Port ruby data_generator.rb to Julia (#258)

* Port ruby data_generator.rb to Julia

This reduces the number of dependencies needed when regenerating the C
code. The new code also separates C code generation from unicode data
analysis somewhat more cleanly which should be better factored for
generating a Julia version of the data files in the future.

The output is identical to the original Ruby script, for now. Some bugs
which were found in the process are noted as FIXMEs in the Julia source
and can be fixed next.

* Replace some explicit loops with a utility function

* fixup! Port ruby data_generator.rb to Julia

* Update Makefile

* Update data/Makefile

* Update data/Makefile

* Update data/Makefile

* Update data/Makefile

* Update data/data_generator.jl

---------

Co-authored-by: Steven G. Johnson <[email protected]>

Author: c42f

Makefile

@@ -73,7 +73,7 @@ manifest: MANIFEST.new
 
 # real targets
 
-data/utf8proc_data.c.new: libutf8proc.$(SHLIB_EXT) data/data_generator.rb data/charwidths.jl
+data/utf8proc_data.c.new: libutf8proc.$(SHLIB_EXT) data/data_generator.jl
 	$(MAKE) -C data utf8proc_data.c.new
 
 utf8proc.o: utf8proc.h utf8proc.c utf8proc_data.c

data/Makefile

@@ -1,11 +1,10 @@
 # Unicode data generation rules.  Except for the test data files, most
 # users will not use these Makefile rules, which are primarily to re-generate
 # unicode_data.c when we get a new Unicode version or charwidth data; they
-# require ruby and julia to be installed.
+# require julia to be installed.
 
 # programs
 CURL=curl
-RUBY=ruby
 PERL=perl
 MAKE=make
 JULIA=julia
@@ -15,11 +14,11 @@ CURLFLAGS = --retry 5 --location
 
 .DELETE_ON_ERROR:
 
-utf8proc_data.c.new: data_generator.rb UnicodeData.txt GraphemeBreakProperty.txt DerivedCoreProperties.txt CompositionExclusions.txt CaseFolding.txt CharWidths.txt emoji-data.txt
-	$(RUBY) data_generator.rb < UnicodeData.txt > $@
+RAWDATA = UnicodeData.txt GraphemeBreakProperty.txt DerivedCoreProperties.txt CompositionExclusions.txt CaseFolding.txt EastAsianWidth.txt emoji-data.txt
 
-CharWidths.txt: charwidths.jl EastAsianWidth.txt
-	$(JULIA) charwidths.jl > $@
+utf8proc_data.c.new: data_generator.jl $(RAWDATA)
+	$(JULIA) --project=. -e 'using Pkg; Pkg.instantiate()'
+	$(JULIA) --project=. data_generator.jl > $@
 
 # Unicode data version (must also update utf8proc_unicode_version function)
 UNICODE_VERSION=15.1.0
@@ -52,12 +51,12 @@ emoji-data.txt:
 	$(CURL) $(CURLFLAGS) -o $@ $(URLCACHE)https://unicode.org/Public/$(UNICODE_VERSION)/ucd/emoji/emoji-data.txt
 
 Uppercase.txt: DerivedCoreProperties.txt
-	$(RUBY) -e 'puts File.read("DerivedCoreProperties.txt")[/# Derived Property: Uppercase.*?# Total code points:/m]' > $@
+	$(JULIA) -e 'print(match(r"# Derived Property: Uppercase.*?# Total code points:"s, read("DerivedCoreProperties.txt", String)).match)' > $@
 
 Lowercase.txt: DerivedCoreProperties.txt
-	$(RUBY) -e 'puts File.read("DerivedCoreProperties.txt")[/# Derived Property: Lowercase.*?# Total code points:/m]' > $@
+	$(JULIA) -e 'print(match(r"# Derived Property: Lowercase.*?# Total code points:"s, read("DerivedCoreProperties.txt", String)).match)' > $@
 
 clean:
-	rm -f UnicodeData.txt EastAsianWidth.txt GraphemeBreakProperty.txt DerivedCoreProperties.txt CompositionExclusions.txt CaseFolding.txt NormalizationTest.txt GraphemeBreakTest.txt CharWidths.txt emoji-data.txt
+	rm -f $(RAWDATA) NormalizationTest.txt GraphemeBreakTest.txt
 	rm -f Uppercase.txt Lowercase.txt
 	rm -f utf8proc_data.c.new

data/Manifest.toml

@@ -0,0 +1,69 @@
+# This file is machine-generated - editing it directly is not advised
+
+julia_version = "1.9.3"
+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"
+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"
+
+[[deps.UUIDs]]
+deps = ["Random", "SHA"]
+uuid = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
+
+[[deps.libblastrampoline_jll]]
+deps = ["Artifacts", "Libdl"]
+uuid = "8e850b90-86db-534c-a0d3-1478176c7d93"
+version = "5.8.0+0"

data/Project.toml

@@ -0,0 +1,2 @@
+[deps]
+OffsetArrays = "6fe1bfb0-de20-5000-8ca7-80f57d26f881"