init

.envrc

@@ -0,0 +1 @@
+use flake

.gitignore

@@ -0,0 +1,3 @@
+/target
+/_build
+/.direnv

bin/dune

@@ -0,0 +1,4 @@
+(executable
+ (public_name inshellah-parser)
+ (name main)
+ (libraries inshellah_parser))

bin/main.ml

@@ -0,0 +1,171 @@
+open Inshellah_parser.Parser
+
+let () =
+  let _cp =
+    {|
+  -A, --show-all           equivalent to -vET
+  -b, --number-nonblank    number nonempty output lines, overrides -n
+  -e                       equivalent to -vE
+  -E, --show-ends          display $ or ^M$ at end of each line
+  -n, --number             number all output lines
+  -s, --squeeze-blank      suppress repeated empty output lines
+  -t                       equivalent to -vT
+  -T, --show-tabs          display TAB characters as ^I
+  -u                       (ignored)
+  -v, --show-nonprinting   use ^ and M- notation, except for LFD and TAB
+      --help
+         display this help and exit
+      --version
+         output version information and exit
+|}
+  and ls =
+    {|
+  -a, --all
+         do not ignore entries starting with .
+  -A, --almost-all
+         do not list implied . and ..
+      --author
+         with -l, print the author of each file
+  -b, --escape
+         print C-style escapes for nongraphic characters
+      --block-size=SIZE
+         with -l, scale sizes by SIZE when printing them;
+         e.g., '--block-size=M'; see SIZE format below
+  -B, --ignore-backups
+         do not list implied entries ending with ~
+  -c
+         with -lt: sort by, and show, ctime
+           (time of last change of file status information);
+         with -l: show ctime and sort by name;
+         otherwise: sort by ctime, newest first
+  -C
+         list entries by columns
+      --color[=WHEN]
+         color the output WHEN; more info below
+  -d, --directory
+         list directories themselves, not their contents
+  -D, --dired
+         generate output designed for Emacs' dired mode
+  -f
+         same as -a -U
+  -F, --classify[=WHEN]
+         append indicator (one of */=>@|) to entries WHEN
+      --file-type
+         like -F, except do not append '*'
+      --format=WORD
+         across,horizontal (-x), commas (-m), long (-l),
+         single-column (-1), verbose (-l), vertical (-C)
+      --full-time
+         like -l --time-style=full-iso
+  -g
+         like -l, but do not list owner
+      --group-directories-first
+         group directories before files
+  -G, --no-group
+         in a long listing, don't print group names
+  -h, --human-readable
+         with -l and -s, print sizes like 1K 234M 2G etc.
+      --si
+         likewise, but use powers of 1000 not 1024
+  -H, --dereference-command-line
+         follow symbolic links listed on the command line
+      --dereference-command-line-symlink-to-dir
+         follow each command line symbolic link that points to a directory
+      --hide=PATTERN
+         do not list implied entries matching shell PATTERN
+         (overridden by -a or -A)
+      --hyperlink[=WHEN]
+         hyperlink file names WHEN
+      --indicator-style=WORD
+         append indicator with style WORD to entry names:
+           none (default), slash (-p), file-type (--file-type), classify (-F)
+  -i, --inode
+         print the index number of each file
+  -I, --ignore=PATTERN
+         do not list implied entries matching shell PATTERN
+  -k, --kibibytes
+         default to 1024-byte blocks for file system usage;
+         used only with -s and per directory totals
+  -l
+         use a long listing format
+  -L, --dereference
+         when showing file information for a symbolic link,
+         show information for the file the link references
+         rather than for the link itself
+  -m
+         fill width with a comma separated list of entries
+  -n, --numeric-uid-gid
+         like -l, but list numeric user and group IDs
+  -N, --literal
+         print entry names without quoting
+  -o
+         like -l, but do not list group information
+  -p, --indicator-style=slash
+         append / indicator to directories
+  -q, --hide-control-chars
+         print ? instead of nongraphic characters
+      --show-control-chars
+         show nongraphic characters as-is;
+         the default, unless program is 'ls' and output is a terminal
+  -Q, --quote-name
+         enclose entry names in double quotes
+      --quoting-style=WORD
+         use quoting style WORD for entry names:
+           literal, locale, shell, shell-always,
+           shell-escape, shell-escape-always, c, escape
+         (overrides QUOTING_STYLE environment variable)
+  -r, --reverse
+         reverse order while sorting
+  -R, --recursive
+         list subdirectories recursively
+  -s, --size
+         print the allocated size of each file, in blocks
+  -S
+         sort by file size, largest first
+      --sort=WORD
+         change default 'name' sort to WORD:
+           none (-U), size (-S), time (-t),
+           version (-v), extension (-X), name, width
+      --time=WORD
+         select which timestamp used to display or sort;
+           access time (-u): atime, access, use;
+           metadata change time (-c): ctime, status;
+           modified time (default): mtime, modification;
+           birth time: birth, creation;
+         with -l, WORD determines which time to show;
+         with --sort=time, sort by WORD (newest first)
+      --time-style=TIME_STYLE
+         time/date format with -l; see TIME_STYLE below
+  -t
+         sort by time, newest first; see --time
+  -T, --tabsize=COLS
+         assume tab stops at each COLS instead of 8
+  -u
+         with -lt: sort by, and show, access time;
+         with -l: show access time and sort by name;
+         otherwise: sort by access time, newest first
+  -U
+         do not sort directory entries
+  -v
+         natural sort of (version) numbers within text
+  -w, --width=COLS
+         set output width to COLS.  0 means no limit
+  -x
+         list entries by lines instead of by columns
+  -X
+         sort alphabetically by entry extension
+  -Z, --context
+         print any security context of each file
+      --zero
+         end each output line with NUL, not newline
+  -1
+         list one file per line
+      --help
+         display this help and exit
+      --version
+         output version information and exit
+  |}
+  in
+  match parse_help ls with
+  | Ok entries -> List.iter (fun e -> print_entry e) entries
+  | Error msg -> Printf.eprintf "parse error: %s\n" msg

