sanscript 0.4.3 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 978f081a49e46e4cade8a7cdef95ebdb89f7daac
-  data.tar.gz: e46caf2df596e745398a6a5ac86d2c11ed0c666d
+  metadata.gz: 348f8d72cc3d76ba760a4225a4f784324294474a
+  data.tar.gz: f3a1215ad14dc3778795dc0f6563345aaa3015fe
 SHA512:
-  metadata.gz: e0f01c0322755e57c5690799660e810cc7d85271c5b6ef185ce21b13f516c396f1ae8e090529ecbfa8fd8a9bfcce8519f15d4d3291188d6bc1f83279c0b59071
-  data.tar.gz: f87954bc573383f2ddf530274ef69dbe32e67ab49d3f49e6db90790abafef51e51c8596c22d044ae40b4907921c38fc26182342f0c96008492aec938e56afbc9
+  metadata.gz: c8eae2315a8d3a68ce1a873585ab752902287a027a6d45961fef77ad0174d3646d7c7c36107a5879b5b8b36c10afef93428b34098b2ae86dfb6026bb4d644e94
+  data.tar.gz: 1997c7bb6d11f4b139eb5cde903bc17bffb786bcad236351100e55248d57945fbd19e7cf83f409af357c4c36d1dfb43fbb5adc5a0c2997e66622ed1576bb1921

data/README.md

@@ -25,7 +25,9 @@ Or install it yourself as:
 
 ## Usage
 
-You can access detection through `Sanscript.detect(text)` and transliteration through `Sanscript.transliterate(text, from, to)`. Code should be fairly straightforward and partially documented.
+You can access detection through `Sanscript.detect(text)` and transliteration through `Sanscript.transliterate(text, from, to)`.
+
+Documentation is provided in YARD format and available online at [rubydoc.info](http://www.rubydoc.info/github/ubcsanskrit/sanscript.rb).
 
 ## Development
 

data/lib/sanscript.rb

@@ -1,5 +1,8 @@
 # frozen_string_literal: true
+require "ragabash"
+
 require "sanscript/version"
+require "sanscript/exceptions"
 require "sanscript/detect"
 require "sanscript/transliterate"
 require "sanscript/benchmark"
@@ -21,23 +24,35 @@ module Sanscript
   #
   # @overload transliterate(text, from, to, **opts)
   #   @param text [String] the String to transliterate
-  #   @param from [Symbol] the name of the scheme to transliterate from
+  #   @param from [Symbol, nil] the name of the scheme to transliterate from, or Nil to detect
   #   @param to [Symbol] the name of the scheme to transliterate to
+  #   @option opts [Symbol] :default_scheme a default scheme to fall-back to if detection fails
   #   @option opts [Boolean] :skip_sgml (false) escape SGML-style tags in text string
   #   @option opts [Boolean] :syncope (false) activate Hindi-style schwa syncope
   #   @return [String] the transliterated String
   #
+  #   @raise [DetectionError] if scheme detection and fallback fail
+  #   @raise [SchemeNotSupportedError] if a provided transliteration scheme is not supported
+  #
   # @overload transliterate(text, to, **opts)
   #   @param text [String] the String to transliterate
   #   @param to [Symbol] the name of the scheme to transliterate to
   #   @option opts [Symbol] :default_scheme a default scheme to fall-back to if detection fails
   #   @option opts [Boolean] :skip_sgml (false) escape SGML-style tags in text string
   #   @option opts [Boolean] :syncope (false) activate Hindi-style schwa syncope
-  #   @return [String, nil] the transliterated String, or nil if detection and fallback fail
+  #   @return [String] the transliterated String
+  #
+  #   @raise [DetectionError] if scheme detection and fallback fail
+  #   @raise [SchemeNotSupportedError] if a provided transliteration scheme is not supported
+  #
   def transliterate(text, from, to = nil, **opts)
     if to.nil?
       to = from
-      from = Detect.detect_scheme(text) || opts[:default_scheme] || return
+      from = nil
+    end
+    if from.nil?
+      from = Detect.detect_scheme(text) || opts[:default_scheme] ||
+             raise(DetectionError, "String detection and fallback failed.")
     end
     Transliterate.transliterate(text, from, to, opts)
   end

data/lib/sanscript/benchmark.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
+#:nocov:
 
