ruby_unicode_prop 1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 995fd4cfd7ebc81e4621b58517e94c827cb76e06b40d99189537558813c060c4
+  data.tar.gz: 402b13940827cd2b4538c2f8ac83bda464c728eee6f6fbd774593c802c55d857
+SHA512:
+  metadata.gz: bf2a92ce22fb744822bd6a687c9c5874a8ee22c7dd72dcbadfd830d133f289615b8573107139c6f8de9a659500deda0d85454578d90608d284eef65f1ae38dce
+  data.tar.gz: 6dafbbabc31fe0133fd08815fd71b6d086697cfbab3180b3678ed5997c834de4a531f8f083053c5da8541ec031e33f1f8d01069540ee088f43af5319f63c5090

data/.gitignore

@@ -0,0 +1,51 @@
+# See https://help.github.com/articles/ignoring-files for more about ignoring files.
+#
+# If you find yourself ignoring temporary files generated by your text editor
+# or operating system, you probably want to add a global ignore instead:
+#   git config --global core.excludesfile '~/.gitignore_global'
+
+# Ignore bundler config.
+/.bundle
+/vendor/bundle
+
+# Ignore all logfiles and tempfiles.
+/log/*
+/tmp/*
+!/log/.keep
+!/tmp/.keep
+
+.rbenv-version
+# unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
+.rvmrc
+
+/node_modules
+/yarn-error.log
+
+.byebug_history
+
+*.[oa]
+*.so
+*~
+*.nogem
+*nogem.*
+*.bak
+*.BAK
+*.backup
+*.org
+*.orig
+*.elc
+*.pyc
+\#*\#
+
+# Elastic Beanstalk Files
+.elasticbeanstalk/*
+!.elasticbeanstalk/*.cfg.yml
+!.elasticbeanstalk/*.global.yml
+
+# yard
+*.yardoc
+
+# Ruby Gem doc
+*.gem
+doc/*
+

data/ChangeLog

@@ -0,0 +1,5 @@
+-----
+(Version: 1.0)
+2019-10-26  Masa Sakano
+
+ * Initial commit (I think pretty complete).

data/LICENSE.txt

@@ -0,0 +1,20 @@
+Copyright (c) 2012-2018 Scott Chacon and others
+
+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:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/Makefile

@@ -0,0 +1,23 @@
+ALL	= 
+
+objs	= 
+
+.SUFFIXES:	.so .o .c .f
+
+#.o.so:
+#	${LD} ${LFLAGS} -o $@ $< ${LINK_LIB}
+
+all: ${ALL}
+
+
+.PHONY: clean test doc
+clean:
+	$(RM) bin/*~
+
+## You may need RUBYLIB=`pwd`/lib:$RUBYLIB
+test:
+	rake test
+
+doc:
+	yard doc
+

