hebrew 0.0.2 → 0.1.3

checksums.yaml

@@ -1,15 +1,7 @@
 ---
-!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=
+SHA1:
+  metadata.gz: 41268cfa1a659bd6997ec10f67fbc3afd7d15f19
+  data.tar.gz: f2d888c38878d69b06e7e9a057a58ffe175cf6af
+SHA512:
+  metadata.gz: 686135b818c4d6867fe4a005ce09862705ed9b9eac5ed309e5bdbcae8bc1cd04764f8cd8f49feb1db6eccd4002abb4bde65b72f0db15cec9d53a9a91dc4a22b9
+  data.tar.gz: 1241dc30e1b38a16cc2371d5d0e5c43441022b700a1c1569508e220fb69c6ef8d7d05af3bc965593ca19bce078c4159773532cfef32089bf8ba7820763321aab

data/lib/hebrew.rb

@@ -3,19 +3,42 @@
 # @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"]
+# codepoints for CP1255 nikkud
+NIKKUD_CP1255 = [192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 203, 204, 209, 210]
+#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 = [0x05b0, 0x05b1, 0x05b2, 0x05b3, 0x05b4, 0x05b5, 0x05b6, 0x05b7, 0x05b8, 0x05b9, 0x05bb, 0x05bc, 0x05c1, 0x05c2]
+#NIKKUD_UTF8 = ["\u05b0", "\u05b1", "\u05b2", "\u05b3", "\u05b4", "\u05b5", "\u05b6", "\u05b7", "\u05b8", "\u05b9", "\u05bb", "\u05bc", "\u05c1", "\u05c2"]
 # TODO: Mac encoding
 
+FIANLS_CP1255 = ["\xea".force_encoding('windows-1255'), "\xed".force_encoding('windows-1255'), "\xef".force_encoding('windows-1255'), "\xf3".force_encoding('windows-1255'), "\xf5".force_encoding('windows-1255')]
+
+FINALS_UTF8 = []
+
 # extend String class
 class String
   # this will return the string, stripped of any Hebrew nikkud characters
   def strip_nikkud
+    case self.encoding
+    when Encoding::UTF_8
+      strip_nikkud_utf8
+    when Encoding::WINDOWS_1255 || Encoding::CP1255
+      strip_nikkud_cp1255
+    end
+  end
+  def strip_nikkud_cp1255
+    target = ''.force_encoding('windows-1255')
+    self.each_codepoint {|cp|
+      unless self.class.is_codepoint_nikkud_cp1255(cp)
+        target += cp.chr(Encoding::CP1255) # is there a neater way?
+      end
+    }
+    return target
+  end
+  def strip_nikkud_utf8
     target = ''
-    self.each_char {|c|
-      unless is_nikkud(c)
-        target += c 
+    self.each_codepoint {|cp|
+      unless self.class.is_codepoint_nikkud_utf8(cp)
+        target += cp.chr(Encoding::UTF_8)
       end
     }
     return target
@@ -24,6 +47,12 @@ class String
   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_codepoint_nikkud_cp1255(cp)
+    NIKKUD_CP1255.include?(cp)
+  end
+  def self.is_codepoint_nikkud_utf8(cp)
+    NIKKUD_UTF8.include?(cp)
+  end
   def self.is_nikkud_by_encoding(c, encoding)
     case encoding
     when Encoding::UTF_8
@@ -35,4 +64,12 @@ class String
     # TODO: add Mac encoding?
     end
   end
+  def self.is_final_by_encoding(c, encoding)
+    case encoding
+    when Encoding::UTF_8
+      FIANLS_UTF8.include?(c)
+    when Encoding::WINDOWS_1255 || Encoding::CP1255
+      FINALS_CP1255.include?(c)
+    end
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: hebrew
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.1.3
 platform: ruby
 authors:
 - Asaf Bartov
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-09-10 00:00:00.000000000 Z
+date: 2014-02-11 00:00:00.000000000 Z
 dependencies: []
 description: Some useful code to identify, transcode, and manipulate Hebrew text
 email: asaf.bartov@gmail.com
@@ -27,17 +27,17 @@ 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
+rubygems_version: 2.2.1
 signing_key: 
 specification_version: 4
 summary: Hebrew string manipulation