hebrew 0.0.2

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    ZGQ0NGU1ODllODliMzU4NmNhOTI4ZGJkMmU4ZjBlNjg2ZTY0NTE4YQ==
+  data.tar.gz: !binary |-
+    OWJiNjU1MTMyYTRmZjZmZWE5MDY1NWVmMWNlOTJkYTM1MTVkNjQ2Yg==
+!binary "U0hBNTEy":
+  metadata.gz: !binary |-
+    MzcxYjMzODk1MWZlM2VkMWE4OGZjYjczNzQ4YmIyY2IzMzc2NzI3MDBjNGI1
+    OWFhZDFhYzdiZWExMTczNzAwNjZhYWJkMDM5MGM0YWQ4YTYxZGVlYTliM2Rh
+    ZGY1ZTdmMjY5NjNjZDA3MTMyMzY4MzU5YTZhNDEzNzNhMjJjNWY=
+  data.tar.gz: !binary |-
+    OGYwODM0MTk0NmQ0YjQxMjEzMTYzMWQ4MzUyYTQ2YjY1YWEwOTMxMjQzZDNl
+    MWZmOWIxNjk3NzFhYTI1YjA4ZTc1NDhlMjM0MzQ0NzBjMTE4YjRlNjRjOTRm
+    ZTZhMDc0YjQ4NDYzYzhmMmE2NGNhYjQxOTk4NDgzMTQxYTgwOTE=

data/lib/hebrew.rb

@@ -0,0 +1,38 @@
+# Some useful Hebrew manipulation routines
+#
+# @author Asaf Bartov <asaf.bartov@gmail.com>
+#
+
+
+NIKKUD_CP1255 = ["\xc0".force_encoding('windows-1255'), "\xc1".force_encoding('windows-1255'), "\xc2".force_encoding('windows-1255'), "\xc3".force_encoding('windows-1255'), "\xc4".force_encoding('windows-1255'), "\xc5".force_encoding('windows-1255'), "\xc6".force_encoding('windows-1255'), "\xc7".force_encoding('windows-1255'), "\xc8".force_encoding('windows-1255'), "\xc9".force_encoding('windows-1255'), "\xcb".force_encoding('windows-1255'), "\xcc".force_encoding('windows-1255'), "\xd1".force_encoding('windows-1255'), "\xd2".force_encoding('windows-1255')] # wow, this is fugly.  Is there a neater way to specify CP1255 literal?
+NIKKUD_UTF8 = ["\u05b0", "\u05b1", "\u05b2", "\u05b3", "\u05b4", "\u05b5", "\u05b6", "\u05b7", "\u05b8", "\u05b9", "\u05bb", "\u05bc", "\u05c1", "\u05c2"]
+# TODO: Mac encoding
+
+# extend String class
+class String
+  # this will return the string, stripped of any Hebrew nikkud characters
+  def strip_nikkud
+    target = ''
+    self.each_char {|c|
+      unless is_nikkud(c)
+        target += c 
+      end
+    }
+    return target
+  end
+  # TODO: add strip_nikkud!
+  def is_nikkud(c)
+    self.class.is_nikkud_by_encoding(c, self.encoding) # delegate to class method based on instance encoding
+  end
+  def self.is_nikkud_by_encoding(c, encoding)
+    case encoding
+    when Encoding::UTF_8
+      # DBG: puts "utf8 - #{c} - #{c.codepoints.first}"
+      NIKKUD_UTF8.include?(c)
+    when Encoding::WINDOWS_1255 || Encoding::CP1255
+      # DBG: puts "cp1255 - #{c} - #{c.codepoints.first}"
+      NIKKUD_CP1255.include?(c)
+    # TODO: add Mac encoding?
+    end
+  end
+end

metadata

@@ -0,0 +1,44 @@
+--- !ruby/object:Gem::Specification
+name: hebrew
+version: !ruby/object:Gem::Version
+  version: 0.0.2
+platform: ruby
+authors:
+- Asaf Bartov
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-09-10 00:00:00.000000000 Z
+dependencies: []
+description: Some useful code to identify, transcode, and manipulate Hebrew text
+email: asaf.bartov@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/hebrew.rb
+homepage: http://rubygems.org/gems/hebrew
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.0.6
+signing_key: 
+specification_version: 4
+summary: Hebrew string manipulation
+test_files: []