romanized_hebrew 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: fc125022b5101cd4196d95f009cc2f7b6b83aa6f945841ff2a8bc43e0ff6a511
+  data.tar.gz: 2b78fe60ec46c16f94799360cac55e6df7d89b10851086705c5de933d2d8dc1c
+SHA512:
+  metadata.gz: 10b5778b44903dbf40c57a10daef40325a9c344fba17b77ccf610dbe0c559c34db46c367fa1c651dd140b17e109d7d406ac42720cc41943b485d48082ffd0868
+  data.tar.gz: 4ef964215498b137dcd3eb482a4f10053272917cfa1bd0c0763dc76a5c8c3a86f1bf037136c17ebbc4c218202e815ce0d736b31a21f1b4b9e3d60f513e185054

data/lib/romanized_hebrew.rb

@@ -0,0 +1,100 @@
+# Romanized Hebrew library
+
+# RomanizedHebrew converts the romanization menthod used by the
+# English occultists of the 19th and 20th centuries. It is as follows:
+#
+#   A  = aleph   B  = beth    G  = gimel    D  = dalet
+#   H  = heh     V  = vav     Z  = zayin    Ch = chet
+#   T  = teth    I  = yod     K  = kaf      L  = lamed
+#   M  = mem     N  = nun     S  = samekh   O  = ayin
+#   P  = peh     Tz = tzaddi  Q  = qoph     R  = resh
+#   Sh = shin    Th = tav
+# 
+#   Ligatures:
+#   Ii = yod-yod   Vi = vav-yod     Vv = vav-vav
+# 
+#   Niqqud:
+#   ;  = Sh'va                *  = Dagesh
+#   \\ =  Kubutz              `  = Holam
+#   1  = Hiriq                2  = Zeire                
+#   3  = Segol                ;3 = Reduced Segol        
+#   _  = Patach               ;_ = Reduced Patach       
+#   7  = Kamatz               ;7 = Reduced Kamatz       
+#   Shl = Shin dot left       Shr = Shin dot right
+#       ;; = escape an actual semicolon
+# 
+# Letters which can be final can take a 'f' or 'i' prefix to
+# force the interpretation to be 'final' or 'initial'... otherwise
+# a letter at the end of a word is considered final.
+class RomanizedHebrew
+  NIQQUD = %r!;[;37_]?  |  [1237_*\\`]!x
+  INFERRED_FINAL = %r!
+     (?:K|M|N|P|Tz)  # one of the possibly-final letters
+     (?= #{NIQQUD}*+   # looking at niqqod
+        (?:\W|\Z))     # ... followed by a non-word or end-of-line
+  !x
+  TRANSLITERATE = %r!
+    ([A-Z][fhilvz]*+)          # consonant (and Shin dots)
+    (#{NIQQUD}?+)(#{NIQQUD}?+) # possible niqqud 
+  !x
+
+  @trans_tbl = {   # transliteration table
+    # aleph, beth, gimel, dalet
+    'A' => "\u05d0", 'B' => "\u05d1", 'G' => "\u05d2", 'D' => "\u05d3",    
+    # heh, vav, zain, cheth
+    'H' => "\u05d4", 'V' => "\u05d5", 'Z' => "\u05d6", 'Ch' => "\u05d7",