data/README.en.rdoc

@@ -0,0 +1,153 @@
+
+= Command to print out Unicode characters that satisfy expressions for Ruby Regexp
+
+== Summary
+
+This package contains a standalone Ruby (executable) source file
++bin/ruby_unicode_prop+ - a command to be used from terminals etc, and it outputs (to STDOUT)
+Unicode characters and/or their hexagonal codepoints that satisfy one or more given expressions
+defined in Regexp in Ruby.  Specifically, they are +\p{XXX}+ -type expressions (e.g., +\p{Katakana}+)
+for Unicode, as well as +[[:blank:]]+ -type expressions for POSIX representation.
+
+Some supplementary files are found in the top and +test+ directories,
+none of which is essential to run the command.
+
+== Description
+
+The help doc is viewable with +-h+ (or +--help+) option, which all the basics:
+
+  % /YOUR/INSTALLED/PATH/ruby_unicode_prop -h
+  USAGE: ruby_unicode_prop [options] Property1 [Property2, ...]
+    Print all the characters and/or their hex-codepoints that have
+    the given "Unicode property" used in Ruby Regexp like \p{Currency_Symbol}
+    (or POSIX expression like [[:blank:]] if -p option is given).
+  
+  Options:
+      -c, --[no-]without-codepoint     Print characters only? (Def: false)
+      -n, --[no-]without-char          Print codepoints only? (Def: false)
+      -d, --delimiter=CHAR             Delimeter in output.
+      -l, --[no-]lowercase             Lower cases alphabets are used for Hex in codepoints (Def: false)
+      -p, --[no-]posix                 Use POSIX expression instead of Unicode (Def: false)
+          --[no-]list-property         Print all the Ruby Unicode properties and exit.
+  
+  Note1: Delimeter means one
+    (1) between multiple characters and codepoints if either of -n or -c is specified
+        (Default: Null for -c (characters only) and a new line for -n.
+    (2) between the number and character of each pair if both are specified
+        (Def: a whitespace), whereas the delimeter between pairs is always a newline.
+    To specify a newline as a delimiter, give 'NL'
+  Note2: Properties differ for '-p', 'ascii' in POSIX and 'ASCII' in Unicode.
+
+The reference file (used in the +-l+ option) is dynamically retrieved
+from https://github.com/k-takata/Onigmo/blob/master/doc/UnicodeProps.txt
+The definition file in the Ruby source tree is at +/enc/unicode/name2ctype.h+
+
+=== Limitations
+
+The output of this command is generated by the Ruby it runs, and hence
+is fully consistent with Regexp matching results with the same
+property names in any applications when you run the same Ruby.  That
+also means the output can depend on the version of the Ruby you run,
+because the unicode table has expanded over the years (such as emojis)
+and it will keep doing so.
+
+Currently, the searches by this command is limited up to the second
+Supplementary Plane
+({Supplementary Ideographic Plane}[https://en.wikipedia.org/wiki/Plane_(Unicode)#Supplementary_Ideographic_Plane]), which should be enough in practice
+in most cases now in 2019 and perhaps will be so for some time.
+
+In fact, in many practical cases, searching over
+only the {Basic Multilingual Plane}[https://en.wikipedia.org/wiki/Plane_(Unicode)#Basic_Multilingual_Plane] (up to 0xFFFF) is probably
+sufficient, though it seems the second Supplementary Plane does
+include groups of CJK characters some of which are still in use occasionally in
+modern days.  The maximum codepoint to search for is defined in the constant
++MAX_UNICODE_HEX+ near the beginning of the source code.  If you set
+it to a lower value, that can speed up the processing considerably,
+potentially noticeably.
+
+== Examples
+
+A typical example is as follows:
+
+  % bin/ruby_unicode_prop Greek
+  0370 Ͱ
+  0371 ͱ
+  0372 Ͳ
+  ……(snipped)……
+  0391 Α
+  0392 Β
+  0393 Γ
+  0394 Δ
+  ……(snipped)
+
+For some, POSIX (bracket) expressions are supported:
+
+  % bin/ruby_unicode_prop -p -d '___ ' punct
+  0021___ !
+  0022___ "
+  0023___ #
+  0024___ $
+  0025___ %
+  0026___ &
+  0027___ '
+  0028___ (
+  0029___ )
+  002A___ *
+  002B___ +
+  ……(snipped")
+
+Note the corresponding property name for Unicode +\p{}+ (a backslash
+followed by +p+ and curly brackets) is +Punct+ — it is capitalized,
+compared with the POSIX expression name.
+
+Or, you can specify multiple properties.  The order of the argument
+does not matter and the result is always in the order of the
+codepoints.   No duplication is produced, even if some of the
+specified properties have overlapped ranges of characters.  An example is, 
+
+  % bin/ruby_unicode_prop -c Number Terminal_Punctuation
+  !,.0123456789:;?²³¹¼½¾;……(snipped)
+  % bin/ruby_unicode_prop -c Number Terminal_Punctuation Close_Punctuation
+  !),.0123456789:;?]}²³¹¼½¾;……(snipped)
+
+== Install
+
+This script requires {Ruby}[http://www.ruby-lang.org] Version 2.0
+or above.
+
+If you install it as the standard Ruby Gem package, the executable +bin/ruby_unicode_prop+
+should be located automatically in your command-line search path.
+
+If not, place (copy) it in any of your command-line search paths.  It
+is a self-contained single file and does not need any external
+optional library except the standard library that come in default with Ruby 2.0.
+
+You may need to modify the first line (Shebang line) of the script to suit your
+environment (it should be unnecessary for Linux and macOS), or run it
+explicitly with your Ruby command as
+
+   Prompt% /YOUR/ENV/ruby /YOUR/INSTALLED/ruby_unicode_prop
+
+== Developer's note
+
+The master of this README file is found in
+[RubyGems/plain_text](https://rubygems.org/gems/ruby_unicode_prop)
+
+=== Tests
+
+Ruby codes under the directory <tt>test/</tt> are the test scripts.
+You can run them from the top directory as <tt>ruby test/test_****.rb</tt>
+or simply run <tt>make test</tt>.
+
+
+== Known bugs and Todo items
+
+None.
+
+
+== Copyright
+
+Author::  Masa Sakano < info a_t wisebabel dot com >
+Versions:: The versions of this package follow Semantic Versioning (2.0.0) http://semver.org/
+License:: MIT
+

