update for Unicode 16.0.0

Author: stevengj

CMakeLists.txt

@@ -65,7 +65,7 @@ endif()
 if(UTF8PROC_ENABLE_TESTING)
   enable_testing()
   file(MAKE_DIRECTORY data)
-  set(UNICODE_VERSION 15.1.0)
+  set(UNICODE_VERSION 16.0.0)
   file(DOWNLOAD https://www.unicode.org/Public/${UNICODE_VERSION}/ucd/NormalizationTest.txt ${CMAKE_BINARY_DIR}/data/NormalizationTest.txt SHOW_PROGRESS)
   file(DOWNLOAD https://www.unicode.org/Public/${UNICODE_VERSION}/ucd/auxiliary/GraphemeBreakTest.txt ${CMAKE_BINARY_DIR}/data/GraphemeBreakTest.txt SHOW_PROGRESS)
   add_executable(case test/tests.h test/tests.c utf8proc.h test/case.c)

README.md

@@ -59,7 +59,7 @@ The C library is found in this directory after successful compilation
 and is named `libutf8proc.a` (for the static library) and
 `libutf8proc.so` (for the dynamic library).
 
-The Unicode version supported is 15.1.0.
+The Unicode version supported is 16.0.0.
 
 For Unicode normalizations, the following options are used:
 

data/Makefile

@@ -21,7 +21,7 @@ utf8proc_data.c.new: data_generator.jl $(RAWDATA)
 	$(JULIA) --project=. data_generator.jl > $@
 
 # Unicode data version (must also update utf8proc_unicode_version function)
-UNICODE_VERSION=15.1.0
+UNICODE_VERSION=16.0.0
 
 UnicodeData.txt:
 	$(CURL) $(CURLFLAGS) -o $@ https://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/UnicodeData.txt

data/Manifest.toml

@@ -1,69 +1,16 @@
 # This file is machine-generated - editing it directly is not advised
 
-julia_version = "1.9.3"
+julia_version = "1.10.5"
 manifest_format = "2.0"
 project_hash = "bc0740aa2247b17bd49ba693fb87f41bbbddead6"
 
-[[deps.Adapt]]
-deps = ["LinearAlgebra", "Requires"]
-git-tree-sha1 = "cde29ddf7e5726c9fb511f340244ea3481267608"
-uuid = "79e6a3ab-5dfb-504d-930d-738a2a938a0e"
-version = "3.7.2"
-
-    [deps.Adapt.extensions]
-    AdaptStaticArraysExt = "StaticArrays"
-
-    [deps.Adapt.weakdeps]
-    StaticArrays = "90137ffa-7385-5640-81b9-e52037218182"
-
-[[deps.Artifacts]]
-uuid = "56f22d72-fd6d-98f1-02f0-08ddc0907c33"
-
-[[deps.CompilerSupportLibraries_jll]]
-deps = ["Artifacts", "Libdl"]
-uuid = "e66e0078-7015-5450-92f7-15fbd957f2ae"
-version = "1.0.5+0"
-
-[[deps.Libdl]]
-uuid = "8f399da3-3557-5675-b5ff-fb832c97cbdb"
-
-[[deps.LinearAlgebra]]
-deps = ["Libdl", "OpenBLAS_jll", "libblastrampoline_jll"]
-uuid = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
-
 [[deps.OffsetArrays]]
-deps = ["Adapt"]
-git-tree-sha1 = "2ac17d29c523ce1cd38e27785a7d23024853a4bb"
+git-tree-sha1 = "1a27764e945a152f7ca7efa04de513d473e9542e"
 uuid = "6fe1bfb0-de20-5000-8ca7-80f57d26f881"
-version = "1.12.10"
-
-[[deps.OpenBLAS_jll]]
-deps = ["Artifacts", "CompilerSupportLibraries_jll", "Libdl"]
-uuid = "4536629a-c528-5b80-bd46-f80d51c5b363"
-version = "0.3.21+4"
-
-[[deps.Random]]
-deps = ["SHA", "Serialization"]
-uuid = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
-
-[[deps.Requires]]
-deps = ["UUIDs"]
-git-tree-sha1 = "838a3a4188e2ded87a4f9f184b4b0d78a1e91cb7"
-uuid = "ae029012-a4dd-5104-9daa-d747884805df"
-version = "1.3.0"
-
-[[deps.SHA]]
-uuid = "ea8e919c-243c-51af-8825-aaa63cd721ce"
-version = "0.7.0"
-
-[[deps.Serialization]]
-uuid = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
+version = "1.14.1"
 
-[[deps.UUIDs]]
-deps = ["Random", "SHA"]
-uuid = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
+    [deps.OffsetArrays.extensions]
+    OffsetArraysAdaptExt = "Adapt"
 
-[[deps.libblastrampoline_jll]]
-deps = ["Artifacts", "Libdl"]
-uuid = "8e850b90-86db-534c-a0d3-1478176c7d93"
-version = "5.8.0+0"
+    [deps.OffsetArrays.weakdeps]
+    Adapt = "79e6a3ab-5dfb-504d-930d-738a2a938a0e"

data/data_generator.jl

@@ -236,8 +236,8 @@ let ea_widths = read_east_asian_widths("EastAsianWidth.txt")
             width = 1
         elseif code == 0x2028 || code == 0x2029
             #By definition, should have zero width (on the same line)
-            #0x002028 '
' category: Zl name: LINE SEPARATOR/
-            #0x002029 '
' category: Zp name: PARAGRAPH SEPARATOR/
+            #0x002028 '\u2028' category: Zl name: LINE SEPARATOR/
+            #0x002029 '\u2029' category: Zp name: PARAGRAPH SEPARATOR/
             width = 0
         end
 
@@ -310,7 +310,7 @@ let
             end
             offset += 1
             if dm1 in comb2nd_indices_nonbasic
-                offset += 1 
+                offset += 1
             end
         end
         comb1st_indices_firstoffsets[index] = first
@@ -550,4 +550,3 @@ if !isinteractive()
                         comb1st_indices_firstoffsets, comb1st_indices_lastoffsets,
                         comb2nd_indices_sorted_keys, comb_array, comb2nd_indices_nonbasic)
 end
-

utf8proc.c

@@ -101,7 +101,7 @@ UTF8PROC_DLLEXPORT const char *utf8proc_version(void) {
 }
 
 UTF8PROC_DLLEXPORT const char *utf8proc_unicode_version(void) {
-  return "15.1.0";
+  return "16.0.0";
 }
 
 UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(utf8proc_ssize_t errcode) {