unicode_utils 1.2.2 → 1.3.0

data/lib/unicode_utils/name_aliases.rb

@@ -0,0 +1,29 @@
+# -*- encoding: utf-8 -*-
+
+require "unicode_utils/name_alias"
+require "unicode_utils/read_cdata"
+
+module UnicodeUtils
+
+  NAME_ALIASES_MAP = Impl.read_name_aliases("name_aliases") # :nodoc:
+  NAME_ALIASES_MAP.default = [].freeze
+
+  # Get an Enumerable of formal name aliases of the given character. Returns an
+  # empty Enumerable if the character doesn't have an alias.
+  #
+  # The aliases are instances of UnicodeUtils::NameAlias, the order of the
+  # aliases in the returned Enumerable is preserved from NameAliases.txt in the
+  # Unicode Character Database.
+  #
+  # Example:
+  #
+  #   require "unicode_utils/name_aliases"
+  #   UnicodeUtils.name_aliases("\n").map(&:name) # => ["LINE FEED", "NEW LINE", "END OF LINE", "LF", "NL", "EOL"]
+  #
+  # See also: UnicodeUtils.char_name
+  def name_aliases(char)
+    NAME_ALIASES_MAP[char.ord]
+  end
+  module_function :name_aliases
+
+end

data/lib/unicode_utils/nfc.rb

@@ -9,7 +9,7 @@ module UnicodeUtils
   module Impl # :nodoc:all
     
     COMPOSITION_EXCLUSION_SET =
-      Impl.read_codepoint_set("composition_exclusion_set")
+      Impl.read_code_point_set("composition_exclusion_set")
 
     CANONICAL_COMPOSITION_MAP = Hash.new.tap do |m|
       CANONICAL_DECOMPOSITION_MAP.each_pair { |comp, decomp|
@@ -124,8 +124,8 @@ module UnicodeUtils
   # Get +str+ in Normalization Form C.
   #
   # The Unicode standard has multiple representations for some
-  # characters. One representation as a single codepoint and other
-  # representation(s) as a combination of multiple codepoints. This
+  # characters. One representation as a single code point and other
+  # representation(s) as a combination of multiple code points. This
   # function "composes" these characters into the former
   # representation.
   #

data/lib/unicode_utils/read_cdata.rb

@@ -16,11 +16,19 @@ module UnicodeUtils
       5 => :Narrow
     }.freeze
 
+    NAME_ALIAS_TYPE_TO_SYMBOL_MAP = {
+      1 => :correction,
+      2 => :control,
+      3 => :alternate,
+      4 => :figment,
+      5 => :abbreviation
+    }.freeze
+
     def self.open_cdata_file(filename, &block)
       File.open(File.join(CDATA_DIR, filename), "r:US-ASCII:-", &block)
     end
 
-    def self.read_codepoint_set(filename)
+    def self.read_code_point_set(filename)
       Hash.new.tap { |set|
         open_cdata_file(filename) do |input|
           buffer = "x" * 6
@@ -32,7 +40,7 @@ module UnicodeUtils
       }
     end
 
-    def self.read_codepoint_map(filename)
+    def self.read_code_point_map(filename)
       Hash.new.tap { |map|
         open_cdata_file(filename) do |input|
           buffer = "x" * 6
@@ -104,7 +112,7 @@ module UnicodeUtils
       }
     end
 
-    # Read a map whose keys are codepoints (6 hexgdigits, converted to
+    # Read a map whose keys are code points (6 hexgdigits, converted to
     # integer) and whose values are single hexdigits (converted to
     # integer).
     def self.read_hexdigit_map(filename)
@@ -122,7 +130,7 @@ module UnicodeUtils
     end
 
     # Returns a list (array) of pairs (two element Arrays) of Range
-    # (codepoints) and associated integer value.
+    # (code points) and associated integer value.
     def self.read_range_to_hexdigit_list(filename)
       Array.new.tap { |list|
         open_cdata_file(filename) do |input|
@@ -208,6 +216,30 @@ module UnicodeUtils
       }
     end
 