-require "sanscript/refinements"
 begin
   require "benchmark/ips"
 rescue LoadError
@@ -12,18 +12,17 @@ rescue LoadError
 end
 
 module Sanscript
-  using Refinements
   # Benchmark/testing module.
   module Benchmark
     module_function
 
     # Runs benchmark-ips test on detection methods.
     def detect!
-      iast_string = "nānāśāstrasubhāṣitāmṛtarasaiḥ śrotrotsavaṃ kurvatāṃ yeṣāṃ yānti dināni paṇḍitajanavyāyāmakhinnātmanām teṣāṃ janma ca jīvitaṃ ca sukṛtaṃ tair eva bhūr bhūṣitā śeṣaih kiṃ paśuvad vivekarahitair bhūbhārabhūtair naraḥ"
       deva_string = "नानाशास्त्रसुभाषितामृतरसैः श्रोत्रोत्सवं कुर्वतां येषां यान्ति दिनानि पण्डितजनव्यायामखिन्नात्मनाम् तेषां जन्म च जीवितं च सुकृतं तैर् एव भूर् भूषिता शेषैह् किं पशुवद् विवेकरहितैर् भूभारभूतैर् नरः"
+      malayalam_string = "നാനാശാസ്ത്രസുഭാഷിതാമൃതരസൈഃ ശ്രോത്രോത്സവം കുര്വതാം യേഷാം യാന്തി ദിനാനി പണ്ഡിതജനവ്യായാമഖിന്നാത്മനാമ് തേഷാം ജന്മ ച ജീവിതം ച സുകൃതം തൈര് ഏവ ഭൂര് ഭൂഷിതാ ശേഷൈഹ് കിം പശുവദ് വിവേകരഹിതൈര് ഭൂഭാരഭൂതൈര് നരഃ"
+      iast_string = "nānāśāstrasubhāṣitāmṛtarasaiḥ śrotrotsavaṃ kurvatāṃ yeṣāṃ yānti dināni paṇḍitajanavyāyāmakhinnātmanām teṣāṃ janma ca jīvitaṃ ca sukṛtaṃ tair eva bhūr bhūṣitā śeṣaih kiṃ paśuvad vivekarahitair bhūbhārabhūtair naraḥ"
       slp1_string = "nAnASAstrasuBAzitAmftarasEH SrotrotsavaM kurvatAM yezAM yAnti dinAni paRqitajanavyAyAmaKinnAtmanAm tezAM janma ca jIvitaM ca sukftaM tEr eva BUr BUzitA SezEh kiM paSuvad vivekarahitEr BUBAraBUtEr naraH"
       hk_string = "nAnAzAstrasubhASitAmRtarasaiH zrotrotsavaM kurvatAM yeSAM yAnti dinAni paNDitajanavyAyAmakhinnAtmanAm teSAM janma ca jIvitaM ca sukRtaM tair eva bhUr bhUSitA zeSaih kiM pazuvad vivekarahitair bhUbhArabhUtair naraH"
-      malayalam_string = "അ ആ ഇ ഈ ഉ ഊ ഋ ൠ ഌ ൡ എ ഏ ഐ ഒ ഓ ഔ"
 
       ::Benchmark.ips do |x|
         x.config(time: 5, warmup: 1)
@@ -47,32 +46,61 @@ module Sanscript
       true
     end
 