data/Rakefile

@@ -0,0 +1,9 @@
+require 'rake/testtask'
+
+Rake::TestTask.new do |t|
+  t.libs << 'test'
+end
+
+desc "Run tests"
+task :default => :test
+

data/bin/ruby_unicode_prop

@@ -0,0 +1,186 @@
+#!/usr/bin/env ruby
+# -*- coding: utf-8 -*-
+
+# Script to print a list of either/both characters or hexadecimal codepoints of
+# the specified Unicode properties.
+#
+# @author: M. Sakano (Wise Babel Ltd)
+
+require 'optparse'
+require 'net/http'
+require 'uri'
+
+URL_RUBY_UNICODE_PROPS = 'https://raw.githubusercontent.com/k-takata/Onigmo/master/doc/UnicodeProps.txt'
+MAX_UNICODE_HEX = 0x2FFFF  # Plane 0-2 (up to Supplementary Ideographic Plane) of Unicode
+
+BANNER = <<"__EOF__"
+USAGE: #{File.basename($0)} [options] Property1 [Property2, ...]
+  Print all the characters and/or their hex-codepoints that have
+  the given "Unicode property" used in Ruby Regexp like \\p{Currency_Symbol}
+  (or POSIX expression like [[:blank:]] if -p option is given).
+__EOF__
+
+# Initialising the hash for the command-line options.
+OPTS = {
+  with_char: true,
+  with_codepoint: true,
+  delimiter: nil,
+  posix: false,
+  lowercase: false,
+  list_property: false,
+  # :chatter => 3,        # Default
+  debug: false,
+}
+
+# Function to handle the command-line arguments.
+#
+# ARGV will be modified, and the constant variable OPTS is set.
+#
+# @return [Hash]  Optional-argument hash.
+#
+def handle_argv
+  opt = OptionParser.new(BANNER)
+  opt.separator ""
+  opt.separator "Options:"
+  opt.on('-c', '--[no-]without-codepoint', sprintf("Print characters only? (Def: %s)", (!OPTS[:with_codepoint]).inspect), FalseClass){|v| OPTS[:with_codepoint] = v} # memo: "-c" for "Characters only"
+  opt.on('-n', '--[no-]without-char',      sprintf("Print codepoints only? (Def: %s)", (!OPTS[:with_char]).inspect),      FalseClass){|v| OPTS[:with_char] = v}      # memo: "-n" for "codepoints Number only"
+  opt.on('-d', '--delimiter=CHAR', sprintf("Delimeter in output.", OPTS[:delimiter].inspect)) {|v| OPTS[:delimiter] = v}
+  opt.on('-l', '--[no-]lowercase', sprintf("Lower cases alphabets are used for Hex in codepoints (Def: %s)", OPTS[:lowercase].inspect)) {|v| OPTS[:lowercase] = v} # memo: "-l" for "Lower case"
+  opt.on('-p', '--[no-]posix', sprintf("Use POSIX expression instead of Unicode (Def: %s)", OPTS[:posix].inspect)) {|v| OPTS[:posix] = v} # memo: "-p" for "POSIX"
+  opt.on(      '--[no-]list-property', 'Print all the Ruby Unicode properties and exit.') {|v| OPTS[:list_property] = v}
+  # opt.on(  '--version', "Display the version and exits.", TrueClass) {|v| OPTS[:version] = v}  # Consider opts.on_tail
+  # opt.on(  '--[no-]debug', "Debug (Def: false)") {|v| OPTS[:debug] = v}
+  opt.separator ""
+  opt.separator "Note1: Delimeter means one"
+  opt.separator "  (1) between multiple characters and codepoints if either of -n or -c is specified (Default: Null for -c (characters only) and a new line for -n."
+  opt.separator "  (2) between the number and character of each pair if both are specified (Def: a whitespace), whereas the delimeter between pairs is always a newline."
+  opt.separator "  To specify a newline as a delimiter, give 'NL'"
