initial commit

.github/workflows/test.yml

@@ -0,0 +1,23 @@
+name: test
+
+on:
+  push:
+    branches:
+      - master
+      - main
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: erlef/setup-beam@v1
+        with:
+          otp-version: "27.1.2"
+          gleam-version: "1.12.0"
+          rebar3-version: "3"
+          # elixir-version: "1"
+      - run: gleam deps download
+      - run: gleam test
+      - run: gleam format --check src test

.gitignore

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

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "toml-test"]
+	path = toml-test
+	url = https://github.com/toml-lang/toml-test.git

README.md

@@ -0,0 +1,24 @@
+# gltoml
+
+[![Package Version](https://img.shields.io/hexpm/v/gltoml)](https://hex.pm/packages/gltoml)
+[![Hex Docs](https://img.shields.io/badge/hex-docs-ffaff3)](https://hexdocs.pm/gltoml/)
+
+```sh
+gleam add gltoml@1
+```
+```gleam
+import gltoml
+
+pub fn main() -> Nil {
+  // TODO: An example of the project in use
+}
+```
+
+Further documentation can be found at <https://hexdocs.pm/gltoml>.
+
+## Development
+
+```sh
+gleam run   # Run the project
+gleam test  # Run the tests
+```

gleam.toml

@@ -0,0 +1,23 @@
+name = "gltoml"
+version = "1.0.0"
+
+# Fill out these fields if you intend to generate HTML documentation or publish
+# your project to the Hex package manager.
+#
+# description = ""
+# licences = ["Apache-2.0"]
+# repository = { type = "github", user = "", repo = "" }
+# links = [{ title = "Website", href = "" }]
+#
+# For a full reference of all the available options, you can have a look at
+# https://gleam.run/writing-gleam/gleam-toml/.
+
+[dependencies]
+gleam_stdlib = ">= 0.44.0 and < 2.0.0"
+tom = ">= 2.0.0 and < 3.0.0"
+gleam_time = ">= 1.4.0 and < 2.0.0"
+
+[dev-dependencies]
+gleeunit = ">= 1.0.0 and < 2.0.0"
+startest = ">= 0.7.0 and < 1.0.0"
+simplifile = ">= 2.3.0 and < 3.0.0"

