check in

.forgejo/workflows/test.yml

@@ -0,0 +1,21 @@
+name: test
+
+on:
+  push:
+    branches:
+      - master
+  pull_request:
+
+jobs:
+  test:
+    runs-on: docker
+    steps:
+      - uses: actions/checkout@v4
+      - uses: erlef/setup-beam@v1
+        with:
+          otp-version: "27.1.2"
+          gleam-version: "1.6.2"
+          rebar3-version: "3"
+      - run: gleam deps download
+      - run: gleam test
+      - run: gleam format --check src test

.gitignore

@@ -0,0 +1,4 @@
+*.beam
+*.ez
+/build
+erl_crash.dump

README.md

@@ -0,0 +1,12 @@
+# Kmer, father of [Pdor]
+
+Decoder library for CBOR.
+
+Based on Noah Pederson's [gleemor] module, licensed under MIT
+
+## License
+
+This library is licensed under the GNU Affero General Public License version 3, see `LICENSE`.
+
+[Pdor]:https://www.youtube.com/watch?v=k3aehC2SSPw
+[gleemor]:https://github.com/chiefnoah/gleebor

gleam.toml

@@ -0,0 +1,13 @@
+name = "kmer"
+version = "0.1.0"
+
+description = "CBOR decoder library"
+licences = ["AGPL-3.0-only"]
+repository = { type = "forgejo", host = "git.fromouter.space", user = "hamcha", repo = "kmer" }
+gleam = ">= 1.6.2"
+
+[dependencies]
+gleam_stdlib = ">= 0.34.0 and < 2.0.0"
+
+[dev-dependencies]
+gleeunit = ">= 1.0.0 and < 2.0.0"

manifest.toml

@@ -0,0 +1,11 @@
+# This file was generated by Gleam
+# You typically do not need to edit this file
+
+packages = [
+  { name = "gleam_stdlib", version = "0.45.0", build_tools = ["gleam"], requirements = [], otp_app = "gleam_stdlib", source = "hex", outer_checksum = "206FCE1A76974AECFC55AEBCD0217D59EDE4E408C016E2CFCCC8FF51278F186E" },
+  { name = "gleeunit", version = "1.2.0", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "gleeunit", source = "hex", outer_checksum = "F7A7228925D3EE7D0813C922E062BFD6D7E9310F0BEE585D3A42F3307E3CFD13" },
+]
+
+[requirements]
+gleam_stdlib = { version = ">= 0.34.0 and < 2.0.0" }
+gleeunit = { version = ">= 1.0.0 and < 2.0.0" }

src/kmer.gleam

@@ -0,0 +1,51 @@
+import gleam/result.{try}
+
+pub type DecodedValue {
+  Integer(value: Int)
+}
+
+type DecoderResult(t) =
+  Result(#(t, BitArray), DecodeError)
+
+pub type DecodeResult =
+  DecoderResult(DecodedValue)
+
+pub opaque type DecodeError {
+  // More data was expected but file/stream ended prematurely
+  UnexpectedEnd
+
+  // Malformed sequence found
+  Malformed
+}
+
+pub fn decode_next_value(bits: BitArray) -> DecodeResult {
+  case bits {
+    <<0:3, rest:bits>> ->
+      decode_int(rest)
+      |> map_decoded(Integer)
+    <<1:3, rest:bits>> ->
+      decode_int(rest)
+      |> map_decoded(fn(x) { Integer(-1 - x) })
+    _ -> Error(Malformed)
+  }
+}
+
+fn decode_int(bits: BitArray) -> DecoderResult(Int) {
+  case bits {
+    <<24:int-size(5), val:int-unsigned-size(8), rest:bits>> -> Ok(#(val, rest))
+    <<25:int-size(5), val:int-unsigned-size(16), rest:bits>> -> Ok(#(val, rest))
+    <<26:int-size(5), val:int-unsigned-size(32), rest:bits>> -> Ok(#(val, rest))
+    <<27:int-size(5), val:int-unsigned-size(64), rest:bits>> -> Ok(#(val, rest))
+    <<x:int-size(5), rest:bits>> if x < 24 -> Ok(#(x, rest))
+    <<x:int-size(5), _:bits>> if x >= 24 -> Error(Malformed)
+    _ -> Error(UnexpectedEnd)
+  }
+}
+
+fn map_decoded(
+  result: DecoderResult(t),
+  map_fn: fn(t) -> DecodedValue,
+) -> DecodeResult {
+  use #(value, rest) <- try(result)
+  Ok(#(map_fn(value), rest))
+}