+  opt.separator "Note2: Properties differ for '-p', 'ascii' in POSIX and 'ASCII' in Unicode."
+  opt.separator "Reference: https://github.com/k-takata/Onigmo/blob/master/doc/UnicodeProps.txt"
+  # opt.separator "  Ruby-Source: /enc/unicode/name2ctype.h"
+
+  opt.parse!(ARGV)
+
+  # exit if --list-property
+  (puts get_file_unicode_properties; exit 1) if OPTS[:list_property]
+
+  if !OPTS[:with_char] && !OPTS[:with_codepoint]
+    warn "Specify (or do not specify at all) what to print (do not specify -p and -c simultaneously)."
+    exit 1
+  end
+
+  if ARGV.size == 0
+    warn "ERROR: Specify Unicode property(ies). To see help, run #{File.basename($0)} --help"
+    exit 1
+  end
+
+  # Adjustments
+  OPTS[:delimiter] = "\n" if 'NL' == OPTS[:delimiter]  # Special case; 'NL' means a newline.
+  OPTS[:delimiter] ||= 
+    if    OPTS[:with_char] && OPTS[:with_codepoint]
+      " "
+    elsif OPTS[:with_char]
+      ""
+    else
+      $/
+    end
+
+  OPTS
+end
+
+# Returns the array of characters that satisfies the Property conditions.
+#
+# @param argv [ARGV]
+# @param opts [Hash] Hash of command-line options.
+# @return [Array]
+def get_ary_chars(argv, opts)
+  if opts[:posix]
+    # for 'ascii' and 'blank', joined as [[:ascii:][:blank:]]
+    fmt1 = '[%s]'
+    fmt2 = '[:%s:]'
+    fmt_deli = ""
+  else
+    # for 'ASCII' and 'Digit', joined as (?:\p{ASCII}|\p{Digit})
+    fmt1 = '(?:%s)'
+    fmt2 = '\\p{%s}'
+    fmt_deli = '|'
+  end
+
+  prop_q = fmt1 % argv.map{|c| fmt2 % Regexp.quote(c)}.join(fmt_deli)
+
+  fmt0 = (opts[:lowercase] ? "%04x" : "%04X")
+
+  arret = []
+  begin
+    (0..MAX_UNICODE_HEX).each do |i|
+      s = i.chr(Encoding::UTF_8) rescue next  # invalid codepoint 0xD800 in UTF-8 (RangeError)
+      next if Regexp.new(prop_q) !~ s
+      arret <<
+      if    opts[:with_char] && opts[:with_codepoint]
+        (fmt0+"%s%s") % [i, opts[:delimiter], s]
+      elsif opts[:with_char]
+        s
+      else
+        fmt0 % i
+      end
+    end
+  rescue RegexpError => er
+    warn '(RegexpError) '+er.message
+    exit 1
+  end
+
+  arret
+end
+
+
+# Returns the array of characters that satisfies the Property conditions.
+#
+# If encountering ERROR, this directly exits!
+#
+# @return [String]
+def get_file_unicode_properties
+  url = URL_RUBY_UNICODE_PROPS
+  #url = "http://google.com/naiyo.txt"
+  #url = "http://googlegoo345.com/naiyo.txt"
+  begin
+    resp = Net::HTTP.get_response( URI.parse url )
+  rescue SocketError => er
+    warn(er.message + "\nERROR: Host not reachable: " + url)
+    exit 1
+  end
+
+  return "Fetched from: %s\n%s" % [url, resp.body] if resp.code.to_i == 200
+
+  warn "ERROR in HTTP response (#{resp.code}) - File not found or something: "+url
+  exit 1
+end
+
+
+################################################
+# MAIN
+################################################
+
+$stdout.sync=true
+$stderr.sync=true
+
+# Handle the command-line options => OPTS
+begin
+  handle_argv()
+rescue OptionParser::InvalidOption, OptionParser::AmbiguousOption => er
+  warn er
+  exit 1
+end
+
+arret = get_ary_chars(ARGV, OPTS)
+
+if OPTS[:with_char] && OPTS[:with_codepoint]
+  puts arret.join($/)
+else
+  puts arret.join(OPTS[:delimiter])
+end
+
+exit
+
+__END__
+
+