+    def self.read_name_aliases(filename)
+      Hash.new.tap { |map|
+        open_cdata_file(filename) do |input|
+          cp_buffer = "x" * 6
+          cp_buffer.force_encoding(Encoding::US_ASCII)
+          ac_buffer = "x" * 1
+          ac_buffer.force_encoding(Encoding::US_ASCII)
+          at_buffer = "x" * 1
+          at_buffer.force_encoding(Encoding::US_ASCII)
+          al_buffer = "x" * 2
+          al_buffer.force_encoding(Encoding::US_ASCII)
+          while input.read(6, cp_buffer)
+            aliases = Array.new(input.read(1, ac_buffer).to_i(16))
+            0.upto(aliases.length - 1) { |i|
+              type = NAME_ALIAS_TYPE_TO_SYMBOL_MAP[input.read(1, at_buffer).to_i(16)]
+              name = input.read(input.read(2, al_buffer).to_i(16))
+              aliases[i] = NameAlias.new(name.freeze, type)
+            }
+            map[cp_buffer.to_i(16)] = aliases.freeze
+          end
+        end
+      }
+    end
+
   end
 
 end

data/lib/unicode_utils/sid.rb

@@ -0,0 +1,63 @@
+# -*- encoding: utf-8 -*-
+
+require "unicode_utils/name_aliases"
+require "unicode_utils/code_point_type"
+
+module UnicodeUtils
+
+  CP_PREFERRED_ALIAS_STRING_MAP = Hash.new.tap do |map|
+    NAME_ALIASES_MAP.each { |cp, aliases|
+      al =
+        (aliases.find { |al| al.type == :correction } ||
+         aliases.find { |al| al.type == :control } ||
+         aliases.find { |al| al.type == :figment } ||
+         aliases.find { |al| al.type == :alternate })
+      map[cp] = al.name if al
+    }
+  end #:nodoc:
+
+  # Returns a unique string identifier for every code point. Returns
+  # nil if +code_point+ is not in the Unicode codespace. +code_point+
+  # must be an Integer.
+  #
+  # The returned string identifier is either the non-empty Name
+  # property value of +code_point+, a non-empty Name_Alias string
+  # property value of +code_point+, or the code point label as
+  # described by section "Code Point Labels" in chapter 4.8 "Name" of
+  # the Unicode standard.
+  #
+  # If the returned identifier starts with "<", it is a code point
+  # label and it ends with ">". Otherwise it is the normative name or
+  # a formal alias string.
+  #
+  # The exact name/alias/label selection algorithm may change even in
+  # minor UnicodeUtils releases, but overall behaviour will stay the
+  # same in spirit.
+  #
+  # The selection process in this version of UnicodeUtils is:
+  # 1. Use an alias of type :correction, :control, :figment or
+  #    :alternate (with listed precendence) if available
+  # 2. Use the Unicode Name property value if it is not empty
+  # 3. Construct a code point label in angle brackets.
+  #
+  # Examples:
+  #
+  #     require "unicode_utils/sid"
+  #
+  #     U.sid 0xa     # => "LINE FEED"
+  #     U.sid 0x0     # => "NULL"
+  #     U.sid 0xfeff  # => "BYTE ORDER MARK"
+  #     U.sid 0xe000  # => "<private-use-E000>"
+  #     U.sid 0x61    # => "LATIN SMALL LETTER A"
+  #     U.sid -1      # => nil
+  def sid(code_point)
+    s = CP_PREFERRED_ALIAS_STRING_MAP[code_point] and return s
+    cn = UnicodeUtils.char_name(code_point)
+    return cn if cn && cn !~ /\A(\<|\z)/
+    ct = UnicodeUtils.code_point_type(code_point) or return nil
+    ts = ct.to_s.downcase.gsub('_', '-')
+    "<#{ts}-#{code_point.to_s(16).upcase.rjust(4, '0')}>"
+  end
+  module_function :sid
+
+end

data/lib/unicode_utils/simple_casefold.rb

@@ -4,9 +4,9 @@ require "unicode_utils/read_cdata"
 
 module UnicodeUtils
 
-  CASEFOLD_C_MAP = Impl.read_codepoint_map("casefold_c_map") # :nodoc:
+  CASEFOLD_C_MAP = Impl.read_code_point_map("casefold_c_map") # :nodoc:
 
