hebrew 0.1.9 → 0.2.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 5a8c1321cb8e5040931921ab180b86295427e64f
-  data.tar.gz: fe567fbdb5384b967dfff2a0b787a1b403433a7a
+SHA256:
+  metadata.gz: f51ccf60da40434c682c097f6986b2ce581351d84b51990afa5d8fe7aa43a8ee
+  data.tar.gz: cd79e5dac8aa79c605b6b8e43fa9c710f3d66be233f18af381e22f6a17b1940b
 SHA512:
-  metadata.gz: 33ec8188e66991dca122aef6ecbb69a34ab566b79ede6fabce62f6de6975f97eeed2be3b4c176b74f4c1b03da3ef44283bb01017b67c2d3e25c86fb2c5619734
-  data.tar.gz: 674d5e7ca61a186d7713d245459e4b19b856b0fdc2fc56bd42d557a7e0d0d035ba87b0e194a8f0c5a27a91ffe751d7c247b2b04dda8293b79cf6351cdbb948e3
+  metadata.gz: 043bd286ef937aaa988bb0434684b16b349b35f743896892a51d6fc0ccb58697e885be356061f0a2c87a7f27e617c7762b82342cd524aacd2c20876838260d2a
+  data.tar.gz: dfe91f87abcf3bc0605e603cd1323809d3016c495a3f9b694fb7e149f3612e9985e3bdf3d6255a4e64850e897507ac97e9bcbbbc67c2fda31cd73e3dd08e5db4

data/lib/hebrew.rb

@@ -5,9 +5,7 @@
 
 # codepoints for CP1255 nikkud
 NIKKUD_CP1255 = [192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 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, 0x05bd, 0x05bf, 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')]
@@ -15,9 +13,39 @@ FIANLS_CP1255 = ["\xea".force_encoding('windows-1255'), "\xed".force_encoding('w
 FINALS_UTF8 = ["\u05da", "\u05dd", "\u05df", "\u05e3", "\u05e5"]
 HEB_UTF8_START = 1424
 HEB_UTF8_END = 1535
+HEB_UTF8_XIRIK = 1460
+HEB_UTF8_XOLAM = 1465
+HEB_UTF8_QUBBUTS = 1467
+HEB_UTF8_SHURUK = 1468
 
 # extend String class
 class String
+  def strip_hebrew
+    case self.encoding
+    when Encoding::UTF_8
+      strip_hebrew_utf8
+    when Encoding::WINDOWS_1255 || Encoding::CP1255
+      strip_hebrew_cp1255
+    end
+  end
+  def strip_hebrew_utf8
+    target = ''
+    self.each_codepoint {|cp|
+      unless self.class.is_codepoint_nikkud_utf8(cp) or self.is_hebrew_codepoint_utf8(cp)
+        target << cp.chr(Encoding::UTF_8)
+      end
+    }
+    return target
+  end
+  def strip_hebrew_cp1255
+    target = ''.force_encoding('windows-1255')
+    self.each_codepoint {|cp|
+      unless self.class.is_codepoint_nikkud_cp1255(cp) or self.is_hebrew_codepoint_cp1255(cp)
+        target << cp.chr(Encoding::CP1255) # is there a neater way?
+      end
+    }
+    return target
+  end
   # this will return the string, stripped of any Hebrew nikkud characters
   def strip_nikkud
     case self.encoding
@@ -58,6 +86,43 @@ class String
       return false
     end
   end
+
+  def falsehood
+    false
+  end
+
+  # this will add matres lectionis (yods and vavs as vowels) after diacritics that denote those vowels. The result won't always be morphologically correct Hebrew, but is useful for generating mostly-likely variants users may search for, when typing inputs (almost no Hebrew users know how to produce diacritics on the keyboard).
+  def naive_full_nikkud
+    ret = ''
+    prev_char = nil
+    case self.encoding
+    when Encoding::UTF_8
+      self.each_char do |c|
+        ret += c
+        ret += 'י' if c.codepoints[0] == HEB_UTF8_XIRIK
+        ret += 'ו' if c.codepoints[0] == HEB_UTF8_QUBBUTS
+        ret += 'ו' if c.codepoints[0] == HEB_UTF8_XOLAM && prev_char != 'ו'
+        prev_char = c
+      end
+      return ret.gsub("\u05b4יי","\u05b4י") # get rid of extraneous yods possibly added because we weren't looking ahead
+    else
+      return nil # not implemented for other encodings for now.
+    end
+  end
+
+  def any_nikkud?
+    func = case self.encoding
+      when Encoding::UTF_8
+        :is_codepoint_nikkud_utf8
+      when Encoding::WINDOWS_1255 || Encoding::CP1255
+        :is_codepoint_nikkud_cp1255
+      else
+        :falsehood
+      end
+    self.each_codepoint{|cp| return true if String.send(func, cp)}
+    return false
+  end
+
   def is_hebrew_codepoint_cp1255(cp)
     return ((cp > 191 && cp < 202) or [203, 204, 209, 210].include?(cp))
   end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: hebrew
 version: !ruby/object:Gem::Version
-  version: 0.1.9
+  version: 0.2.4
 platform: ruby
 authors:
 - Asaf Bartov
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-10-21 00:00:00.000000000 Z
+date: 2020-10-20 00:00:00.000000000 Z
 dependencies: []
 description: Some useful code to identify, transcode, and manipulate Hebrew text
 email: asaf.bartov@gmail.com
@@ -36,8 +36,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.4.6
+rubygems_version: 3.1.2
 signing_key: 
 specification_version: 4
 summary: Hebrew string manipulation