-    # Runs benchmark-ips test on transliteration methods.
-    def transliterate!
+    # Runs benchmark-ips test on roman-source transliteration methods.
+    def transliterate_roman!
       iast_string = "nānāśāstrasubhāṣitāmṛtarasaiḥ śrotrotsavaṃ kurvatāṃ yeṣāṃ yānti dināni paṇḍitajanavyāyāmakhinnātmanām teṣāṃ janma ca jīvitaṃ ca sukṛtaṃ tair eva bhūr bhūṣitā śeṣaih kiṃ paśuvad vivekarahitair bhūbhārabhūtair naraḥ"
-      deva_string = "नानाशास्त्रसुभाषितामृतरसैः श्रोत्रोत्सवं कुर्वतां येषां यान्ति दिनानि पण्डितजनव्यायामखिन्नात्मनाम् तेषां जन्म च जीवितं च सुकृतं तैर् एव भूर् भूषिता शेषैह् किं पशुवद् विवेकरहितैर् भूभारभूतैर् नरः"
       slp1_string = "nAnASAstrasuBAzitAmftarasEH SrotrotsavaM kurvatAM yezAM yAnti dinAni paRqitajanavyAyAmaKinnAtmanAm tezAM janma ca jIvitaM ca sukftaM tEr eva BUr BUzitA SezEh kiM paSuvad vivekarahitEr BUBAraBUtEr naraH"
+      hk_string = "nAnAzAstrasubhASitAmRtarasaiH zrotrotsavaM kurvatAM yeSAM yAnti dinAni paNDitajanavyAyAmakhinnAtmanAm teSAM janma ca jIvitaM ca sukRtaM tair eva bhUr bhUSitA zeSaih kiM pazuvad vivekarahitair bhUbhArabhUtair naraH"
 
       ::Benchmark.ips do |x|
-        x.config(time: 5, warmup: 2)
+        x.config(time: 3, warmup: 2)
 
         x.report("IAST==>Devanagari") do
-          raise unless Sanscript.transliterate(iast_string, :iast, :devanagari) == deva_string
+          Sanscript.transliterate(iast_string, :iast, :devanagari)
+        end
+        x.report("IAST==>SLP1") do
+          Sanscript.transliterate(iast_string, :iast, :slp1)
         end
         x.report("IAST==>SLP1") do
-          raise unless Sanscript.transliterate(iast_string, :iast, :slp1) == slp1_string
+          Sanscript.transliterate(iast_string, :iast, :hk)
         end
         x.report("SLP1==>Devanagari") do
-          raise unless Sanscript.transliterate(slp1_string, :slp1, :devanagari) == deva_string
+          Sanscript.transliterate(slp1_string, :slp1, :devanagari)
         end
         x.report("SLP1==>IAST") do
-          raise unless Sanscript.transliterate(slp1_string, :slp1, :iast) == iast_string
+          Sanscript.transliterate(slp1_string, :slp1, :iast)
         end
-        x.report("Devanagari==>SLP1") do
-          raise unless Sanscript.transliterate(deva_string, :devanagari, :slp1) == slp1_string
+        x.report("SLP1==>HK") do
+          Sanscript.transliterate(slp1_string, :slp1, :hk)
+        end
+        x.report("HK==>Devanagari") do
+          Sanscript.transliterate(hk_string, :hk, :devanagari)
         end
+        x.report("HK==>IAST") do
+          Sanscript.transliterate(hk_string, :hk, :iast)
+        end
+        x.report("HK==>SLP1") do
+          Sanscript.transliterate(hk_string, :hk, :slp1)
+        end
+        x.compare!
+      end
+      true
+    end
+
+    # Runs benchmark-ips test on brahmic-source transliteration methods.
+    def transliterate_brahmic!
+      deva_string = "नानाशास्त्रसुभाषितामृतरसैः श्रोत्रोत्सवं कुर्वतां येषां यान्ति दिनानि पण्डितजनव्यायामखिन्नात्मनाम् तेषां जन्म च जीवितं च सुकृतं तैर् एव भूर् भूषिता शेषैह् किं पशुवद् विवेकरहितैर् भूभारभूतैर् नरः"
+
+      ::Benchmark.ips do |x|
+        x.config(time: 5, warmup: 2)
         x.report("Devanagari==>IAST") do
-          raise unless Sanscript.transliterate(deva_string, :devanagari, :iast) == iast_string
+          Sanscript.transliterate(deva_string, :devanagari, :iast)
+        end
+        x.report("Devanagari==>SLP1") do
+          Sanscript.transliterate(deva_string, :devanagari, :slp1)
+        end
+        x.report("Devanagari==>HK") do
+          Sanscript.transliterate(deva_string, :devanagari, :hk)
         end
         x.compare!
       end

