unisec 0.0.6 → 0.0.8

data/lib/unisec/utils.rb

@@ -20,33 +20,66 @@ class Integer
   end
 end
 
+class String
+  # Convert a string to a boolean
+  # @return [TrueClass|FalseClass]
+  # @example
+  #   "true".to_bool # => true
+  def to_bool
+    case to_s.chomp.downcase
+    when 'true', 'yes', 'y', '1'
+      true
+    when 'false', 'no', 'n', '0'
+      false
+    else
+      raise ArgumentError, "invalid value for Boolean: #{str.inspect}"
+    end
+  end
+end
+
+class Range
+  # Is a range included in another range? Are all values of range B included in range A?
+  # @param range [Range]
+  # @return [TrueClass|FalseClass]
+  # @example
+  #   (1..10).include_range?(2..11) # => false
+  #   (1..10).include_range?(2..4) # => true
+  def include_range?(range)
+    self.begin <= range.begin && self.end >= range.end
+  end
+end
+
 module Unisec
   # Generic stuff not Unicode-related that can be re-used.
   module Utils
     # About string conversion and manipulation.
     module String
       # Convert a string input into the chosen type.
-      # @param input [String] If the target type is `:integer`, the string must represent a number encoded in
-      #   hexadecimal, decimal, binary. If it's a Unicode string, only the first code point will be taken into account.
-      # @param target_type [Symbol] Convert to the chosen type. Currently only supports `:integer`.
+      # @param input [String] If the input is a Unicode string, only the first code point will be taken into account.
+      #   The input must represent a character encoded in hexadecimal, decimal, binary or standard code point format.
+      #   See {convert_to_integer} and {convert_to_char} for detailed examples.
+      # @param target_type [Symbol] Convert to the chosen type. Currently only supports `:integer` and `:char`.
       # @return [Variable] The type of the output depends on the chosen `target_type`.
       # @example
       #   Unisec::Utils::String.convert('0x1f4a9', :integer) # => 128169
+      #   Unisec::Utils::String.convert('0x1f4a9', :char) # => "💩"
       def self.convert(input, target_type)
         case target_type
         when :integer
           convert_to_integer(input)
+        when :char
+          convert_to_char(input)
         else
           raise TypeError, "Target type \"#{target_type}\" not avaible"
         end
       end
 
-      # Internal method used for {.convert}.
+      # Internal method used for {convert}.
       #
       # Convert a string input into integer.
-      # @param input [String] The string must represent a number encoded in hexadecimal, decimal, binary. If it's a
-      #   Unicode string, only the first code point will be taken into account. The input type is determined
-      #   automatically based on the prefix.
+      # @param input [String] If the input is a Unicode string, only the first code point will be taken into account.
+      #   The input must represent a character encoded in hexadecimal, decimal, binary, standard code point format.
+      #   The input type is determined automatically based on the prefix.
       # @return [Integer]
       # @example
       #   # Hexadecimal
@@ -57,10 +90,14 @@ module Unisec
       #   Unisec::Utils::String.convert_to_integer('0b11111010010101001') # => 128169
       #   # Unicode string
       #   Unisec::Utils::String.convert_to_integer('💩') # => 128169
+      #   # Standardized format of hexadecimal code point
+      #   Unisec::Utils::String.convert_to_integer('U+1F4A9') # => 128169
       def self.convert_to_integer(input)
         case autodetect(input)
         when :hexadecimal
           input.hex2dec(prefix: '0x').to_i
+        when :stdcp
+          input.hex2dec(prefix: 'U+').to_i
         when :decimal
           input.to_i
         when :binary
@@ -72,11 +109,38 @@ module Unisec
         end
       end
 
+      # Internal method used for {convert}.
+      #
+      # Convert a string input into a character.
+      # @param input [String] If the input is a Unicode string, only the first code point will be taken into account.
+      #   The input must represent a character encoded in hexadecimal, decimal, binary, standard code point format.
+      #   The input type is determined automatically based on the prefix.
+      # @return [String]
+      # @example
+      #   # Hexadecimal
+      #   Unisec::Utils::String.convert_to_char('0x1f4a9') # => "💩"
+      #   # Decimal
+      #   Unisec::Utils::String.convert_to_char('0d128169') # => "💩"
+      #   # Binary
+      #   Unisec::Utils::String.convert_to_char('0b11111010010101001') # => "💩"
+      #   # Unicode string
+      #   Unisec::Utils::String.convert_to_char('💩') # => "💩"
+      #   # Standardized format of hexadecimal code point
+      #   Unisec::Utils::String.convert_to_char('U+1F4A9') # => "💩"
+      def self.convert_to_char(input)
+        case autodetect(input)
+        when :hexadecimal, :stdcp, :decimal, :binary, :string
+          [convert(input, :integer)].pack('U')
+        else
+          raise TypeError, "Input \"#{input}\" is not of the expected type"
+        end
+      end
+
       # Internal method used for {.convert}.
       #
       # Autodetect the representation type of the string input.
       # @param str [String] Input.
-      # @return [Symbol] the detected type: `:hexadecimal`, `:decimal`, `:binary`, `:string`.
+      # @return [Symbol] the detected type: `:hexadecimal`, `:decimal`, `:binary`, `:string`, :stdcp.
       # @example
       #   # Hexadecimal
       #   Unisec::Utils::String.autodetect('0x1f4a9') # => :hexadecimal
@@ -86,10 +150,14 @@ module Unisec
       #   Unisec::Utils::String.autodetect('0b11111010010101001') # => :binary
       #   # Unicode string
       #   Unisec::Utils::String.autodetect('💩') # => :string
+      #   # Standardized format of hexadecimal code point
+      #   Unisec::Utils::String.autodetect('U+1F4A9') # => :stdcp
       def self.autodetect(str)
         case str
-        when /0x[0-9a-fA-F]/
+        when /0x[0-9a-fA-F]+/
           :hexadecimal
+        when /U\+[0-9A-F]+/
+          :stdcp
         when /0d[0-9]+/
           :decimal
         when /0b[0-1]+/
@@ -108,6 +176,72 @@ module Unisec
       def self.grapheme_reverse(str)
         str.grapheme_clusters.reverse.join
       end
+
+      # Display the code point in Unicode format for a given character (code point as string)
+      # @param chr [String] Unicode code point (as character / string)
+      # @return [String] code point in Unicode format
+      # @todo Replace this method by target type :stdcp in String.convert()
+      # @example
+      #   Unisec::Utils::String.char2codepoint('💎') # => "U+1F48E"
+      def self.char2codepoint(chr)
+        Integer.deccp2stdhexcp(chr.codepoints.first)
+      end
+
+      # Display the code points in Unicode format for the given characters (code points as string)
+      # @param chrs [String] Unicode code points (as characters / string)
+      # @return [String] code points in Unicode format
+      # @example
+      #   Unisec::Utils::String.chars2codepoints("ỳ́") # => "U+0079 U+0300 U+0301"
+      #   Unisec::Utils::String.chars2codepoints("🧑‍🌾") # => "U+1F9D1 U+200D U+1F33E"
+      def self.chars2codepoints(chrs)
+        out = []
+        chrs.each_char do |chr|
+          out << char2codepoint(chr)
+        end
+        out.join(' ')
+      end
+
+      # Display the code points in integer format for the given characters (code points as string)
+      # @param chrs [String] Unicode code points (as characters / string)
+      # @return [String] code points in integer format
+      # @example
+      #   Unisec::Utils::String.chars2intcodepoints('I 💕 Ruby 💎') # => "73 32 128149 32 82 117 98 121 32 128142"
+      def self.chars2intcodepoints(chrs)
+        chrs.codepoints.map(&:to_s).join(' ')
+      end
+
+      # Convert a string of hex encoded Unicode code points range to actual
+      # integer Ruby range.
+      # @param range_str [String] Unicode code points range as in data/Blocks.txt
+      # @return [Range]
+      # @example
+      #   Unisec::Utils::String::to_range('0080..00FF') # => 128..255
+      def self.to_range(range_str)
+        ::Range.new(*range_str.split('..').map { |x| x.hex2dec.to_i })
+      end
+    end
+
+    module Integer
+      # Convert from decimal code point to standardized format hexadecimal code point
+      # @param int_cp [Integer] Code point in decimal format
+      # @return [String] code point in Unicode format
+      # @todo Replace this method by the Integer.convert()
+      # @example
+      #   Unisec::Utils::Integer.deccp2stdhexcp(128640) # => "U+1F680"
+      def self.deccp2stdhexcp(int_cp)
+        "U+#{format('%.4x', int_cp).upcase}"
+      end
+    end
+
+    module Range
+      # Convert a (integer) range to a range of Unicode code points
+      # @param range [::Range]
+      # @return [String]
+      # @example
+      #   Unisec::Utils::Range.range2codepoint_range(1048576..1114111) # => "U+100000 - U+10FFFF"
+      def self.range2codepoint_range(range)
+        "#{Integer.deccp2stdhexcp(range.begin)} - #{Integer.deccp2stdhexcp(range.end)}"
+      end
     end
   end
 end

data/lib/unisec/version.rb

@@ -2,5 +2,5 @@
 
 module Unisec
   # Version of unisec library and app
-  VERSION = '0.0.6'
+  VERSION = '0.0.8'
 end

data/lib/unisec/versions.rb

@@ -55,6 +55,10 @@ module Unisec
         ucd_derivedname: {
           version: Unisec::Rugrep.ucd_derivedname_version,
           label: 'UCD (data/DerivedName.txt)'
+        },
+        ucd_blocks: {
+          version: Unisec::Blocks.ucd_blocks_version,
+          label: 'UCD (data/Blocks.txt)'
         }
       }
     end
@@ -81,6 +85,7 @@ module Unisec
         colorize.call(:twittercldr_cldr) +
         colorize.call(:ruby_unicode_emoji) +
         colorize.call(:ucd_derivedname) +
+        colorize.call(:ucd_blocks) +
         Paint["\nGems:\n", :underline] +
         colorize.call(:unisec) +
         colorize.call(:twittercldr) +

data/lib/unisec.rb

@@ -3,9 +3,12 @@
 require 'unisec/version'
 
 require 'unisec/bidi'
+require 'unisec/blocks'
 require 'unisec/confusables'
+require 'unisec/decdump'
 require 'unisec/hexdump'
 require 'unisec/normalization'
+require 'unisec/planes'
 require 'unisec/properties'
 require 'unisec/rugrep'
 require 'unisec/size'