data/ruby_unicode_prop.gemspec

@@ -0,0 +1,50 @@
+# -*- encoding: utf-8 -*-
+
+require 'rake'
+
+Gem::Specification.new do |s|
+  s.name = %q{ruby_unicode_prop}.sub(/.*/){|c| (c == File.basename(Dir.pwd)) ? c : raise("ERROR: s.name=(#{c}) in gemspec seems wrong!")}
+  s.version = "1.0"
+  # s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.bindir = 'bin'
+  %w(ruby_unicode_prop).each do |f|
+    path = s.bindir+'/'+f
+    File.executable?(path) ? s.executables << f : raise("ERROR: Executable (#{path}) is not executable!")
+  end
+  s.authors = ["Masa Sakano"]
+  s.date = %q{2019-10-26}
+  s.summary = %q{Command to print the characters and hex-codepoints with the given Unicode properties}
+  s.description = %q{This module provides utility functions and methods to handle plain text, classes Part/Paragraph/Boundary to represent the logical structure of a document and ParseRule to describe the rules to parse plain text to produce a Part-type Ruby instance.}
+  # s.email = %q{abc@example.com}
+  s.extra_rdoc_files = [
+     #"LICENSE.txt",
+     "README.en.rdoc",
+  ]
+  s.license = 'MIT'
+  s.files = FileList['.gitignore','lib/**/*.rb','[A-Z]*','test/**/*.rb', '*.gemspec', 'bin'].to_a.delete_if{ |f|
+    ret = false
+    arignore = IO.readlines('.gitignore')
+    arignore.map{|i| i.chomp}.each do |suffix|
+      if File.fnmatch(suffix, File.basename(f))
+        ret = true
+        break
+      end
+    end
+    ret
+  }
+  s.files.reject! { |fn| File.symlink? fn }
+  # s.add_runtime_dependency 'rails'
+  # s.add_development_dependency "bourne", [">= 0"]
+  s.homepage = %q{https://www.wisebabel.com}
+  s.rdoc_options = ["--charset=UTF-8"]
+
+  # s.require_paths = ["lib"]	# Default "lib"
+  s.required_ruby_version = '>= 2.0'
+  s.test_files = Dir['test/**/*.rb']
+  s.test_files.reject! { |fn| File.symlink? fn }
+  # s.requirements << 'libmagick, v6.0' # Simply, info to users.
+  # s.rubygems_version = %q{1.3.5}      # This is always set automatically!!
+
+  s.metadata["yard.run"] = "yri" # use "yard" to build full HTML docs.
+end
+