-  CASEFOLD_S_MAP = Impl.read_codepoint_map("casefold_s_map") # :nodoc:
+  CASEFOLD_S_MAP = Impl.read_code_point_map("casefold_s_map") # :nodoc:
 
   # Perform simple case folding. Contrary to full case folding, this
   # uses only one to one mappings, so that the length of the returned

data/lib/unicode_utils/simple_downcase.rb

@@ -4,9 +4,9 @@ require "unicode_utils/read_cdata"
 
 module UnicodeUtils
 
-  SIMPLE_DOWNCASE_MAP = Impl.read_codepoint_map("simple_lc_map") # :nodoc:
+  SIMPLE_DOWNCASE_MAP = Impl.read_code_point_map("simple_lc_map") # :nodoc:
 
-  # Map each codepoint in +str+ that has a single codepoint
+  # Map each code point in +str+ that has a single code point
   # lowercase-mapping to that lowercase mapping. The returned string
   # has the same length as the original string.
   #

data/lib/unicode_utils/simple_upcase.rb

@@ -4,9 +4,9 @@ require "unicode_utils/read_cdata"
 
 module UnicodeUtils
 
-  SIMPLE_UPCASE_MAP = Impl.read_codepoint_map("simple_uc_map") # :nodoc:
+  SIMPLE_UPCASE_MAP = Impl.read_code_point_map("simple_uc_map") # :nodoc:
 
-  # Map each codepoint in +str+ that has a single codepoint
+  # Map each code point in +str+ that has a single code point
   # uppercase-mapping to that uppercase mapping. The returned string
   # has the same length as the original string.
   #

data/lib/unicode_utils/soft_dotted_char_q.rb

@@ -4,7 +4,7 @@ require "unicode_utils/read_cdata"
 
 module UnicodeUtils
 
-  SOFT_DOTTED_SET = Impl.read_codepoint_set("soft_dotted_set") # :nodoc:
+  SOFT_DOTTED_SET = Impl.read_code_point_set("soft_dotted_set") # :nodoc:
 
   # Returns true if the given character has the Unicode property
   # Soft_Dotted.

data/lib/unicode_utils/titlecase.rb

@@ -8,7 +8,7 @@ require "unicode_utils/downcase"
 
 module UnicodeUtils
 
-  SIMPLE_TITLECASE_MAP = Impl.read_codepoint_map("simple_tc_map") # :nodoc:
+  SIMPLE_TITLECASE_MAP = Impl.read_code_point_map("simple_tc_map") # :nodoc:
   SPECIAL_TITLECASE_MAP = Impl.read_multivalued_map("special_tc_map") # :nodoc:
 
   # Convert the first cased character after each word boundary to

data/lib/unicode_utils/titlecase_char_q.rb

@@ -4,7 +4,7 @@ require "unicode_utils/read_cdata"
 
 module UnicodeUtils
 
-  TITLECASE_LETTER_SET = Impl.read_codepoint_set("cat_set_titlecase") # :nodoc:
+  TITLECASE_LETTER_SET = Impl.read_code_point_set("cat_set_titlecase") # :nodoc:
 
   # True if the given character has the General_Category
   # Titlecase_Letter (Lt).

data/lib/unicode_utils/uppercase_char_q.rb

@@ -4,7 +4,7 @@ require "unicode_utils/read_cdata"
 
 module UnicodeUtils
 
-  PROP_UPPERCASE_SET = Impl.read_codepoint_set("prop_set_uppercase") # :nodoc:
+  PROP_UPPERCASE_SET = Impl.read_code_point_set("prop_set_uppercase") # :nodoc:
 