+    # tayt, yod, kaf_final, kaf, kaf_initial
+    'T' => "\u05d8", 'I' => "\u05d9", 'Kf' => "\u05da", 'K' => "\u05db",  'Ki' => "\u05db",  
+    # lamed, mem_final, mem, mem_initial, nun_final
+    'L' => "\u05dc", 'Mf' => "\u05dd", 'M' => "\u05de", 'Mi' => "\u05de", 'Nf' => "\u05df",  
+    # nun, samekh, ayin, peh_final
+    'N' => "\u05e0", 'Ni' => "\u05e0", 'S' => "\u05e1", 'O' => "\u05e2", 'Pf' => "\u05e3", 
+    # peh, peh_initial, tzaddi_final, tzaddi, tzaddi_initial 
+    'P' => "\u05e4", 'Pi' => "\u05e4", 'Tzf' => "\u05e5", 'Tz' => "\u05e6", 'Tzi' => "\u05e6", 
+    # qoph, resh, shin, tav
+    'Q' => "\u05e7",  'R' => "\u05e8", 'Sh' => "\u05e9", 'Th' => "\u05ea",  
+    # Ligatures
+    # doube-yod, double-vav, vav-yod
+    'Ii' => "\u05f2", 'Vv' => "\u05f0", 'Vi' => "\u05f1",
+    # niqqud
+    ';;' => ';',      # escape an actual semicolon
+    ';' => "\u05b0",  # Sh'va 
+    ';3' => "\u05b1", # Reduced Segol
+    ';_' => "\u05b2", # Reduced Patach
+    ';7' => "\u05b3", # Reduced Kamatz
+    '1' => "\u05b4",  # Hiriq
+    '2' => "\u05b5",  # Zeire
+    '3' => "\u05b6",  # Segol
+    '_' => "\u05b7",  # Patach
+    '7' => "\u05b8",  # Kamatz
+    '*' => "\u05bc",  # Dagesh
+    '\\' => "\u05bb", # Kubutz
+    '`' => "\u05b9",  # Holam
+    'Shl' => "\u05e9\u05c2", # Shin dot left
+    'Shr' => "\u05e9\u05c1"  # Shin dot right
+  }
+  @trans_tbl.default_proc = Proc.new {|h,k| k } # identity when unknown chars appear
+
+  # Convert a romanized hebrew string, `rom`, to actual hebrew.  If the format is set to
+  # `:html`, then the output is a series of hexadecimal html entities, which can be
+  # easier to work with than mixing RTL and LTR languages in a file.
+  #
+  #  RomanizedHebrew.convert('ABG')                 # => אבג
+  #  RomanizedHebrew.convert('ABG', format: :html)  # => אבג 
+  def self.convert(rom, format: :unicode)
+    # first, add automatic final letters
+    hebrew = rom.gsub(INFERRED_FINAL, '\0f')
+    # second, perform the transliteration
+    hebrew.gsub!(TRANSLITERATE) do |m|
+      "#{@trans_tbl[$1]}#{@trans_tbl[$2]}#{@trans_tbl[$3]}"
+    end
+    # finally, convert to html entities if needed
+    if format == :html then
+      hebrew = hebrew.codepoints.map do |cp|
+        cp > 127 ? "&\#x#{cp.to_s(16)};" : cp.chr
+      end.join('')
+    end
+    hebrew
+  end
+
+end

