
+
maintainer: ["Anil Madhavapeddy <anil@recoil.org>"]
9
+
authors: ["Anil Madhavapeddy"]
11
10
license: "ISC"
12
-
homepage: "https://github.com/username/puny"
13
-
bug-reports: "https://github.com/username/puny/issues"
11
+
homepage: "https://tangled.org/@anil.recoil.org/ocaml-punycode"
12
+
bug-reports: "https://tangled.org/@anil.recoil.org/ocaml-punycode/issues"
14
13
depends: [
15
14
"ocaml" {>= "4.14.0"}
16
-
"dune" {>= "3.0" & >= "3.0"}
15
+
"dune" {>= "3.20" & >= "3.0"}
17
16
"uutf" {>= "1.0.0"}
18
17
"uunf" {>= "15.0.0"}
19
18
"domain-name" {>= "0.4.0"}
20
-
"alcotest" {with-test}
21
19
"odoc" {with-doc}
20
+
"alcotest" {with-test}
22
21
]
23
22
build: [
24
23
["dune" "subst"] {dev}
···
34
33
"@doc" {with-doc}
35
34
]
36
35
]
37
-
dev-repo: "git+https://github.com/username/puny.git"
36
+
x-maintenance-intent: ["(latest)"]
+1
-1
test/dune
+1
-1
test/dune
+7
-2
test/test_punycode.ml
+7
-2
test/test_punycode.ml
···
1
+
(*---------------------------------------------------------------------------
2
+
Copyright (c) 2025 Anil Madhavapeddy <anil@recoil.org>. All rights reserved.
3
+
SPDX-License-Identifier: ISC
4
+
---------------------------------------------------------------------------*)
5
+
1
6
(* Comprehensive tests for Punycode (RFC 3492) implementation *)
2
7
3
8
open Alcotest
4
-
module Punycode = Puny.Punycode
5
-
module Punycode_idna = Puny.Punycode_idna
9
+
module Punycode = Punycode
10
+
module Punycode_idna = Punycode_idna
6
11
7
12
(* Helper to convert hex code points to Uchar array *)
8
13
let codepoints_of_hex_list hex_list =