   # True if the given character has the Unicode property Uppercase.
   def uppercase_char?(char)

data/lib/unicode_utils/version.rb

@@ -4,13 +4,20 @@ module UnicodeUtils
 
   # Corresponds to the unicode_utils gem version.
   #
+  # Conforms to Semantic Versioning as documented at semver.org.
+  #
+  # Summary:
   # MAJOR.MINOR.PATCHLEVEL
   # - A backwards incompatible change causes a change in MAJOR
   # - New features or non-bugfix improvals cause a change in MINOR
   # - Bugfixes increase only PATCHLEVEL.
+  # - Pre-release versions append more info after a dash.
+  VERSION = "1.3.0"
+
+  # The version of Unicode implemented by this version of UnicodeUtils.
   #
-  # A release always has an even PATCHLEVEL. PATCHLEVEL is uneven
-  # during development.
-  VERSION = "1.2.2"
+  #   require "unicode_utils/version"
+  #   puts "Unicode #{UnicodeUtils::UNICODE_VERSION}"
+  UNICODE_VERSION = "6.1.0"
 
 end

data/test/test_unicode_utils.rb

@@ -8,6 +8,10 @@ require "unicode_utils"
 # Fast tests for allmost all UnicodeUtils functions.
 class TestUnicodeUtils < Test::Unit::TestCase
 
+  def test_unicode_version
+    assert_match /\A\d+\.\d+\.\d+\z/, UnicodeUtils::UNICODE_VERSION
+  end
+
   def test_name
     assert_equal "LATIN SMALL LETTER F", UnicodeUtils.char_name("f")
     assert_equal Encoding::US_ASCII, UnicodeUtils.char_name("f").encoding
@@ -421,19 +425,119 @@ class TestUnicodeUtils < Test::Unit::TestCase
     io = StringIO.new
     UnicodeUtils.debug("", io: io)
     assert_equal <<-'EOF', io.string
- Char | Ordinal | Name | General Category | UTF-8
-------+---------+------+------------------+-------
+ Char | Ordinal | Sid | General Category | UTF-8
+------+---------+-----+------------------+-------
     EOF
     io = StringIO.new
     UnicodeUtils.debug("一 \u{100000}\n", io: io)
     assert_equal <<-'EOF', io.string
- Char | Ordinal | Name                       | General Category | UTF-8
+ Char | Ordinal | Sid                        | General Category | UTF-8
 ------+---------+----------------------------+------------------+-------------
  "一" |    4E00 | CJK UNIFIED IDEOGRAPH-4E00 | Other_Letter     | E4 B8 80
  " "  |      20 | SPACE                      | Space_Separator  | 20
- N/A  |  100000 | N/A                        | Private_Use      | F4 80 80 80
- "\n" |       A | <control>                  | Control          | 0A
+ N/A  |  100000 | <private-use-100000>       | Private_Use      | F4 80 80 80
+ "\n" |       A | LINE FEED                  | Control          | 0A
     EOF
   end
 