metadata

@@ -0,0 +1,74 @@
+--- !ruby/object:Gem::Specification
+name: romanized_hebrew
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- Richard Todd
+autorequire:
+bindir: bin
+cert_chain:
+- |
+  -----BEGIN CERTIFICATE-----
+  MIIEnjCCAwagAwIBAgIBATANBgkqhkiG9w0BAQsFADBKMRwwGgYDVQQDDBNyaWNo
+  YXJkLndlc2xleS50b2RkMRUwEwYKCZImiZPyLGQBGRYFZ21haWwxEzARBgoJkiaJ
+  k/IsZAEZFgNjb20wHhcNMjMwODA3MjE0NDQ0WhcNMjQwODA2MjE0NDQ0WjBKMRww
+  GgYDVQQDDBNyaWNoYXJkLndlc2xleS50b2RkMRUwEwYKCZImiZPyLGQBGRYFZ21h
+  aWwxEzARBgoJkiaJk/IsZAEZFgNjb20wggGiMA0GCSqGSIb3DQEBAQUAA4IBjwAw
+  ggGKAoIBgQCu8oYnBNhjNeRWLr/ugYWP8eTGYtYR2LDj5A/9D0Fn7K5tJ4/w7idk
+  o32XeigO6khrUdVNun1NyukX+eGUsP46UM3ZovRaCAtXcFRRnlK4+121TlWAJ12R
+  eF9FojSzLdZgMO3xxRqPFk/2L8neWastB+zXijo59dsQLDqBtjH3fNdw3HBJBB2Y
+  VqtqdlvPBIzORJ6dhXyFVFU1oPW2VM0/tiPv9TY5GwPG7xvRnU/SShYLQ8o3cK1V
+  eiBkJvt1ETu2Gt2dHwWW22+Al/fNVBiamyY4GzFJOywkEH6plXvxyhPilbcrhCH7
+  MY4++WGphTxwi8zGZwTXM0l60OZVDZRur7Qk45BLUlmc01GHfi09Z+Vu79D1QTuP
+  BdCl6TxJ8RXvaPjFLZd7LGDWe0hjg94dNJTqfuDsTZ46E68vMbH2f4LywWasUgcG
+  DTVzqGgLDXmn2RmSaXkr3x5yHeBM4Ab6D6HlQO8kA5McnOr875DKiuTnjqbjNbtP
+  FpUprgfv4sECAwEAAaOBjjCBizAJBgNVHRMEAjAAMAsGA1UdDwQEAwIEsDAdBgNV
+  HQ4EFgQUJARBYPHE9LuKukuhbU/h5Xjzw94wKAYDVR0RBCEwH4EdcmljaGFyZC53
+  ZXNsZXkudG9kZEBnbWFpbC5jb20wKAYDVR0SBCEwH4EdcmljaGFyZC53ZXNsZXku
+  dG9kZEBnbWFpbC5jb20wDQYJKoZIhvcNAQELBQADggGBAH0e5AxjTWi61jv1c+0N
+  BKhR1AYIG3b76lW5FYzwwUsdQWEDIMiDuqGYU+TLIoCILa/PSnuVyoVshzBJhOyV
+  d/HaM0+clcaHa/rhqI4PtY3eOMW58e/To1dKvru8QfyUTy4KdSz2ETVliNGh+4HN
+  Ft3/WqgEmwQsVsWKfvlldg9qmM20dgyn7P50CF2fx4MRdrpXKomDoK8aV7iUoaCE
+  Q4my4ZRA6lMiaSN4GI1BG1T+qYFE2YoDl5Ako4BIFvGgUbBkj2Hch+P+wnGJkw7m
+  bgRMhCH9xl3z8f167zIghNDkCFY541EKBQt8sDRRzTkohg0sz4+bgirfhQlQPrzI
+  P6BznyHsH1zchecDaX7bMZylACxISH3beJWUTybIxOApKK2WVHFjSTwCo6LLaAox
+  F4N2DQ+zWN/3QJeBhuhKb6E5CESZ3gFKrYzucXZwIlbYSbW3v+43niQAvCjy4ef2
+  mFxhcR0tTgLoosbpbTbKgowVeGIFOARJZXGWUzkEb9UiKg==
+  -----END CERTIFICATE-----
+date: 2023-08-07 00:00:00.000000000 Z
+dependencies: []
+description: "The romanized_hebrew gem was built to \nconvert the hebrew romanization
+  commonly used by the 19th and 20th-century\nEnglish occultists (e.g. Mathers, Waite,
+  etc) into actual hebrew unicode. It\ncan provide the unicode string, or a string
+  of HTML entities.\n"
+email: rwtodd@users.noreply.github.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/romanized_hebrew.rb
+homepage: https://github.com/rwtodd/romanized_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: []
+rubygems_version: 3.4.10
+signing_key:
+specification_version: 4
+summary: Converts romanized hebrew to unicode hebrew letters.
+test_files: []

metadata.gz.sig

@@ -0,0 +1,3 @@
+k��b�����l�8�f7ca�iF������	�����d<��$(6�s�pX�:�be��ai1OY�o���G��6B@�8�`�aH��ذ�0�v�*�]�V9Q���T��O(�&�e.f�
Rl�d���MO[��_\I [�}� �0�}~���P��?�2���W;.�U���,t$Tc�gU�L���FX�E�+&���~�\9S�b3�H��&�6��:���,�V5oՃ�h��k���ƿ�k��&�&h�����t�U�'�G��U��iU˒�P����
+�c
+���Q/�l@l�PoI����%��HjeH�ثH�)˗.ѹ�Z��+�c���}c�sS