manifest.toml

@@ -0,0 +1,35 @@
+# This file was generated by Gleam
+# You typically do not need to edit this file
+
+packages = [
+  { name = "argv", version = "1.0.2", build_tools = ["gleam"], requirements = [], otp_app = "argv", source = "hex", outer_checksum = "BA1FF0929525DEBA1CE67256E5ADF77A7CDDFE729E3E3F57A5BDCAA031DED09D" },
+  { name = "bigben", version = "1.0.1", build_tools = ["gleam"], requirements = ["birl", "gleam_erlang", "gleam_otp", "gleam_stdlib"], otp_app = "bigben", source = "hex", outer_checksum = "190E489610A80D76C48BACC75EB8314BD184FF0220AB0F251ABE760B993B91BB" },
+  { name = "birl", version = "1.8.0", build_tools = ["gleam"], requirements = ["gleam_regexp", "gleam_stdlib", "ranger"], otp_app = "birl", source = "hex", outer_checksum = "2AC7BA26F998E3DFADDB657148BD5DDFE966958AD4D6D6957DD0D22E5B56C400" },
+  { name = "exception", version = "2.1.0", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "exception", source = "hex", outer_checksum = "329D269D5C2A314F7364BD2711372B6F2C58FA6F39981572E5CA68624D291F8C" },
+  { name = "filepath", version = "1.1.2", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "filepath", source = "hex", outer_checksum = "B06A9AF0BF10E51401D64B98E4B627F1D2E48C154967DA7AF4D0914780A6D40A" },
+  { name = "gleam_community_ansi", version = "1.4.3", build_tools = ["gleam"], requirements = ["gleam_community_colour", "gleam_regexp", "gleam_stdlib"], otp_app = "gleam_community_ansi", source = "hex", outer_checksum = "8A62AE9CC6EA65BEA630D95016D6C07E4F9973565FA3D0DE68DC4200D8E0DD27" },
+  { name = "gleam_community_colour", version = "2.0.2", build_tools = ["gleam"], requirements = ["gleam_json", "gleam_stdlib"], otp_app = "gleam_community_colour", source = "hex", outer_checksum = "E34DD2C896AC3792151EDA939DA435FF3B69922F33415ED3C4406C932FBE9634" },
+  { name = "gleam_erlang", version = "1.3.0", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "gleam_erlang", source = "hex", outer_checksum = "1124AD3AA21143E5AF0FC5CF3D9529F6DB8CA03E43A55711B60B6B7B3874375C" },
+  { name = "gleam_javascript", version = "1.0.0", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "gleam_javascript", source = "hex", outer_checksum = "EF6C77A506F026C6FB37941889477CD5E4234FCD4337FF0E9384E297CB8F97EB" },
+  { name = "gleam_json", version = "3.0.2", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "gleam_json", source = "hex", outer_checksum = "874FA3C3BB6E22DD2BB111966BD40B3759E9094E05257899A7C08F5DE77EC049" },
+  { name = "gleam_otp", version = "1.1.0", build_tools = ["gleam"], requirements = ["gleam_erlang", "gleam_stdlib"], otp_app = "gleam_otp", source = "hex", outer_checksum = "7987CBEBC8060B88F14575DEF546253F3116EBE2A5DA6FD82F38243FCE97C54B" },
+  { name = "gleam_regexp", version = "1.1.1", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "gleam_regexp", source = "hex", outer_checksum = "9C215C6CA84A5B35BB934A9B61A9A306EC743153BE2B0425A0D032E477B062A9" },
+  { name = "gleam_stdlib", version = "0.63.2", build_tools = ["gleam"], requirements = [], otp_app = "gleam_stdlib", source = "hex", outer_checksum = "962B25C667DA07F4CAB32001F44D3C41C1A89E58E3BBA54F183B482CF6122150" },
+  { name = "gleam_time", version = "1.4.0", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "gleam_time", source = "hex", outer_checksum = "DCDDC040CE97DA3D2A925CDBBA08D8A78681139745754A83998641C8A3F6587E" },
+  { name = "gleam_yielder", version = "1.1.0", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "gleam_yielder", source = "hex", outer_checksum = "8E4E4ECFA7982859F430C57F549200C7749823C106759F4A19A78AEA6687717A" },
+  { name = "gleeunit", version = "1.6.1", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "gleeunit", source = "hex", outer_checksum = "FDC68A8C492B1E9B429249062CD9BAC9B5538C6FBF584817205D0998C42E1DAC" },
+  { name = "glint", version = "1.2.1", build_tools = ["gleam"], requirements = ["gleam_community_ansi", "gleam_community_colour", "gleam_stdlib", "snag"], otp_app = "glint", source = "hex", outer_checksum = "2214C7CEFDE457CEE62140C3D4899B964E05236DA74E4243DFADF4AF29C382BB" },
+  { name = "ranger", version = "1.4.0", build_tools = ["gleam"], requirements = ["gleam_stdlib", "gleam_yielder"], otp_app = "ranger", source = "hex", outer_checksum = "C8988E8F8CDBD3E7F4D8F2E663EF76490390899C2B2885A6432E942495B3E854" },
+  { name = "simplifile", version = "2.3.0", build_tools = ["gleam"], requirements = ["filepath", "gleam_stdlib"], otp_app = "simplifile", source = "hex", outer_checksum = "0A868DAC6063D9E983477981839810DC2E553285AB4588B87E3E9C96A7FB4CB4" },
+  { name = "snag", version = "1.1.0", build_tools = ["gleam"], requirements = ["gleam_stdlib"], otp_app = "snag", source = "hex", outer_checksum = "7E9F06390040EB5FAB392CE642771484136F2EC103A92AE11BA898C8167E6E17" },
+  { name = "startest", version = "0.7.0", build_tools = ["gleam"], requirements = ["argv", "bigben", "birl", "exception", "gleam_community_ansi", "gleam_erlang", "gleam_javascript", "gleam_regexp", "gleam_stdlib", "glint", "simplifile", "tom"], otp_app = "startest", source = "hex", outer_checksum = "71B9CB82C4B8779A4BD54C7151DF7D0B0F778D0DDE805B782B44EFA7BA8F50DA" },
+  { name = "tom", version = "2.0.0", build_tools = ["gleam"], requirements = ["gleam_stdlib", "gleam_time"], otp_app = "tom", source = "hex", outer_checksum = "74D0C5A3761F7A7D06994755D4D5AD854122EF8E9F9F76A3E7547606D8C77091" },
+]
+
+[requirements]
+gleam_stdlib = { version = ">= 0.44.0 and < 2.0.0" }
+gleam_time = { version = ">= 1.4.0 and < 2.0.0" }
+gleeunit = { version = ">= 1.0.0 and < 2.0.0" }
+simplifile = { version = ">= 2.3.0 and < 3.0.0" }
+startest = { version = ">= 0.7.0 and < 1.0.0" }
+tom = { version = ">= 2.0.0 and < 3.0.0" }