dune-project

@@ -0,0 +1,31 @@
+(lang dune 3.20)
+
+(name inshellah-parser)
+
+(generate_opam_files true)
+
+(source
+ (github username/reponame))
+
+(authors "Author Name <author@example.com>")
+
+(maintainers "Maintainer Name <maintainer@example.com>")
+
+(license LICENSE)
+
+(documentation https://url/to/documentation)
+
+(package
+ (name inshellah-parser)
+ (synopsis "A short synopsis")
+ (description "A longer description")
+ (depends
+  ocaml
+  dune
+  angstrom
+  angstrom-unix
+  (ppx_inline_test :with-test))
+ (tags
+  ("add topics" "to describe" your project)))
+
+; See the complete stanza docs at https://dune.readthedocs.io/en/stable/reference/dune-project/index.html

flake.lock

@@ -0,0 +1,27 @@
+{
+  "nodes": {
+    "nixpkgs": {
+      "locked": {
+        "lastModified": 1773385838,
+        "narHash": "sha256-ylF2AGl08seexxlLvMqj3jd+yZq56W9zicwe51mp0Pw=",
+        "owner": "nixos",
+        "repo": "nixpkgs",
+        "rev": "fef542e7a88eec2b698389e6279464fd479926b6",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nixos",
+        "ref": "nixpkgs-unstable",
+        "repo": "nixpkgs",
+        "type": "github"
+      }
+    },
+    "root": {
+      "inputs": {
+        "nixpkgs": "nixpkgs"
+      }
+    }
+  },
+  "root": "root",
+  "version": 7
+}

flake.nix

@@ -0,0 +1,32 @@
+{
+  inputs.nixpkgs.url = "github:nixos/nixpkgs/nixpkgs-unstable";
+
+  outputs =
+    { self, nixpkgs }:
+    let
+      forAllSystems =
+        f:
+        nixpkgs.lib.genAttrs [ "x86_64-linux" "aarch64-linux" ] (
+          system: f (import nixpkgs { inherit system; }) system
+        );
+    in
+    {
+      devShells = forAllSystems (
+        pkgs: sys: {
+          default = pkgs.mkShell {
+            packages = with pkgs.ocamlPackages; [
+              dune_3
+              ocaml
+              angstrom
+              angstrom-unix
+              ppx_inline_test
+              ocaml-lsp
+              ocamlformat
+              ocamlformat-rpc-lib
+              utop
+            ];
+          };
+        }
+      );
+    };
+}