data/test/test_ruby_unicode_prop.rb

@@ -0,0 +1,140 @@
+# -*- encoding: utf-8 -*-
+
+# @author: M. Sakano (Wise Babel Ltd)
+
+require 'plain_text'
+require 'open3'
+
+$stdout.sync=true
+$stderr.sync=true
+# print '$LOAD_PATH=';p $LOAD_PATH
+
+#################################################
+# Unit Test
+#################################################
+
+gem "minitest"
+# require 'minitest/unit'
+require 'minitest/autorun'
+
+class TestUnitRubyUnicodeProp < MiniTest::Test
+  T = true
+  F = false
+  SCFNAME = File.basename(__FILE__)
+  EXE = "%s/../bin/%s" % [File.dirname(__FILE__), File.basename(__FILE__).sub(/^test_(.+)\.rb/, '\1')]
+
+  def setup
+  end
+
+  def teardown
+  end
+
+  def test_ruby_unicode_prop01
+    o, e, s = Open3.capture3 EXE+" ASCII"
+    assert_equal 0, s.exitstatus
+    assert_match(/\A0000 .\n0001 .\n.*\n004A J/m, o)
+    assert_operator 70, '<', o.count($/)
+    assert_empty e
+    size_ascii = o.size
+
+    o, e, s = Open3.capture3 EXE+" -l ASCII"
+    assert_equal 0, s.exitstatus
+    assert_match(/\A0000 .\n0001 .\n.*\n004a J/m, o)
+
+    o, e, s = Open3.capture3 EXE+" ascii"
+    assert_equal 0, s.exitstatus
+    assert_match(/\A0000 .\n0001 .\n.*\n004A J/m, o)
+    assert_operator 70, '<', o.count($/)
+    assert_empty e
+
+    o, e, s = Open3.capture3 EXE+" -p ASCII" # => Error (b/c "ascii" in the POSIX form)
+    assert_equal 1, s.exitstatus
+    assert_match(/invalid POSIX/i, e)
+
+    o, e, s = Open3.capture3 EXE+" -d H ASCII"
+    assert_equal 0, s.exitstatus
+    assert_match(/\A0000H.\n0001H.\n.*\n004AHJ/m, o)
+    o, e, s = Open3.capture3 EXE+" --delimiter=H ASCII"
+    assert_match(/\A0000H.\n0001H.\n.*\n004AHJ/m, o)
+
+    o, e, s = Open3.capture3 EXE+" --without-codepoint ASCII"  # characters only (-c)
+    assert_equal 0, s.exitstatus
+    assert_equal 0, o[40..-1].chomp.count($/) # "\n" is included in ASCII itself.
+    assert_equal 1, o.count(" ")
+    assert_match(/XYZ/m, o)
+    assert_empty e
+
+    o, e, s = Open3.capture3 EXE+" -c -d H ASCII"  # characters only (-c)
+    assert_equal 0, o[40..-1].chomp.count($/) # "\n" is included in ASCII itself.
+    assert_equal 1, o.count(" ")
+    assert_match(/XHYHZ/m, o)
+    assert_empty e
+    
+    o, e, s = Open3.capture3 EXE+" -c -d NL ASCII"  # characters only (-c)
+    assert_operator 70, '<', o.count($/), "Special case of 'NL' is not handled correctly."
+    assert_equal 1, o.count(" ")
+    assert_match(/X\nY\nZ/m, o)
+    assert_empty e
+    
+    o, e, s = Open3.capture3 EXE+" --without-char ASCII"  # codepoints only (-n)
+    assert_equal 0, o.count(" ")
+    assert_equal 0, o.count("X")
+    assert_operator 70, '<', o.count($/)
+    assert_equal "0000\n0001\n", o[0..9]
+    assert_empty e
+
+    o, e, s = Open3.capture3 EXE+" -n -d H ASCII"  # codepoints only (-n)
+    assert_equal 0, o[60..-1].chomp.count($/) # "\n" is included in ASCII itself.
+    assert_operator 70, '<', o.count(?H)
+    assert_equal "0000H0001H", o[0..9]
+    assert_match(/\A0000H0001H.*H004AH/m, o)
+    assert_empty e
+
+    o, e, s = Open3.capture3 EXE+" -l -n -d H ASCII"  # codepoints only (-n)
+    assert_match(/\A0000H0001H.*H004aH/m, o)
+
+    # Multiple arguments
+    o, e, s = Open3.capture3 EXE+" Currency_Symbol ASCII"
+    assert_equal 0, s.exitstatus
+    assert_match(/0023 \#\n0024 \$\n.*00A3 £/m, o)
+    assert_operator size_ascii, '<', o.size  # Increased size (because Currency Symbols are added!)
+
+    o, e, s = Open3.capture3 EXE+" ASCII Digit"
+    ou_ad = o
+    si_ad = o.size
+    o, e, s = Open3.capture3 EXE+" Digit ASCII"
+    ou_da = o
+    o, e, s = Open3.capture3 EXE+" Digit"
+    size_digit  = o.size
+
+    assert_equal    ou_ad, ou_da, 'Should be unordered for multiple arguments.'
+    assert_operator si_ad, '<', size_ascii + size_digit, 'Duplication should not appear.'
+  end
+
+
+  ## tests of Errors ##
+  def test_ruby_unicode_prop_error02
+    o, e, s = Open3.capture3 EXE+" ASCII -d" # => Error (-d without a parameter)
+    assert_equal 1, s.exitstatus
+    assert_empty o
+
+    o, e, s = Open3.capture3 EXE+" -n -c ASCII" # => Error
+    assert_equal 1, s.exitstatus
+    assert_empty o
+    assert_match(/specify/m, e)
+
+    o, e, s = Open3.capture3 EXE+" -Z ASCII" # => Error
+    assert_equal 1, s.exitstatus
+    assert_match(/(invalid|ambiguous) option/i, e)
+
+    o, e, s = Open3.capture3 EXE+" naiyo" # => Error
+    assert_equal 1, s.exitstatus
+    assert_empty o
+    assert_match(/RegexpError/m, e)
+
+    o, e, s = Open3.capture3 EXE  # => Error (No arguments specified)
+    assert_equal 1, s.exitstatus
+    assert_empty o
+  end
+end # class TestUnitRubyUnicodeProp < MiniTest::Test
+