data/lib/sanscript/detect.rb

@@ -61,6 +61,7 @@ module Sanscript
     #   @return [Symbol, nil] the Symbol of the scheme, or nil if no match
 
     # @!visibility private
+    # :nocov:
     if Regexp.method_defined?(:match?)
       require "sanscript/detect/ruby24"
       extend Ruby24
@@ -68,5 +69,6 @@ module Sanscript
       require "sanscript/detect/ruby2x"
       extend Ruby2x
     end
+    # :nocov:
   end
 end

data/lib/sanscript/exceptions.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+module Sanscript
+  using ::Ragabash::Refinements
+  # Error for when transliteration scheme is not supported.
+  class SchemeNotSupportedError < StandardError
+    def initialize(scheme = :unknown)
+      super(":#{scheme} is not supported.")
+    end
+  end
+
+  # Error for when scheme detection should non-silently fail
+  # (such as inside a transliteration method).
+  class DetectionError < StandardError
+    def initialize(message = "String detection failed.")
+      super
+    end
+  end
+end

data/lib/sanscript/transliterate.rb

@@ -1,9 +1,8 @@
 # frozen_string_literal: true
 
-require "sanscript/refinements"
 require "sanscript/transliterate/schemes"
 module Sanscript
-  using Refinements
+  using ::Ragabash::Refinements
   # Sanskrit transliteration module.
   # Derived from Sanscript (https://github.com/sanskrit/sanscript.js), which is
   # released under the MIT and GPL Licenses.
@@ -144,8 +143,8 @@ module Sanscript
       from = from.to_sym
       to = to.to_sym
       return data if from == to
-      raise "Scheme not known ':#{from}'" unless @schemes.key?(from)
-      raise "Scheme not known ':#{to}'" unless @schemes.key?(to)
+      raise SchemeNotSupportedError, from unless @schemes.key?(from)
+      raise SchemeNotSupportedError, to unless @schemes.key?(to)
 
       data = data.to_str.dup
       options = @defaults.merge(opts)
@@ -229,39 +228,40 @@ module Sanscript
       # @param map [Hash] map data generated from {#make_map}
       # @return [String] the transliterated string
       def transliterate_roman(data, map, options = {})
-        data = data.to_str.dup
+        data = data.to_str.chars
         buf = []
-        token_buffer = String.new
+        token_buffer = []
         had_consonant = false
         transliteration_enabled = true
         control_char = false
+        max_token_length = map[:max_token_length]
 