inshellah-parser.opam

@@ -0,0 +1,35 @@
+# This file is generated by dune, edit dune-project instead
+opam-version: "2.0"
+synopsis: "A short synopsis"
+description: "A longer description"
+maintainer: ["Maintainer Name <maintainer@example.com>"]
+authors: ["Author Name <author@example.com>"]
+license: "LICENSE"
+tags: ["add topics" "to describe" "your" "project"]
+homepage: "https://github.com/username/reponame"
+doc: "https://url/to/documentation"
+bug-reports: "https://github.com/username/reponame/issues"
+depends: [
+  "ocaml"
+  "dune" {>= "3.20"}
+  "angstrom"
+  "angstrom-unix"
+  "ppx_inline_test" {with-test}
+  "odoc" {with-doc}
+]
+build: [
+  ["dune" "subst"] {dev}
+  [
+    "dune"
+    "build"
+    "-p"
+    name
+    "-j"
+    jobs
+    "@install"
+    "@runtest" {with-test}
+    "@doc" {with-doc}
+  ]
+]
+dev-repo: "git+https://github.com/username/reponame.git"
+x-maintenance-intent: ["(latest)"]

lib/dune

@@ -0,0 +1,3 @@
+(library
+ (name inshellah_parser)
+ (libraries angstrom angstrom-unix))

lib/parser.ml

@@ -0,0 +1,77 @@
+(* open Angstrom_unix *)
+(* also look for "subcommands" for clapslop *)
+(* and other common help patterns *)
+open Angstrom
+
+let ( <| ) = ( @@ )
+let ( <&> ) p1 p2 = lift2 (fun a b -> (a, b)) p1 p2
+let is_whitespace = function ' ' | '\t' | '\n' | '\r' -> true | _ -> false
+
+let is_alphanumeric = function
+  | 'A' .. 'Z' | 'a' .. 'z' | '0' .. '9' -> true
+  | _ -> false
+
+let is_long_char = function
+  | 'A' .. 'Z' | 'a' .. 'z' | '0' .. '9' | '-' -> true
+  | _ -> false
+
+type switch = Short of char | Long of string | Both of char * string
+type param = Mandatory of string | Optional of string
+type entry = { switch : switch; param : param option; desc : string }
+
+let whitespace = skip_while is_whitespace
+let comma = char ',' *> whitespace
+let short_switch = char '-' *> satisfy is_alphanumeric
+let long_switch = string "--" *> take_while1 is_long_char
+
+let opt_param =
+  print_endline "opt param is running";
+  string "[=" *> take_while is_alphanumeric <* char ']' >>| fun a -> Optional a
+
+let man_param =
+  print_endline "man param is running";
+  char '=' *> take_while is_alphanumeric >>| fun a -> Mandatory a
+
+let param_parser =
+  option None (choice [ opt_param; man_param ] >>| fun a -> Some a)
+
+let switch_parser =
+  choice
+    [
+      (* -a, --all *)
+      ( short_switch >>= fun s ->
+        comma *> long_switch >>| fun l -> Both (s, l) );
+      (* -a *)
+      (short_switch >>| fun s -> Short s);
+      (* --all *)
+      (long_switch >>| fun l -> Long l);
+    ]
+
+let description = whitespace *> take_till (fun c -> c = '\n') <* end_of_line
+
+let entry =
+  skip_while (fun c -> c <> '-')
+  *> lift3 (fun a b c -> (a, b, c)) switch_parser param_parser description
+  >>| fun (switch, param, desc) -> { switch; param; desc }
+
+let endline = option () (char '\n' *> return ())
+let entry_line = entry <* endline
+let help_parser = many entry_line
+
+let parse_help txt =
+  Angstrom.parse_string ~consume:Consume.Prefix help_parser txt
+
+let print_switch = function
+  | Short o -> Printf.sprintf "Short: %c" o
+  | Long o -> Printf.sprintf "Long: %s" o
+  | Both (s, l) -> Printf.sprintf "Both, short: %c long: %s" s l
+
+let print_opt = function
+  | Some (Mandatory o) -> Printf.sprintf "Mandatory: %s" o
+  | Some (Optional o) -> Printf.sprintf "Optional: %s" o
+  | None -> "None"
+
+let print_entry e =
+  Printf.printf
+    "\n\t** ENTRY **\n\tSwitch: %s\n\tParam: %s\n\tDescription: %s\n"
+    (print_switch e.switch) (print_opt e.param) e.desc

test/dune

@@ -0,0 +1,2 @@
+(test
+ (name test_inshellah_parser))