Merge branch 'main' of github.com:Yoxem/stringCodepointSplitter

dep version correcting

CHANGES

@@ -1,2 +1,6 @@
+## v0.0.2 (2023-08-30)
+ - add more tests
+ - optimalize the list processing
+ - disable dynamic linking to uutf
 ## v0.0.1 (2023-08-27)
  - add `split_string_by_unicode_codepoint` initially

LICENSE

@@ -1,4 +1,4 @@
-Copyright 2023 Tan Kian-ting
+Copyright 2023 Tan Kian-ting &  Raphaël Proust 
 
 Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the “Software”), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
 

README.md

@@ -5,7 +5,7 @@ Split a string to a list of strings of a character by the unicode codepoint.
 It requires module Uutf.
 
 ## Dependencies
- - OCaml >= 4.13
+ - OCaml >= 4.06
  - dune
  - uutf
  - fildlib

dune-project

@@ -1,7 +1,8 @@
 (lang dune 3.9)
+(cram enable)
 
 (name stringCodepointSplitter)
-(version 0.0.1)
+(version 0.0.2)
 (generate_opam_files true)
 
 (source
@@ -21,7 +22,7 @@
  (description "Split a string to a list of strings of a character by the unicode codepoint.
 It requires module Uutf.")
 
- (depends ocaml ocamlfind dune uutf)
+ (depends (ocaml (>= 4.06)) ocamlfind dune uutf)
  (tags (string utf8)))
 
 ; See the complete stanza docs at https://dune.readthedocs.io/en/stable/dune-files.html#dune-project

lib/dune

@@ -1,4 +1,4 @@
 (library
  (name stringCodepointSplitter)
  (public_name stringCodepointSplitter)
- (libraries uutf findlib.dynload))
+ (libraries uutf))

lib/stringCodepointSplitter.ml

@@ -1,6 +1,6 @@
 open Stdlib
 (*
-(c) Tan Kian-ting 2023
+(c) 2023 Tan Kian-ting (main author) & Raphaël Proust (PR giver)
 Under MIT License
 
 习包子 梁家河小学博士 清零宗 习炀帝 庆丰大帝
@@ -13,9 +13,6 @@ Under MIT License
     It only contains [split_string_by_unicode_codepoint], which splits an OCaml string [str] to a [string list] 
 *)
 
-let _ = Findlib.init ();;
-Fl_dynload.load_packages ["uutf"];;
-
 
 (** Split an OCaml string [str] to a [string list] 
 
@@ -36,23 +33,22 @@ let split_string_by_unicode_codepoint str =
 (*Split a Ocaml string [str] to a `str list` *)
   let pred_codepoint = ref (-1) in
   let segmented_unit_list = ref [] in
-  let iterator x y _ =
-    let _ = if  !pred_codepoint > -1 then
+  let iterator () y _ =
+    let () = if  !pred_codepoint > -1 then
       let current_codepoint = y in
       let pred_char_len = current_codepoint - !pred_codepoint in
-      let unit_substring = Stdlib.String.sub x !pred_codepoint pred_char_len in
-      let _ = segmented_unit_list := !segmented_unit_list @ [unit_substring] in
-      unit_substring
-    else
-      "" in
-    let _ =  pred_codepoint := y in x in
+      let unit_substring = Stdlib.String.sub str !pred_codepoint pred_char_len in
+      segmented_unit_list := unit_substring :: !segmented_unit_list
+    in
+    let () =  pred_codepoint := y in
+    ()
+  in
 
-  let _ = Uutf.String.fold_utf_8 iterator str str in
+  let _ = Uutf.String.fold_utf_8 iterator () str in
   let last_char_len = (Stdlib.String.length str) - !pred_codepoint in
-  if last_char_len > 0 then
-    let unit_substring = Stdlib.String.sub str !pred_codepoint last_char_len in
-    let _ = segmented_unit_list := !segmented_unit_list @ [unit_substring] in
-    !segmented_unit_list
-  else
-    !segmented_unit_list;;
-
+  let () =
+    if last_char_len > 0 then
+      let unit_substring = Stdlib.String.sub str !pred_codepoint last_char_len in
+      segmented_unit_list := unit_substring :: !segmented_unit_list
+  in
+  List.rev !segmented_unit_list;;

stringCodepointSplitter.opam

@@ -1,6 +1,6 @@
 # This file is generated by dune, edit dune-project instead
 opam-version: "2.0"
-version: "0.0.1"
+version: "0.0.2"
 synopsis:
   "Split a string to a list of strings of a character by the unicode codepoint"
 description: """
@@ -13,7 +13,7 @@ tags: ["string" "utf8"]
 homepage: "https://github.com/yoxem/stringCodepointSplitter"
 bug-reports: "https://github.com/Yoxem/stringCodepointSplitter/issues"
 depends: [
-  "ocaml"
+  "ocaml" {>= "4.06"}
   "ocamlfind"
   "dune" {>= "3.9"}
   "uutf"

test/dune

@@ -1,2 +1,6 @@
-(test
- (name stringCodepointSplitter))
+(executable
+ (libraries stringCodepointSplitter)
+ (name stringCodepointSplitterTest))
+
+(cram
+ (deps ./stringCodepointSplitterTest.exe))

test/stringCodepointSplitter.t

@@ -0,0 +1,29 @@
+ASCII only
+  $ ./stringCodepointSplitterTest.exe abc
+  a
+  b
+  c
+
+Still simple but not just ASCII
+  $ ./stringCodepointSplitterTest.exe «—»
+  «
+  —
+  »
+
+Example from the docstring of the lib
+  $ ./stringCodepointSplitterTest.exe "m̄知 who you're."
+  m
+  ̄
+  知
+   
+  w
+  h
+  o
+   
+  y
+  o
+  u
+  '
+  r
+  e
+  .

test/stringCodepointSplitterTest.ml

@@ -0,0 +1,4 @@
+let () =
+  Sys.argv.(1)
+  |> StringCodepointSplitter.split_string_by_unicode_codepoint
+  |> List.iter print_endline