         until data.empty? && token_buffer.empty?
-          token_buffer << data.slice!(0, map[:max_token_length] - token_buffer.length)
-
           # Match all token substrings to our map.
-          map[:max_token_length].downto(1) do |j|
-            token = token_buffer[0, j]
-
-            if !control_char && token == "##"
-              transliteration_enabled = !transliteration_enabled
-              token_buffer.slice!(0, 2)
-              break
-            elsif control_char && token == "#}"
-              transliteration_enabled = true
-              control_char = false
-              buf << token
-              token_buffer.slice!(0, 2)
-              break
-            elsif transliteration_enabled && token == "{#"
-              transliteration_enabled = false
-              control_char = true
-              buf << token
-              token_buffer.slice!(0, 2)
-              break
+          token = data[0, max_token_length].join("")
+          max_token_length.downto(1) do |j|
+            token = token[0, j] unless j == max_token_length
+            if j == 2
+              if !control_char && token == "##"
+                transliteration_enabled = !transliteration_enabled
+                data.shift(2)
+                break
+              elsif control_char && token == "#}"
+                transliteration_enabled = true
+                control_char = false
+                buf << token
+                data.shift(2)
+                break
+              elsif transliteration_enabled && token == "{#"
+                transliteration_enabled = false
+                control_char = true
+                buf << token
+                data.shift(2)
+                break
+              end
             end
-            temp_letter = map[:letters][token]
-            if !temp_letter.nil? && transliteration_enabled
+
+            if transliteration_enabled && (temp_letter = map[:letters][token])
               if map[:to_roman?]
                 buf << temp_letter
               else
@@ -269,18 +269,19 @@ module Sanscript
                 # vowels to appear as marks if we've just seen a
                 # consonant.
                 if had_consonant
-                  temp_mark = map[:marks][token]
-                  if !temp_mark.nil?
+                  # rubocop:disable Metrics/BlockNesting
+                  if (temp_mark = map[:marks][token])
                     buf << temp_mark
                   elsif token != "a"
-                    buf << map[:virama] << temp_letter
+                    buf.push(map[:virama], temp_letter)
                   end
+                  # rubocop:enable Metrics/BlockNesting
                 else
                   buf << temp_letter
                 end
                 had_consonant = map[:consonants].key?(token)
               end
-              token_buffer.slice!(0, j)
+              j > 1 ? data.shift(j) : data.shift
               break
             elsif j == 1 # Last iteration
               if had_consonant
@@ -288,7 +289,7 @@ module Sanscript
                 buf << map[:virama] unless options[:syncope]
               end
               buf << token
-              token_buffer.slice!(0, 1)
+              data.shift
             end
           end
         end
@@ -302,27 +303,27 @@ module Sanscript
       # @param map [Hash] map data generated from {#make_map}
       # @return [String] the transliterated string
       def transliterate_brahmic(data, map)
-        data = data.to_str.dup
+        data = data.to_str.chars
         buf = []
         had_roman_consonant = false
         transliteration_enabled = true
         control_char = false
 
         until data.empty?
-          token = data.slice(0, 2)
+          token = data[0, 2].join("")
           if !control_char && token == "##"
             if had_roman_consonant
               buf << "a" if transliteration_enabled
               had_roman_consonant = false
             end
             transliteration_enabled = !transliteration_enabled
-            data.slice!(0, 2)
+            data.shift(2)
             next
           elsif control_char && token == "#}"
             transliteration_enabled = true
             control_char = false
             buf << token
-            data.slice!(0, 2)
+            data.shift(2)
             next
           elsif transliteration_enabled && token == "{#"
             if had_roman_consonant
@@ -332,11 +333,11 @@ module Sanscript
             transliteration_enabled = false
             control_char = true
             buf << token
-            data.slice!(0, 2)
+            data.shift(2)
             next
           end
 
-          l = data.slice!(0, 1)
+          l = data.shift
           unless transliteration_enabled
             buf << l
             next

data/lib/sanscript/transliterate/schemes.rb

@@ -1,8 +1,7 @@
 # frozen_string_literal: true
-require "sanscript/refinements"
 