src/TOML.abnf

@@ -0,0 +1,247 @@
+;; This document describes TOML's syntax, using the ABNF format (defined in
+;; RFC 5234 -- https://www.ietf.org/rfc/rfc5234.txt).
+;;
+;; Although a TOML document must be valid UTF-8, this grammar refers to the
+;; Unicode Code Points you get after you decode the UTF-8 input.
+;;
+;; All valid TOML documents will match this description, however certain
+;; invalid documents would need to be rejected as per the semantics described
+;; in the supporting text description.
+
+;; It is possible to try this grammar interactively, using instaparse.
+;;     http://instaparse.mojombo.com/
+;;
+;; To do so, in the lower right, click on Options and change `:input-format` to
+;; ':abnf'. Then paste this entire ABNF document into the grammar entry box
+;; (above the options). Then you can type or paste a sample TOML document into
+;; the beige box on the left. Tada!
+
+;; Overall Structure
+
+toml = expression *( newline expression )
+
+expression =  ws [ comment ]
+expression =/ ws keyval ws [ comment ]
+expression =/ ws table ws [ comment ]
+
+;; Whitespace
+
+ws = *wschar
+wschar =  %x20  ; Space
+wschar =/ %x09  ; Horizontal tab
+
+;; Newline
+
+newline =  %x0A     ; LF
+newline =/ %x0D.0A  ; CRLF
+
+;; Comment
+
+comment-start-symbol = %x23 ; #
+non-ascii = %x80-D7FF / %xE000-10FFFF
+non-eol = %x09 / %x20-7E / non-ascii
+
+comment = comment-start-symbol *non-eol
+
+;; Key-Value pairs
+
+keyval = key keyval-sep val
+key = simple-key / dotted-key
+val = string / boolean / array / inline-table / date-time / float / integer
+
+simple-key = quoted-key / unquoted-key
+unquoted-key = 1*( ALPHA / DIGIT / %x2D / %x5F ) ; A-Z / a-z / 0-9 / - / _
+
+;; Quoted and dotted key
+
+quoted-key = basic-string / literal-string
+dotted-key = simple-key 1*( dot-sep simple-key )
+
+dot-sep   = ws %x2E ws  ; . Period
+keyval-sep = ws %x3D ws ; =
+
+;; String
+
+string = ml-basic-string / basic-string / ml-literal-string / literal-string
+
+;; Basic String
+
+basic-string = quotation-mark *basic-char quotation-mark
+
+quotation-mark = %x22            ; "
+
+basic-char = basic-unescaped / escaped
+basic-unescaped = wschar / %x21 / %x23-5B / %x5D-7E / non-ascii
+escaped = escape escape-seq-char
+
+escape = %x5C                   ; \
+escape-seq-char =  %x22         ; "    quotation mark  U+0022
+escape-seq-char =/ %x5C         ; \    reverse solidus U+005C
+escape-seq-char =/ %x62         ; b    backspace       U+0008
+escape-seq-char =/ %x65         ; e    escape          U+001B
+escape-seq-char =/ %x66         ; f    form feed       U+000C
+escape-seq-char =/ %x6E         ; n    line feed       U+000A
+escape-seq-char =/ %x72         ; r    carriage return U+000D
+escape-seq-char =/ %x74         ; t    tab             U+0009
+escape-seq-char =/ %x78 2HEXDIG ; xHH                  U+00HH
+escape-seq-char =/ %x75 4HEXDIG ; uHHHH                U+HHHH
+escape-seq-char =/ %x55 8HEXDIG ; UHHHHHHHH            U+HHHHHHHH
+
+;; Multiline Basic String
+
+ml-basic-string = ml-basic-string-delim [ newline ] ml-basic-body
+                  ml-basic-string-delim
+ml-basic-string-delim = 3quotation-mark
+ml-basic-body = *mlb-content *( mlb-quotes 1*mlb-content ) [ mlb-quotes ]
+
+mlb-content = basic-char / newline / mlb-escaped-nl
+mlb-quotes = 1*2quotation-mark
+mlb-escaped-nl = escape ws newline *( wschar / newline )
+
+;; Literal String
+
+literal-string = apostrophe *literal-char apostrophe
+
+apostrophe = %x27 ; ' apostrophe
+
+literal-char = %x09 / %x20-26 / %x28-7E / non-ascii
+
+;; Multiline Literal String
+
+ml-literal-string = ml-literal-string-delim [ newline ] ml-literal-body
+                    ml-literal-string-delim
+ml-literal-string-delim = 3apostrophe
+ml-literal-body = *mll-content *( mll-quotes 1*mll-content ) [ mll-quotes ]
