anil.recoil.org
OCaml implementation of the Mozilla Public Suffix service
metadata
+183
-27
+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
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.
+63
-11
README.md
+63
-11
README.md
···
1
-
# ocaml-publicsuffix
1
+
# ocaml-publicsuffix - Public Suffix List for OCaml
2
2
3
-
Public Suffix List implementation for OCaml.
3
+
An OCaml library for parsing and querying the Mozilla Public Suffix List (PSL) to determine public suffixes and registrable domains. This library implements the algorithm specified at [publicsuffix.org](https://publicsuffix.org/list/) and provides efficient lookups using a pre-compiled trie data structure.
4
4
5
-
Parse and query the Mozilla Public Suffix List (PSL) to determine public suffixes and registrable domains. Supports ICANN and private domain sections, wildcard rules, and exception rules per the PSL specification.
5
+
## Key Features
6
6
7
-
## Data File
7
+
- **Complete PSL Support**: Handles ICANN and private domain sections
8
+
- **Full Rule Coverage**: Supports normal rules, wildcard rules (e.g., `*.uk`), and exception rules (e.g., `!parliament.uk`)
9
+
- **Efficient Lookups**: Pre-compiled trie structure for fast domain matching
10
+
- **Punycode Support**: Automatic handling of internationalized domain names via the `punycode` library
11
+
- **Type Safety**: Uses the `domain-name` library for validated domain representations
8
12
9
-
The `data/public_suffix_list.dat` file contains the public suffix list data. This file can be fetched from:
13
+
## Usage
10
14
11
-
https://publicsuffix.org/list/public_suffix_list.dat
15
+
```ocaml
16
+
(* Determine the registrable domain (public suffix + one label) *)
17
+
let domain = Domain_name.of_string_exn "www.example.com" in
18
+
match Publicsuffix.registrable_domain domain with
19
+
| Some reg_domain -> Format.printf "Registrable: %a\n" Domain_name.pp reg_domain
20
+
| None -> Format.printf "No registrable domain\n"
21
+
(* Output: Registrable: example.com *)
12
22
13
-
To update the data file to the latest version:
23
+
(* Find the public suffix *)
24
+
match Publicsuffix.public_suffix domain with
25
+
| Some suffix -> Format.printf "Suffix: %a\n" Domain_name.pp suffix
26
+
| None -> Format.printf "No public suffix\n"
27
+
(* Output: Suffix: com *)
14
28
15
-
```bash
16
-
curl -o data/public_suffix_list.dat https://publicsuffix.org/list/public_suffix_list.dat
29
+
(* Check if a domain is itself a public suffix *)
30
+
let is_suffix = Publicsuffix.is_public_suffix domain in
31
+
Format.printf "Is public suffix: %b\n" is_suffix
32
+
(* Output: Is public suffix: false *)
17
33
```
18
34
19
-
## Building
35
+
For domains with wildcards and exceptions:
36
+
37
+
```ocaml
38
+
(* Example with wildcard rule: *.uk *)
39
+
let domain = Domain_name.of_string_exn "example.uk" in
40
+
match Publicsuffix.public_suffix domain with
41
+
| Some suffix -> Format.printf "Suffix: %a\n" Domain_name.pp suffix
42
+
| None -> ()
43
+
(* Output: Suffix: uk *)
44
+
45
+
(* Example with exception rule: !parliament.uk *)
46
+
let domain = Domain_name.of_string_exn "parliament.uk" in
47
+
match Publicsuffix.registrable_domain domain with
48
+
| Some reg_domain -> Format.printf "Registrable: %a\n" Domain_name.pp reg_domain
49
+
| None -> ()
50
+
(* Output: Registrable: parliament.uk *)
51
+
```
52
+
53
+
## Installation
54
+
55
+
```
56
+
opam install publicsuffix
57
+
```
58
+
59
+
## Updating the Public Suffix List Data
60
+
61
+
The `data/public_suffix_list.dat` file contains the PSL data, which is compiled into the library at build time. To update to the latest version:
20
62
21
63
```bash
22
-
opam exec -- dune build @check
64
+
curl -o data/public_suffix_list.dat https://publicsuffix.org/list/public_suffix_list.dat
65
+
opam exec -- dune build
23
66
```
24
67
25
68
## Documentation
69
+
70
+
API documentation is available via:
71
+
72
+
```
73
+
opam install publicsuffix
74
+
odig doc publicsuffix
75
+
```
76
+
77
+
Or build locally:
26
78
27
79
```bash
28
80
opam exec -- dune build @doc
+4
dune
+4
dune
+5
-9
dune-project
+5
-9
dune-project
···
1
-
(lang dune 3.0)
1
+
(lang dune 3.18)
2
2
3
3
(name publicsuffix)
4
-
5
-
(version 0.1.0)
6
4
7
5
(generate_opam_files true)
8
6
9
7
(license ISC)
10
-
11
8
(authors "Anil Madhavapeddy")
12
-
13
-
(maintainers "Anil Madhavapeddy")
14
-
15
-
(source
16
-
(github avsm/ocaml-publicsuffix))
9
+
(homepage "https://tangled.org/@anil.recoil.org/ocaml-publicsuffix")
10
+
(maintainers "Anil Madhavapeddy <anil@recoil.org>")
11
+
(bug_reports "https://tangled.org/@anil.recoil.org/ocaml-publicsuffix/issues")
12
+
(maintenance_intent "(latest)")
17
13
18
14
(package
19
15
(name publicsuffix)
+5
gen/gen_psl.ml
+5
gen/gen_psl.ml
···
1
+
(*---------------------------------------------------------------------------
2
+
Copyright (c) 2025 Anil Madhavapeddy <anil@recoil.org>. All rights reserved.