 module Sanscript
-  using Refinements
+  using ::Ragabash::Refinements
   module Transliterate
     #  Schemes
     #  =======
@@ -25,13 +24,13 @@ module Sanscript
       # 'va' and 'ba' are both rendered as ব.
       #
       bengali: {
-        vowels: "অ আ ই ঈ উ ঊ ঋ ৠ ঌ ৡ  এ ঐ  ও ঔ".w_split,
-        vowel_marks: "া ি ী ু ূ ৃ ৄ ৢ ৣ  ে ৈ  ো ৌ".w_split,
-        other_marks: "ং ঃ ঁ".w_split,
+        vowels: "অ আ ই ঈ উ ঊ ঋ ৠ ঌ ৡ  এ ঐ  ও ঔ".split(/\s/),
+        vowel_marks: "া ি ী ু ূ ৃ ৄ ৢ ৣ  ে ৈ  ো ৌ".split(/\s/),
+        other_marks: "ং ঃ ঁ".split(/\s/),
         virama: ["্"],
-        consonants: "ক খ গ ঘ ঙ চ ছ জ ঝ ঞ ট ঠ ড ঢ ণ ত থ দ ধ ন প ফ ব ভ ম য র ল ব শ ষ স হ ळ ক্ষ জ্ঞ".w_split,
-        symbols: "০ ১ ২ ৩ ৪ ৫ ৬ ৭ ৮ ৯ ॐ ঽ । ॥".w_split,
-        other: "    ড ঢ  য ".w_split,
+        consonants: "ক খ গ ঘ ঙ চ ছ জ ঝ ঞ ট ঠ ড ঢ ণ ত থ দ ধ ন প ফ ব ভ ম য র ল ব শ ষ স হ ळ ক্ষ জ্ঞ".split(/\s/),
+        symbols: "০ ১ ২ ৩ ৪ ৫ ৬ ৭ ৮ ৯ ॐ ঽ । ॥".split(/\s/),
+        other: "    ড ঢ  য ".split(/\s/),
       },
 
       # Devanagari
@@ -41,15 +40,15 @@ module Sanscript
       devanagari: {
         # "Independent" forms of the vowels. These are used whenever the
         # vowel does not immediately follow a consonant.
-        vowels: "अ आ इ ई उ ऊ ऋ ॠ ऌ ॡ ऎ ए ऐ ऒ ओ औ".w_split,
+        vowels: "अ आ इ ई उ ऊ ऋ ॠ ऌ ॡ ऎ ए ऐ ऒ ओ औ".split(/\s/),
 
         # "Dependent" forms of the vowels. These are used whenever the
         # vowel immediately follows a consonant. If a letter is not
         # listed in `vowels`, it should not be listed here.
-        vowel_marks: "ा ि ी ु ू ृ ॄ ॢ ॣ ॆ े ै ॊ ो ौ".w_split,
+        vowel_marks: "ा ि ी ु ू ृ ॄ ॢ ॣ ॆ े ै ॊ ो ौ".split(/\s/),
 
         # Miscellaneous marks, all of which are used in Sanskrit.
-        other_marks: "ं ः ँ".w_split,
+        other_marks: "ं ः ँ".split(/\s/),
 
         # In syllabic scripts like Devanagari, consonants have an inherent
         # vowel that must be suppressed explicitly. We do so by putting a
@@ -58,10 +57,10 @@ module Sanscript
 
         # Various Sanskrit consonants and consonant clusters. Every token
         # here has an explicit vowel. Thus "क" is "ka" instead of "k".
-        consonants: "क ख ग घ ङ च छ ज झ ञ ट ठ ड ढ ण त थ द ध न प फ ब भ म य र ल व श ष स ह ळ क्ष ज्ञ".w_split,
+        consonants: "क ख ग घ ङ च छ ज झ ञ ट ठ ड ढ ण त थ द ध न प फ ब भ म य र ल व श ष स ह ळ क्ष ज्ञ".split(/\s/),
 
         # Numbers and punctuation
-        symbols: "० १ २ ३ ४ ५ ६ ७ ८ ९ ॐ ऽ । ॥".w_split,
+        symbols: "० १ २ ३ ४ ५ ६ ७ ८ ९ ॐ ऽ । ॥".split(/\s/),
 
         # Zero-width joiner. This is used to separate a consonant cluster
         # and avoid a complex ligature.
@@ -76,12 +75,12 @@ module Sanscript
 
         # Accent combined with anusvara and and visarga. For compatibility
         # with ITRANS, which allows the reverse of these four.
-        combo_accent: "ः॑ ः॒ ं॑ ं॒".w_split,
+        combo_accent: "ः॑ ः॒ ं॑ ं॒".split(/\s/),
 
         candra: ["ॅ"],
 
         # Non-Sanskrit consonants
-        other: "क़ ख़ ग़ ज़ ड़ ढ़ फ़ य़ ऱ".w_split,
+        other: "क़ ख़ ग़ ज़ ड़ ढ़ फ़ य़ ऱ".split(/\s/),
       },
 