+
+mll-content = literal-char / newline
+mll-quotes = 1*2apostrophe
+
+;; Integer
+
+integer = dec-int / hex-int / oct-int / bin-int
+
+minus = %x2D                       ; -
+plus = %x2B                        ; +
+underscore = %x5F                  ; _
+digit1-9 = %x31-39                 ; 1-9
+digit0-7 = %x30-37                 ; 0-7
+digit0-1 = %x30-31                 ; 0-1
+
+hex-prefix = %x30.78               ; 0x
+oct-prefix = %x30.6F               ; 0o
+bin-prefix = %x30.62               ; 0b
+
+dec-int = [ minus / plus ] unsigned-dec-int
+unsigned-dec-int = DIGIT / digit1-9 1*( DIGIT / underscore DIGIT )
+
+hex-int = hex-prefix HEXDIG *( HEXDIG / underscore HEXDIG )
+oct-int = oct-prefix digit0-7 *( digit0-7 / underscore digit0-7 )
+bin-int = bin-prefix digit0-1 *( digit0-1 / underscore digit0-1 )
+
+;; Float
+
+float = float-int-part ( exp / frac [ exp ] )
+float =/ special-float
+
+float-int-part = dec-int
+frac = decimal-point zero-prefixable-int
+decimal-point = %x2E               ; .
+zero-prefixable-int = DIGIT *( DIGIT / underscore DIGIT )
+
+exp = "e" float-exp-part
+float-exp-part = [ minus / plus ] zero-prefixable-int
+
+special-float = [ minus / plus ] ( inf / nan )
+inf = %x69.6E.66  ; inf
+nan = %x6E.61.6E  ; nan
+
+;; Boolean
+
+boolean = true / false
+
+true    = %x74.72.75.65     ; true
+false   = %x66.61.6C.73.65  ; false
+
+;; Date and Time (as defined in RFC 3339)
+
+date-time      = offset-date-time / local-date-time / local-date / local-time
+
+date-fullyear  = 4DIGIT
+date-month     = 2DIGIT  ; 01-12
+date-mday      = 2DIGIT  ; 01-28, 01-29, 01-30, 01-31 based on month/year
+time-delim     = "T" / %x20 ; T, t, or space
+time-hour      = 2DIGIT  ; 00-23
+time-minute    = 2DIGIT  ; 00-59
+time-second    = 2DIGIT  ; 00-58, 00-59, 00-60 based on leap second rules
+time-secfrac   = "." 1*DIGIT
+time-numoffset = ( "+" / "-" ) time-hour ":" time-minute
+time-offset    = "Z" / time-numoffset
+
+partial-time   = time-hour ":" time-minute [ ":" time-second [ time-secfrac ] ]
+full-date      = date-fullyear "-" date-month "-" date-mday
+full-time      = partial-time time-offset
+
+;; Offset Date-Time
+
+offset-date-time = full-date time-delim full-time
+
+;; Local Date-Time
+
+local-date-time = full-date time-delim partial-time
+
+;; Local Date
+
+local-date = full-date
+
+;; Local Time
+
+local-time = partial-time
+
+;; Array
+
+array = array-open [ array-values ] ws-comment-newline array-close
+
+array-open =  %x5B ; [
+array-close = %x5D ; ]
+
+array-values =  ws-comment-newline val ws-comment-newline array-sep array-values
+array-values =/ ws-comment-newline val ws-comment-newline [ array-sep ]
+
+array-sep = %x2C  ; , Comma
+
+ws-comment-newline = *( wschar / [ comment ] newline )
+
+;; Table
+
+table = std-table / array-table
+
+;; Standard Table
+
+std-table = std-table-open key std-table-close
+
+std-table-open  = %x5B ws     ; [ Left square bracket
+std-table-close = ws %x5D     ; ] Right square bracket
+
+;; Inline Table
+
+inline-table = inline-table-open [ inline-table-keyvals ] ws-comment-newline inline-table-close
+
+inline-table-open  = %x7B  ; {
+inline-table-close = %x7D  ; }
+inline-table-sep   = %x2C  ; , Comma
+
+inline-table-keyvals =  ws-comment-newline keyval ws-comment-newline inline-table-sep inline-table-keyvals
+inline-table-keyvals =/ ws-comment-newline keyval ws-comment-newline [ inline-table-sep ]
+
+;; Array Table
+
+array-table = array-table-open key array-table-close
+
+array-table-open  = %x5B.5B ws  ; [[ Double left square bracket
+array-table-close = ws %x5D.5D  ; ]] Double right square bracket
+
+;; Built-in ABNF terms, reproduced here for clarity
+
+ALPHA = %x41-5A / %x61-7A ; A-Z / a-z
+DIGIT = %x30-39 ; 0-9
+HEXDIG = DIGIT / "A" / "B" / "C" / "D" / "E" / "F"

