unisec 0.0.4 → 0.0.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 207fef6efc641ecf3ba11879d368cd2c6ac54f4d7001d948428c32a67e992e05
-  data.tar.gz: bec8d1577d59b146747a1346794df62ea7928feb47ca3c64e669636f91cdb9fa
+  metadata.gz: 0b6f74de3dc3d0f9aebac59ff68bc5731b7185e9e73e86e87477c23408900452
+  data.tar.gz: 910be7b95b71022f352cc6d612c7752fe2ea13a0e6e3dc89aca4566cb1879569
 SHA512:
-  metadata.gz: cb406f1c0b27575d84b497d5cec9a994f05a33f816630ebacd5013594997394c5b5473575d1a241193bb1e586bd3a7510c80a7597d9995f35cbb0f5b09882987
-  data.tar.gz: 994e93feae65577b462e85ac3450dbb4d8a7f6160d00f4a19fe21bae518de85846a2e4cb71668b7fee0c5afb2ea39932831d2e333e802ab048b6dbd5bd653cc1
+  metadata.gz: 47b730a884a30979be5968d90a30bc214ec93725383f20c48a02ec1090ce64e6043f95427c7ed79ebc31b3b4e1d3b66e01c7b0d63f936793f6c8eb008ce5f9fe
+  data.tar.gz: be9ca5cc40baaf9cd56141a3a8e41f5709c6071d5e7797ebd64a1daf231671e6835c168bce53f540e72ead4f68fc93bfd2d211764ba474e1cd8a4ca1bf5e7a65

data/lib/unisec/bidi.rb

@@ -129,6 +129,7 @@ module Unisec
       #
       # The light version displays only the spoof payload for easy piping with other commands.
       # @param light [Boolean] `true` = light display (displays only the spoof payload for easy piping with other commands), `false` (default) = full display.
+      # @return [String] CLI-ready output
       # @example
       #   puts Unisec::Bidi::Spoof.new('noraj').display
       #   # Target string: noraj

data/lib/unisec/cli/cli.rb

@@ -3,6 +3,7 @@
 require 'unisec/cli/bidi'
 require 'unisec/cli/confusables'
 require 'unisec/cli/hexdump'
+require 'unisec/cli/normalization'
 require 'unisec/cli/properties'
 require 'unisec/cli/rugrep'
 require 'unisec/cli/size'
@@ -23,6 +24,7 @@ module Unisec
       register 'confusables randomize', Confusables::Randomize
       register 'grep', Grep
       register 'hexdump', Hexdump
+      register 'normalize', Normalize
       register 'properties char', Properties::Char
       register 'properties codepoints', Properties::Codepoints
       register 'properties list', Properties::List

data/lib/unisec/cli/hexdump.rb

@@ -17,6 +17,9 @@ module Unisec
       # 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'
@@ -35,7 +38,7 @@ module Unisec
             puts Unisec::Hexdump.new(input).display
           else
             # using send() is safe here thanks to the value whitelist
-            puts puts Unisec::Hexdump.send(options[:enc], input)
+            puts Unisec::Hexdump.send(options[:enc], input)
           end
         end
       end

data/lib/unisec/cli/normalization.rb

@@ -0,0 +1,55 @@
+# frozen_string_literal: true
+
+require 'dry/cli'
+require 'unisec'
+require 'unisec/utils'
+
+module Unisec
+  module CLI
+    module Commands
+      # CLI sub-commands `unisec normalize xxx` for the class {Unisec::Normalization} from the lib.
+      #
+      # Command `unisec normalize "example"`
+      #
+      # Example:
+      #
+      # ```plaintext
+      # ➜ unisec normalize ẛ̣
+      # Original: ẛ̣
+      #   U+1E9B U+0323
+      # NFC: ẛ̣
+      #   U+1E9B U+0323
+      # NFKC: ṩ
+      #   U+1E69
+      # NFD: ẛ̣
+      #   U+017F U+0323 U+0307
+      # NFKD: ṩ
+      #   U+0073 U+0323 U+0307
+      #
+      # ➜ unisec normalize ẛ̣  --form nfkd
+      # ṩ
+      # ```
+      class Normalize < Dry::CLI::Command
+        desc 'Normalize in all forms'
+
+        argument :input, required: true,
+                         desc: 'String input. Read from STDIN if equal to -.'
+
+        option :form, default: nil, values: %w[nfc nfkc nfd nfkd],
+                      desc: 'Output only in the specified normalization form.'
+
+        # Normalize in all forms
+        # @param input [String] Input string to normalize
+        def call(input: nil, **options)
+          input = $stdin.read.chomp if input == '-'
+          if options[:form].nil?
+            puts Unisec::Normalization.new(input).display
+          else
+            # using send() is safe here thanks to the value whitelist
+            puts Unisec::Normalization.send(options[:form], input)
+          end
+        end
+      end
+    end
+  end
+end