+  def test_code_point_type
+    assert_equal :Graphic, UnicodeUtils.code_point_type("A")
+    assert_equal :Graphic, UnicodeUtils.code_point_type("a")
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0x1cb)
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0x2b5)
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0x10923)
+
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0x5a0)
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0x93f)
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0x20dd)
+
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0xa901)
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0x10144)
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0x10917)
+
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0x5f)
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0x2011)
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0x2329)
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0xfe38)
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0x201c)
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0x201d)
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0x2e10)
+
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0xff0b)
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0xa3)
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0x2c2)
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0x60f)
+
+    assert_equal :Graphic, UnicodeUtils.code_point_type(0x2001)
+    assert_equal :Format, UnicodeUtils.code_point_type(0x2028)
+    assert_equal :Format, UnicodeUtils.code_point_type(0x2029)
+
+    assert_equal :Control, UnicodeUtils.code_point_type(0x0)
+    assert_equal :Format, UnicodeUtils.code_point_type(0x70f)
+    assert_equal :Surrogate, UnicodeUtils.code_point_type(0xdb82)
+    assert_equal :Private_Use, UnicodeUtils.code_point_type(0xf1020)
+    assert_equal :Private_Use, UnicodeUtils.code_point_type(0x10fffd)
+    assert_equal :Noncharacter, UnicodeUtils.code_point_type(0x10ffff)
+    assert_equal :Noncharacter, UnicodeUtils.code_point_type(0xfffe)
+    assert_equal :Noncharacter, UnicodeUtils.code_point_type(0xffff)
+    assert_equal :Noncharacter, UnicodeUtils.code_point_type(0xbfffe)
+    assert_equal :Noncharacter, UnicodeUtils.code_point_type(0xbffff)
+    assert_equal :Reserved, UnicodeUtils.code_point_type(0x380)
+    assert_equal :Reserved, UnicodeUtils.code_point_type(0xeeb)
+    assert_equal :Reserved, UnicodeUtils.code_point_type(0xfff)
+    assert_equal :Reserved, UnicodeUtils.code_point_type(0x7fffd)
+    assert_equal :Reserved, UnicodeUtils.code_point_type(0xeffef)
+    ### above is at least one assertion for every general category ###
+
+    assert_equal nil, UnicodeUtils.code_point_type(-1)
+    assert_equal nil, UnicodeUtils.code_point_type(0x110000)
+  end
+
+  def test_name_aliases
+    assert_equal [UnicodeUtils::NameAlias.new("NULL", :control),
+                  UnicodeUtils::NameAlias.new("NUL", :abbreviation)],
+                 UnicodeUtils.name_aliases(0x0)
+    assert_equal [UnicodeUtils::NameAlias.new("LATIN CAPITAL LETTER GHA", :correction)],
+                 UnicodeUtils.name_aliases(0x1a2)
+    assert_equal [UnicodeUtils::NameAlias.new("BYTE ORDER MARK", :alternate),
+                  UnicodeUtils::NameAlias.new("BOM", :abbreviation),
+                  UnicodeUtils::NameAlias.new("ZWNBSP", :abbreviation)],
+                 UnicodeUtils.name_aliases(0xfeff)
+    assert_equal [UnicodeUtils::NameAlias.new("PADDING CHARACTER", :figment),
+                  UnicodeUtils::NameAlias.new("PAD", :abbreviation)],
+                 UnicodeUtils.name_aliases(0x80)
+    assert_equal [UnicodeUtils::NameAlias.new("VS256", :abbreviation)],
+                 UnicodeUtils.name_aliases(0xe01ef)
+    assert_equal [UnicodeUtils::NameAlias.new("LINE FEED", :control),
+                  UnicodeUtils::NameAlias.new("NEW LINE", :control),
+                  UnicodeUtils::NameAlias.new("END OF LINE", :control),
+                  UnicodeUtils::NameAlias.new("LF", :abbreviation),
+                  UnicodeUtils::NameAlias.new("NL", :abbreviation),
+                  UnicodeUtils::NameAlias.new("EOL", :abbreviation)],
+                 UnicodeUtils.name_aliases(0xa)
+    assert_equal [UnicodeUtils::NameAlias.new("CHARACTER TABULATION", :control),
+                  UnicodeUtils::NameAlias.new("HORIZONTAL TABULATION", :control),
+                  UnicodeUtils::NameAlias.new("HT", :abbreviation),
+                  UnicodeUtils::NameAlias.new("TAB", :abbreviation)],
+                 UnicodeUtils.name_aliases("\t")
+    assert_equal [],
+                 UnicodeUtils.name_aliases("a")
+  end
+
+  def test_sid
+    assert_equal nil, UnicodeUtils.sid(-1)
+    assert_equal "NULL", UnicodeUtils.sid(0x0)
+    assert_equal "LATIN CAPITAL LETTER GHA", UnicodeUtils.sid(0x1a2)
+    assert_equal "LINE FEED", UnicodeUtils.sid(0xa)
+    assert_equal "PADDING CHARACTER", UnicodeUtils.sid(0x80)
+    assert_equal "BYTE ORDER MARK", UnicodeUtils.sid(0xfeff)
+    assert_equal "SPACE", UnicodeUtils.sid(0x20)
+    assert_equal "<reserved-0380>", UnicodeUtils.sid(0x380)
+    assert_equal "<surrogate-D800>", UnicodeUtils.sid(0xd800)
+    assert_equal "<private-use-F0000>", UnicodeUtils.sid(0xf0000)
+    assert_equal "<private-use-10FFFD>", UnicodeUtils.sid(0x10fffd)
+    assert_equal "<noncharacter-10FFFF>", UnicodeUtils.sid(UnicodeUtils::Codepoint::RANGE.end)
+    assert_equal nil, UnicodeUtils.sid(UnicodeUtils::Codepoint::RANGE.end + 1)
+  end
+
 end