       # Gujarati
@@ -89,12 +88,12 @@ module Sanscript
       # Sanskrit-complete.
       #
       gujarati: {
-        vowels: "અ આ ઇ ઈ ઉ ઊ ઋ ૠ ઌ ૡ  એ ઐ  ઓ ઔ".w_split,
-        vowel_marks: "ા િ ી ુ ૂ ૃ ૄ ૢ ૣ  ે ૈ  ો ૌ".w_split,
-        other_marks: "ં ઃ ઁ".w_split,
+        vowels: "અ આ ઇ ઈ ઉ ઊ ઋ ૠ ઌ ૡ  એ ઐ  ઓ ઔ".split(/\s/),
+        vowel_marks: "ા િ ી ુ ૂ ૃ ૄ ૢ ૣ  ે ૈ  ો ૌ".split(/\s/),
+        other_marks: "ં ઃ ઁ".split(/\s/),
         virama: ["્"],
-        consonants: "ક ખ ગ ઘ ઙ ચ છ જ ઝ ઞ ટ ઠ ડ ઢ ણ ત થ દ ધ ન પ ફ બ ભ મ ય ર લ વ શ ષ સ હ ળ ક્ષ જ્ઞ".w_split,
-        symbols: "૦ ૧ ૨ ૩ ૪ ૫ ૬ ૭ ૮ ૯ ૐ ઽ ૤ ૥".w_split,
+        consonants: "ક ખ ગ ઘ ઙ ચ છ જ ઝ ઞ ટ ઠ ડ ઢ ણ ત થ દ ધ ન પ ફ બ ભ મ ય ર લ વ શ ષ સ હ ળ ક્ષ જ્ઞ".split(/\s/),
+        symbols: "૦ ૧ ૨ ૩ ૪ ૫ ૬ ૭ ૮ ૯ ૐ ઽ ૤ ૥".split(/\s/),
         candra: ["ૅ"],
       },
 
@@ -103,13 +102,13 @@ module Sanscript
       # Missing R/RR/lR/lRR
       #
       gurmukhi: {
-        vowels: "ਅ ਆ ਇ ਈ ਉ ਊ      ਏ ਐ  ਓ ਔ".w_split,
-        vowel_marks: "ਾ ਿ ੀ ੁ ੂ      ੇ ੈ  ੋ ੌ".w_split,
-        other_marks: "ਂ ਃ ਁ".w_split,
+        vowels: "ਅ ਆ ਇ ਈ ਉ ਊ      ਏ ਐ  ਓ ਔ".split(/\s/),
+        vowel_marks: "ਾ ਿ ੀ ੁ ੂ      ੇ ੈ  ੋ ੌ".split(/\s/),
+        other_marks: "ਂ ਃ ਁ".split(/\s/),
         virama: ["੍"],
-        consonants: "ਕ ਖ ਗ ਘ ਙ ਚ ਛ ਜ ਝ ਞ ਟ ਠ ਡ ਢ ਣ ਤ ਥ ਦ ਧ ਨ ਪ ਫ ਬ ਭ ਮ ਯ ਰ ਲ ਵ ਸ਼ ਸ਼ ਸ ਹ ਲ਼ ਕ੍ਸ਼ ਜ੍ਞ".w_split,
-        symbols: "੦ ੧ ੨ ੩ ੪ ੫ ੬ ੭ ੮ ੯ ॐ ऽ । ॥".w_split,
-        other: " ਖ ਗ ਜ ਡ  ਫ  ".w_split,
+        consonants: "ਕ ਖ ਗ ਘ ਙ ਚ ਛ ਜ ਝ ਞ ਟ ਠ ਡ ਢ ਣ ਤ ਥ ