hebrew 0.1.7 → 0.2.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: e744e020d212f7b11acbb82e9e4d99944fc3d06c
-  data.tar.gz: 3f0fb1762473e8b52a4fbf7b33b8251e3a632a08
+SHA256:
+  metadata.gz: 2cc64efe3ce4523383c76a9265c8e0d015f847c1aaefacb903470ec9c295f342
+  data.tar.gz: e0f065db2c27e3dd0b47669abc629eb228e4f37b118db54afa128203d832e8e5
 SHA512:
-  metadata.gz: eeb8e700eaa11b89dbfd77107cb09d15a56de4c5eab1320301fb1445d411ae2e6bc527195f6c83cb24e9189ed09c36a039d458cb19d665d7700952e4d6868151
-  data.tar.gz: f8ded3902c477c207425e64daf813f7f403b9d8652dba662508b6f179e1421ca4a8e3573f12fbd52babcb35e57389c67ef8d0406b3da104122c8129723cc015f
+  metadata.gz: f5143397a2bed96cccc2aead3dee8aac7f7f28637819e1979b61cf37e1bb96712b29e6a7f1f218c6281b4bdda4e67435ce2a5f8d0195c7982bc088adfcdb9fb4
+  data.tar.gz: 8ec1ba901eb082f53f1d8caa1049a5e48302418c48867b11e67e945ef50ef42112e735114fae64df1e0adf0a66296de188ab59cca419779a8d650afc8026aab9

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
@@ -31,7 +59,7 @@ class String
     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?
+        target << cp.chr(Encoding::CP1255) # is there a neater way?
       end
     }
     return target
@@ -40,7 +68,7 @@ class String
     target = ''
     self.each_codepoint {|cp|
       unless self.class.is_codepoint_nikkud_utf8(cp)
-        target += cp.chr(Encoding::UTF_8)
+        target << cp.chr(Encoding::UTF_8)
       end
     }
     return target
@@ -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 [HEB_UTF8_XOLAM, HEB_UTF8_SHURUK].include?(c.codepoints[0]) && prev_char != 'ו'
+        prev_char = c
+      end
+      return ret.gsub('יי','ִי') # 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
@@ -77,7 +142,7 @@ class String
     #NIKKUD_CP1255.include?(cp) # cleaner, but much slower
   end
   def self.is_codepoint_nikkud_utf8(cp)
-    return ((cp > 0x05af && cp < 0x05ba) or [0x05bb, 0x05bc, 0x05c1, 0x05c2].include?(cp))
+    return ((cp > 0x05af && cp < 0x05bd) or [0x05c1, 0x05c2].include?(cp))
     #NIKKUD_UTF8.include?(cp) # cleaner, but much slower
   end
   # this will return true if the first parameter is a nikkud character in the encoding of the second parameter

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: hebrew
 version: !ruby/object:Gem::Version
-  version: 0.1.7
+  version: 0.2.2
 platform: ruby
 authors:
 - Asaf Bartov
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-04-03 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
@@ -27,17 +27,16 @@ 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: 2.2.1
+rubygems_version: 3.1.2
 signing_key: 
 specification_version: 4
 summary: Hebrew string manipulation