3
+
SPDX-License-Identifier: ISC
4
+
---------------------------------------------------------------------------*)
5
+
1
6
(* gen_psl.ml - Generate OCaml code from public_suffix_list.dat
2
7
3
8
This parser reads the Public Suffix List and generates OCaml source code
+5
lib/publicsuffix.ml
+5
lib/publicsuffix.ml
···
1
+
(*---------------------------------------------------------------------------
2
+
Copyright (c) 2025 Anil Madhavapeddy <anil@recoil.org>. All rights reserved.
3
+
SPDX-License-Identifier: ISC
4
+
---------------------------------------------------------------------------*)
5
+
1
6
(* publicsuffix.ml - Public Suffix List implementation for OCaml
2
7
3
8
This implements the PSL algorithm as specified at:
+5
lib/publicsuffix.mli
+5
lib/publicsuffix.mli
···
1
+
(*---------------------------------------------------------------------------
2
+
Copyright (c) 2025 Anil Madhavapeddy <anil@recoil.org>. All rights reserved.
3
+
SPDX-License-Identifier: ISC
4
+
---------------------------------------------------------------------------*)
5
+
1
6
(** Public Suffix List implementation for OCaml
2
7
3
8
This library provides functions to query the Mozilla Public Suffix List (PSL)
+5
-6
publicsuffix.opam
+5
-6
publicsuffix.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: "Public Suffix List implementation for OCaml"
5
4
description:
6
5
"Parse and query the Mozilla Public Suffix List (PSL) to determine public suffixes and registrable domains. Supports ICANN and private domain sections, wildcard rules, and exception rules per the PSL specification."
7
-
maintainer: ["Anil Madhavapeddy"]
6
+
maintainer: ["Anil Madhavapeddy <anil@recoil.org>"]
8
7
authors: ["Anil Madhavapeddy"]
9
8
license: "ISC"
10
-
homepage: "https://github.com/avsm/ocaml-publicsuffix"
11
-
bug-reports: "https://github.com/avsm/ocaml-publicsuffix/issues"
9
+
homepage: "https://tangled.org/@anil.recoil.org/ocaml-publicsuffix"
10
+
bug-reports: "https://tangled.org/@anil.recoil.org/ocaml-publicsuffix/issues"
12
11
depends: [
13
12
"ocaml" {>= "4.14.0"}
14
-
"dune" {>= "3.0" & >= "3.0"}
13
+
"dune" {>= "3.18" & >= "3.0"}
15
14
"domain-name" {>= "0.4.0"}
16
15
"punycode" {>= "0.1.0"}
17
16
"alcotest" {with-test}
···
31
30
"@doc" {with-doc}
32
31
]
33
32
]
34
-
dev-repo: "git+https://github.com/avsm/ocaml-publicsuffix.git"
33
+
x-maintenance-intent: ["(latest)"]
+5
test/psl_test.ml
+5
test/psl_test.ml
···
1
+
(*---------------------------------------------------------------------------
2
+
Copyright (c) 2025 Anil Madhavapeddy <anil@recoil.org>. All rights reserved.
3
+
SPDX-License-Identifier: ISC
4
+
---------------------------------------------------------------------------*)
5
+
1
6
(* psl_test.ml - Command-line tool for testing the Public Suffix List library
2
7
3
8
Usage: