unisec 0.0.7 → 0.0.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9081ac95de968e70cd91438a73b185efee13e33ccf16c40a2791da5963d3d67c
-  data.tar.gz: 99a651d4efc5f6b36ae088ec254e0dc950b5d84db9105dc851f29d51609615f8
+  metadata.gz: fe68d59956b20311ad5d9f5f64c10a6b0648d1c7c146b9fbacf3f25348385207
+  data.tar.gz: 8f62db4e8a2327e0ac36e1be53fb5c168fb856fd81e9cafec0af1297a451bed8
 SHA512:
-  metadata.gz: ab342720e300cd25e167385f70402e00ef240ed6c422f7aeea666774b4e477f423164fe3de49146bc0f4a3f2565f86effb1465f112085568c65b1625b9d911e5
-  data.tar.gz: bc105f1430c812711727600365db10871e1bd69ad274c7ccc0a2b5e1362676304ce27e5e85c6a988986fe9a82bc6189bf3c14e6ecb577f327dc41bd6923f241d
+  metadata.gz: 7eb59fcce432494896adc586f168835578da1ab54f6f64080d4ecc86d91bebd39d569f38e72a6c9c79ea23e303a34315c8aebaf9e2fa2b340d25f234731e82ab
+  data.tar.gz: 33711c517a93ea3e28b25cde223d94f1cc2cf2edc0db39a3af41d5c6268d5bac51bef4d534306a24df21ea283c325fe052e0723780dcdedd294930e6f1d8eeee

data/lib/unisec/blocks.rb

@@ -114,7 +114,7 @@ module Unisec
           if block_arg.size == 1 # is a char (1 code unit, not one grapheme)
             found = true if blk_range.include?(Utils::String.convert_to_integer(block_arg))
           elsif block_arg.start_with?('U+') # string code point
-            found = true if blk_range.include?(Utils::String.stdhexcp2deccp(block_arg))
+            found = true if blk_range.include?(Utils::String.convert(block_arg, :integer))
           elsif blk_name.downcase == block_arg.downcase # block name
             found = true
           end

data/lib/unisec/cli/cli.rb

@@ -27,6 +27,8 @@ module Unisec
       register 'blocks search', Blocks::Search
       register 'confusables list', Confusables::List
       register 'confusables randomize', Confusables::Randomize
+      register 'dump codepoints integer', Dump::Codepoints::Integer
+      register 'dump codepoints standard', Dump::Codepoints::Standard
       register 'dump dec', Dump::Dec
       register 'dump hex', Dump::Hex
       register 'grep', Grep

data/lib/unisec/cli/dump.rb

@@ -81,6 +81,52 @@ module Unisec
             end
           end
         end
+
+        module Codepoints
+          # CLI command `unisec dump codepoints standard`.
+          #
+          # Example:
+          #
+          # ```plaintext
+          # $ unisec dump codepoints standard "unicode"
+          # U+0075 U+006E U+0069 U+0063 U+006F U+0064 U+0065
+          # ```
+          class Standard < Dry::CLI::Command
+            desc 'Code point dump (standard format)'
+
+            argument :input, required: true,
+                             desc: 'String input. Read from STDIN if equal to -.'
+
+            # Code point dump (standard format).
+            # @param input [String] Input string to encode
+            def call(input: nil)
+              input = $stdin.read.chomp if input == '-'
+              puts Unisec::Utils::String.chars2codepoints(input)
+            end
+          end
+
+          # CLI command `unisec dump codepoints integer`.
+          #
+          # Example:
+          #
+          # ```plaintext
+          # $ unisec dump codepoints integer 'I 💕 Ruby 💎'
+          # 73 32 128149 32 82 117 98 121 32 128142
+          # ```
+          class Integer < Dry::CLI::Command
+            desc 'Code point dump (integer format)'
+
+            argument :input, required: true,
+                             desc: 'String input. Read from STDIN if equal to -.'
+
+            # Code point dump (integer format).
+            # @param input [String] Input string to encode
+            def call(input: nil)
+              input = $stdin.read.chomp if input == '-'
+              puts Unisec::Utils::String.chars2intcodepoints(input)
+            end
+          end
+        end
       end
     end
   end

data/lib/unisec/properties.rb

@@ -119,7 +119,7 @@ module Unisec
       data = Properties.char(chr)
       display = ->(key, value) { puts Paint[key, :red, :bold].ljust(30) + " #{value}" }
       display.call('Name:', data[:name])
-      display.call('Code Point:', data[:codepoint])
+      display.call('Code Point:', data[:codepoint] + " (#{Utils::String.convert(chr, :integer)})")
       puts
       display.call('Block:', data[:block])
       display.call('Category:', data[:category])

data/lib/unisec/utils.rb

@@ -55,27 +55,31 @@ module Unisec
     # 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
@@ -86,10 +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
@@ -101,11 +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
@@ -115,10 +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]+/
@@ -141,8 +180,9 @@ module Unisec
       # 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::Properties.char2codepoint('💎') # => "U+1F48E"
+      #   Unisec::Utils::String.char2codepoint('💎') # => "U+1F48E"
       def self.char2codepoint(chr)
         Integer.deccp2stdhexcp(chr.codepoints.first)
       end
@@ -151,8 +191,8 @@ module Unisec
       # @param chrs [String] Unicode code points (as characters / string)
       # @return [String] code points in Unicode format
       # @example
-      #   Unisec::Properties.chars2codepoints("ỳ́") # => "U+0079 U+0300 U+0301"
-      #   Unisec::Properties.chars2codepoints("🧑‍🌾") # => "U+1F9D1 U+200D U+1F33E"
+      #   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|
@@ -161,6 +201,15 @@ module Unisec
         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
@@ -170,22 +219,13 @@ module Unisec
       def self.to_range(range_str)
         ::Range.new(*range_str.split('..').map { |x| x.hex2dec.to_i })
       end
-
-      # Convert from standardized format hexadecimal code point to decimal code point
-      # @param std_hex_cp [String] Code point in standardized hexadecimal format
-      # @return [Integer] Code point in decimal format
-      # @example
-      #   Unisec::Utils::String.stdhexcp2deccp('U+2026') # => 8230
-      def self.stdhexcp2deccp(std_hex_cp)
-        hex = "0x#{std_hex_cp[2..]}" # replace U+ prefix with 0x
-        convert_to_integer(hex)
-      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)

data/lib/unisec/version.rb

@@ -2,5 +2,5 @@
 
 module Unisec
   # Version of unisec library and app
-  VERSION = '0.0.7'
+  VERSION = '0.0.8'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: unisec
 version: !ruby/object:Gem::Version
-  version: 0.0.7
+  version: 0.0.8
 platform: ruby
 authors:
 - Alexandre ZANNI