metadata

@@ -1,14 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: unisec
 version: !ruby/object:Gem::Version
-  version: 0.0.6
+  version: 0.0.8
 platform: ruby
 authors:
 - Alexandre ZANNI
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-05-17 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ctf-party
@@ -16,14 +15,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.0'
+        version: '5.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.0'
+        version: '5.0'
 - !ruby/object:Gem::Dependency
   name: dry-cli
   requirement: !ruby/object:Gem::Requirement
@@ -58,34 +57,28 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '6.11'
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 6.11.5
+        version: '6.13'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '6.11'
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 6.11.5
+        version: '6.13'
 - !ruby/object:Gem::Dependency
   name: unicode-confusable
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.9'
+        version: '1.12'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.9'
+        version: '1.12'
 description: 'Toolkit for security research manipulating Unicode: confusables, homoglyphs,
   hexdump, code point, UTF-8, UTF-16, UTF-32, properties, regexp search, size, grapheme,
   surrogates, version, ICU, CLDR, UCD, BiDi, normalization'
@@ -97,22 +90,28 @@ extra_rdoc_files: []
 files:
 - LICENSE
 - bin/unisec
+- data/Blocks.txt
 - data/DerivedName.txt
 - lib/unisec.rb
 - lib/unisec/bidi.rb
+- lib/unisec/blocks.rb
 - lib/unisec/cli/bidi.rb
+- lib/unisec/cli/blocks.rb
 - lib/unisec/cli/cli.rb
 - lib/unisec/cli/confusables.rb
-- lib/unisec/cli/hexdump.rb
+- lib/unisec/cli/dump.rb
 - lib/unisec/cli/normalization.rb
+- lib/unisec/cli/planes.rb
 - lib/unisec/cli/properties.rb
 - lib/unisec/cli/rugrep.rb
 - lib/unisec/cli/size.rb
 - lib/unisec/cli/surrogates.rb
 - lib/unisec/cli/versions.rb
 - lib/unisec/confusables.rb
+- lib/unisec/decdump.rb
 - lib/unisec/hexdump.rb
 - lib/unisec/normalization.rb
+- lib/unisec/planes.rb
 - lib/unisec/properties.rb
 - lib/unisec/rugrep.rb
 - lib/unisec/size.rb
@@ -120,18 +119,17 @@ files:
 - lib/unisec/utils.rb
 - lib/unisec/version.rb
 - lib/unisec/versions.rb
-homepage: https://github.com/Acceis/unisec
+homepage: https://github.com/noraj/unisec
 licenses:
 - MIT
 metadata:
   yard.run: yard
-  bug_tracker_uri: https://github.com/Acceis/unisec/issues
-  changelog_uri: https://github.com/Acceis/unisec/releases
-  documentation_uri: https://acceis.github.io/unisec/
-  homepage_uri: https://github.com/Acceis/unisec
-  source_code_uri: https://github.com/Acceis/unisec/
+  bug_tracker_uri: https://github.com/noraj/unisec/issues
+  changelog_uri: https://github.com/noraj/unisec/releases
+  documentation_uri: https://noraj.github.io/unisec/
+  homepage_uri: https://github.com/noraj/unisec
+  source_code_uri: https://github.com/noraj/unisec/
   rubygems_mfa_required: 'true'
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -139,18 +137,17 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 3.0.0
+      version: 3.2.0
   - - "<"
     - !ruby/object:Gem::Version
-      version: '4.0'
+      version: '5.0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.3
-signing_key:
+rubygems_version: 4.0.3
 specification_version: 4
 summary: Unicode Security Toolkit
 test_files: []

data/lib/unisec/cli/hexdump.rb

@@ -1,47 +0,0 @@
-# frozen_string_literal: true
-
-require 'dry/cli'
-require 'unisec'
-
-module Unisec
-  module CLI
-    module Commands
-      # CLI command `unisec hexdumps` for the class {Unisec::Hexdump} from the lib.
-      #
-      # Example:
-      #
-      # ```plaintext
-      # $ unisec hexdump "ACCEIS"
-      # UTF-8: 41 43 43 45 49 53
-      # UTF-16BE: 0041 0043 0043 0045 0049 0053
-      # UTF-16LE: 4100 4300 4300 4500 4900 5300
-      # UTF-32BE: 00000041 00000043 00000043 00000045 00000049 00000053
-      # UTF-32LE: 41000000 43000000 43000000 45000000 49000000 53000000
-      #
-      # $unisec hexdump "ACCEIS" --enc utf16le
-      # 4100 4300 4300 4500 4900 5300
-      # ```
-      class Hexdump < Dry::CLI::Command
-        desc 'Hexdump in all Unicode encodings'
-
-        argument :input, required: true,
-                         desc: 'String input. Read from STDIN if equal to -.'
-
-        option :enc, default: nil, values: %w[utf8 utf16be utf16le utf32be utf32le],
-                     desc: 'Output only in the specified encoding.'
-
-        # Hexdump of all Unicode encodings.
-        # @param input [String] Input string to encode
-        def call(input: nil, **options)
-          input = $stdin.read.chomp if input == '-'
-          if options[:enc].nil?
-            puts Unisec::Hexdump.new(input).display
-          else
-            # using send() is safe here thanks to the value whitelist
-            puts Unisec::Hexdump.send(options[:enc], input)
-          end
-        end
-      end
-    end
-  end
-end