metadata

@@ -1,34 +1,25 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: unicode_utils
-version: !ruby/object:Gem::Version 
-  prerelease: false
-  segments: 
-  - 1
-  - 2
-  - 2
-  version: 1.2.2
+version: !ruby/object:Gem::Version
+  version: 1.3.0
+  prerelease: 
 platform: ruby
-authors: 
+authors:
 - Stefan Lang
 autorequire: 
 bindir: bin
 cert_chain: []
-
-date: 2011-11-27 00:00:00 +01:00
-default_executable: 
+date: 2012-03-07 00:00:00.000000000 Z
 dependencies: []
-
 description: 
 email: langstefan@gmx.at
 executables: []
-
 extensions: []
-
-extra_rdoc_files: 
+extra_rdoc_files:
 - README.txt
 - INSTALL.txt
 - CHANGES.txt
-files: 
+files:
 - lib/unicode_utils.rb
 - lib/unicode_utils/conditional_casing.rb
 - lib/unicode_utils/version.rb
@@ -43,8 +34,12 @@ files:
 - lib/unicode_utils/general_category.rb
 - lib/unicode_utils/uppercase_char_q.rb
 - lib/unicode_utils/upcase.rb
+- lib/unicode_utils/sid.rb
 - lib/unicode_utils/u.rb
+- lib/unicode_utils/code_point_type.rb
 - lib/unicode_utils/hangul_syllable_decomposition.rb
+- lib/unicode_utils/name_aliases.rb
+- lib/unicode_utils/name_alias.rb
 - lib/unicode_utils/soft_dotted_char_q.rb
 - lib/unicode_utils/lowercase_char_q.rb
 - lib/unicode_utils/read_cdata.rb
@@ -87,6 +82,7 @@ files:
 - cdata/general_category_aliases
 - cdata/canonical_decomposition_map
 - cdata/cat_set_titlecase
+- cdata/name_aliases
 - cdata/casefold_f_map
 - cdata/special_uc_map
 - cdata/special_tc_map
@@ -107,40 +103,31 @@ files:
 - INSTALL.txt
 - LICENSE.txt
 - CHANGES.txt
-has_rdoc: true
 homepage: http://github.com/lang/unicode_utils
 licenses: []
-
 post_install_message: 
-rdoc_options: 
+rdoc_options:
 - --main=README.txt
 - --charset=UTF-8
-require_paths: 
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
+required_ruby_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      segments: 
-      - 1
-      - 9
-      - 1
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
       version: 1.9.1
-required_rubygems_version: !ruby/object:Gem::Requirement 
+required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      segments: 
-      - 0
-      version: "0"
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
 requirements: []
-
 rubyforge_project: unicode-utils
-rubygems_version: 1.3.7
+rubygems_version: 1.8.11
 signing_key: 
 specification_version: 3
 summary: additional Unicode aware functions for Ruby 1.9
-test_files: 
+test_files:
 - test/test_unicode_utils.rb