metadata

@@ -0,0 +1,60 @@
+--- !ruby/object:Gem::Specification
+name: ruby_unicode_prop
+version: !ruby/object:Gem::Version
+  version: '1.0'
+platform: ruby
+authors:
+- Masa Sakano
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2019-10-26 00:00:00.000000000 Z
+dependencies: []
+description: This module provides utility functions and methods to handle plain text,
+  classes Part/Paragraph/Boundary to represent the logical structure of a document
+  and ParseRule to describe the rules to parse plain text to produce a Part-type Ruby
+  instance.
+email: 
+executables:
+- ruby_unicode_prop
+extensions: []
+extra_rdoc_files:
+- README.en.rdoc
+files:
+- ".gitignore"
+- ChangeLog
+- LICENSE.txt
+- Makefile
+- README.en.rdoc
+- Rakefile
+- bin/ruby_unicode_prop
+- ruby_unicode_prop.gemspec
+- test/test_ruby_unicode_prop.rb
+homepage: https://www.wisebabel.com
+licenses:
+- MIT
+metadata:
+  yard.run: yri
+post_install_message: 
+rdoc_options:
+- "--charset=UTF-8"
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '2.0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.0.3
+signing_key: 
+specification_version: 4
+summary: Command to print the characters and hex-codepoints with the given Unicode
+  properties
+test_files:
+- test/test_ruby_unicode_prop.rb