test/kmer_test.gleam

@@ -0,0 +1,76 @@
+import gleam/list
+import gleeunit
+import gleeunit/should
+import kmer.{type DecodeResult, type DecodedValue, Integer}
+
+pub fn main() {
+  gleeunit.main()
+}
+
+fn table_test_decode_next_value(test_case: BitArray, expected: DecodedValue) {
+  kmer.decode_next_value(test_case) |> is_value(expected)
+}
+
+fn is_value(val: DecodeResult, expected: DecodedValue) {
+  should.be_ok(val) |> should.equal(#(expected, <<>>))
+}
+
+pub fn decode_immediate_int_test() {
+  [
+    // Small integers under 24
+    #(<<0>>, Integer(0)),
+    #(<<10>>, Integer(10)),
+    #(<<23>>, Integer(23)),
+  ]
+  |> table_fn(table_test_decode_next_value)
+}
+
+pub fn decode_int_test() {
+  [
+    // 1-byte length (Maj.arg 24)
+    #(<<24, 24>>, Integer(24)),
+    #(<<24, 100>>, Integer(100)),
+    // 2-byte length (Maj.arg 25)
+    #(<<25, 1234:16>>, Integer(1234)),
+    #(<<25, 12_345:16>>, Integer(12_345)),
+    // 3-byte length (Maj.arg 26)
+    #(<<26, 1_234_567:32>>, Integer(1_234_567)),
+    #(<<26, 999_999_999:32>>, Integer(999_999_999)),
+    // 4-byte length (Maj.arg 27)
+    #(<<27, 2_099_210_021_019_898_881:64>>, Integer(2_099_210_021_019_898_881)),
+    #(<<27, 3:64>>, Integer(3)),
+  ]
+  |> table_fn(table_test_decode_next_value)
+}
+
+pub fn decode_negative_int_test() {
+  [
+    // Immediate negative (under 25)
+    #(<<1:3, 0:5>>, Integer(-1)),
+    #(<<1:3, 8:5>>, Integer(-9)),
+    #(<<1:3, 23:5>>, Integer(-24)),
+    // 1-byte length (Maj.arg 24)
+    #(<<1:3, 24:5, 24:8>>, Integer(-25)),
+    #(<<1:3, 24:5, 100:8>>, Integer(-101)),
+    // 2-byte length (Maj.arg 25)
+    #(<<1:3, 25:5, 1234:16>>, Integer(-1235)),
+    #(<<1:3, 25:5, 12_345:16>>, Integer(-12_346)),
+    // 3-byte length (Maj.arg 26)
+    #(<<1:3, 26:5, 1_234_567:32>>, Integer(-1_234_568)),
+    #(<<1:3, 26:5, 999_999_999:32>>, Integer(-1_000_000_000)),
+    // 4-byte length (Maj.arg 27)
+    #(
+      <<1:3, 27:5, 2_099_210_021_019_898_881:64>>,
+      Integer(-2_099_210_021_019_898_882),
+    ),
+    #(<<1:3, 27:5, 3:64>>, Integer(-4)),
+  ]
+  |> table_fn(table_test_decode_next_value)
+}
+
+fn table_fn(tests: List(#(a, b)), test_fn: fn(a, b) -> Nil) {
+  list.map(tests, fn(t) {
+    let #(test_case, expected) = t
+    test_fn(test_case, expected)
+  })
+}