test/gltoml_test.gleam

@@ -0,0 +1,46 @@
+import gleam/list
+import gleam/string
+import gltoml
+import simplifile
+import startest
+import startest/expect
+
+pub fn main() -> Nil {
+  startest.run(startest.default_config())
+}
+
+// gleeunit test functions end in `_test`
+pub fn files_tests() {
+  let assert Ok(test_file) =
+    simplifile.read("./toml-test/tests/files-toml-1.1.0")
+  let files =
+    string.split(test_file, "\n")
+    |> list.filter(fn(filename) { string.ends_with(filename, ".toml") })
+    // We need to omit the encoding tests because these generally require a different method to
+    // load as simplifile doesn't appear to open non-valid utf 8/16 files
+    |> list.filter(fn(filename) {
+      !string.starts_with(filename, "invalid/encoding")
+    })
+  files |> list.length |> echo
+
+  list.map(files, fn(filename) {
+    startest.it(filename, fn() {
+      let toml =
+        simplifile.read("./toml-test/tests/" <> filename) |> expect.to_be_ok
+
+      let tom = gltoml.parse(toml)
+      case filename {
+        "valid/" <> _ -> {
+          expect.to_be_ok(tom)
+          Nil
+        }
+        "invalid/" <> _ -> {
+          expect.to_be_error(tom)
+          Nil
+        }
+        _ -> Nil
+      }
+    })
+  })
+  |> startest.describe("files test", _)
+}

test/scratch.gleam

@@ -0,0 +1,16 @@
+import gleam/string
+import gleam/time/calendar
+import gltoml
+
+pub fn main() {
+  calendar.Date(25, calendar.March, 2025)
+  |> echo
+  |> calendar.is_valid_date
+  |> echo
+  gltoml.parse(
+    //"#hello\n   'a.b' = '1'\nc = true\ng=2025-03-25T10:03:23.500000000+01:00\nh=12308_123\ni=-2\nf = 0o751\nd=0b1_1_0_1\ne=0x1ab_4ef\nj=-nan\nk=1.5e2",
+    // "tab = { inner.table = [{}], inner.table.val = \"bad\" }",
+    "a = {   a.b  =  1   }",
+  )
+  |> echo
+}