data/lib/unisec/hexdump.rb

@@ -86,6 +86,7 @@ module Unisec
     end
 
     # Display a CLI-friendly output summurizing the hexdump in all Unicode encodings
+    # @return [String] CLI-ready output
     # @example
     #   puts Unisec::Hexdump.new('K').display # =>
     #   # UTF-8: e2 84 aa

data/lib/unisec/normalization.rb

@@ -0,0 +1,94 @@
+# frozen_string_literal: true
+
+require 'ctf_party'
+
+module Unisec
+  # Normalization Forms
+  class Normalization
+    # Original input
+    # @return [String] untouched input
+    attr_reader :original
+
+    # Normalization Form C (NFC) - Canonical Decomposition, followed by Canonical Composition
+    # @return [String] input normalized with NFC
+    attr_reader :nfc
+
+    # Normalization Form KC (NFKC) - Compatibility Decomposition, followed by Canonical Composition
+    # @return [String] input normalized with NFKC
+    attr_reader :nfkc
+
+    # Normalization Form D (NFD) - Canonical Decomposition
+    # @return [String] input normalized with NFD
+    attr_reader :nfd
+
+    # Normalization Form KD (NFKD) - Compatibility Decomposition
+    # @return [String] input normalized with NFKD
+    attr_reader :nfkd
+
+    # Generate all normilzation forms for a given input
+    # @param str [String] the target string
+    # @return [nil]
+    def initialize(str)
+      @original = str
+      @nfc = Normalization.nfc(str)
+      @nfkc = Normalization.nfkc(str)
+      @nfd = Normalization.nfd(str)
+      @nfkd = Normalization.nfkd(str)
+    end
+
+    # Normalization Form C (NFC) - Canonical Decomposition, followed by Canonical Composition
+    # @param str [String] the target string
+    # @return [String] input normalized with NFC
+    def self.nfc(str)
+      str.unicode_normalize(:nfc)
+    end
+
+    # Normalization Form KC (NFKC) - Compatibility Decomposition, followed by Canonical Composition
+    # @param str [String] the target string
+    # @return [String] input normalized with NFKC
+    def self.nfkc(str)
+      str.unicode_normalize(:nfkc)
+    end
+
+    # Normalization Form D (NFD) - Canonical Decomposition
+    # @param str [String] the target string
+    # @return [String] input normalized with NFD
+    def self.nfd(str)
+      str.unicode_normalize(:nfd)
+    end
+
+    # Normalization Form KD (NFKD) - Compatibility Decomposition
+    # @param str [String] the target string
+    # @return [String] input normalized with NFKD
+    def self.nfkd(str)
+      str.unicode_normalize(:nfkd)
+    end
+
+    # Display a CLI-friendly output summurizing all normalization forms
+    # @return [String] CLI-ready output
+    # @example
+    #   puts Unisec::Normalization.new("\u{1E9B 0323}").display
+    #   # =>
+    #   # Original: ẛ̣
+    #   #   U+1E9B U+0323
+    #   # NFC: ẛ̣
+    #   #   U+1E9B U+0323
+    #   # NFKC: ṩ
+    #   #   U+1E69
+    #   # NFD: ẛ̣
+    #   #   U+017F U+0323 U+0307
+    #   # NFKD: ṩ
+    #   #   U+0073 U+0323 U+0307
+    def display
+      colorize = lambda { |form_title, form_attr|
+        "#{Paint[form_title.to_s, :underline,
+                 :bold]}: #{form_attr}\n  #{Paint[Unisec::Properties.chars2codepoints(form_attr), :red]}\n"
+      }
+      colorize.call('Original', @original) +
+        colorize.call('NFC', @nfc) +
+        colorize.call('NFKC', @nfkc) +
+        colorize.call('NFD', @nfd) +
+        colorize.call('NFKD', @nfkd)
+    end
+  end
+end

data/lib/unisec/surrogates.rb

@@ -102,6 +102,7 @@ module Unisec
     # Display a CLI-friendly output summurizing everithing about the surrogates:
     # the corresponding character, code point, high and low surrogates
     # (each displayed as hexadecimal, decimal and binary).
+    # @return [String] CLI-ready output
     # @example
     #   surr = Unisec::Surrogates.new(128169)
     #   puts surr.display # =>

data/lib/unisec/version.rb

@@ -2,5 +2,5 @@
 
 module Unisec
   # Version of unisec library and app
-  VERSION = '0.0.4'
+  VERSION = '0.0.5'
 end

data/lib/unisec/versions.rb

@@ -72,19 +72,19 @@ module Unisec
     #   # …
     def self.display # rubocop:disable Metrics/AbcSize
       data = versions
-      display = ->(node) { puts Paint[data[node][:label], :red, :bold].ljust(44) + " #{data[node][:version]}" }
-      puts Paint['Unicode:', :underline]
-      display.call(:ruby_unicode)
-      display.call(:twittercldr_unicode)
-      display.call(:unicodeconfusable_unicode)
-      display.call(:twittercldr_icu)
-      display.call(:twittercldr_cldr)
-      display.call(:ruby_unicode_emoji)
-      display.call(:ucd_derivedname)
-      puts Paint["\nGems:", :underline]
-      display.call(:unisec)
-      display.call(:twittercldr)
-      display.call(:unicodeconfusable)
+      colorize = ->(node) { Paint[data[node][:label], :red, :bold].ljust(44) + " #{data[node][:version]}\n" }
+      Paint["Unicode:\n", :underline] +
+        colorize.call(:ruby_unicode) +
+        colorize.call(:twittercldr_unicode) +
+        colorize.call(:unicodeconfusable_unicode) +
+        colorize.call(:twittercldr_icu) +
+        colorize.call(:twittercldr_cldr) +
+        colorize.call(:ruby_unicode_emoji) +
+        colorize.call(:ucd_derivedname) +
+        Paint["\nGems:\n", :underline] +
+        colorize.call(:unisec) +
+        colorize.call(:twittercldr) +
+        colorize.call(:unicodeconfusable)
     end
   end
 end

data/lib/unisec.rb

@@ -5,6 +5,7 @@ require 'unisec/version'
 require 'unisec/bidi'
 require 'unisec/confusables'
 require 'unisec/hexdump'
+require 'unisec/normalization'
 require 'unisec/properties'
 require 'unisec/rugrep'
 require 'unisec/size'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: unisec
 version: !ruby/object:Gem::Version
-  version: 0.0.4
+  version: 0.0.5
 platform: ruby
 authors:
 - Alexandre ZANNI
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-01-23 00:00:00.000000000 Z
+date: 2024-02-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ctf-party
@@ -88,7 +88,7 @@ dependencies:
         version: '1.9'
 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'
+  surrogates, version, ICU, CLDR, UCD, BiDi, normalization'
 email: alexandre.zanni@europe.com
 executables:
 - unisec
@@ -104,6 +104,7 @@ files:
 - lib/unisec/cli/cli.rb
 - lib/unisec/cli/confusables.rb
 - lib/unisec/cli/hexdump.rb
+- lib/unisec/cli/normalization.rb
 - lib/unisec/cli/properties.rb
 - lib/unisec/cli/rugrep.rb
 - lib/unisec/cli/size.rb
@@ -111,6 +112,7 @@ files:
 - lib/unisec/cli/versions.rb
 - lib/unisec/confusables.rb
 - lib/unisec/hexdump.rb
+- lib/unisec/normalization.rb
 - lib/unisec/properties.rb
 - lib/unisec/rugrep.rb
 - lib/unisec/size.rb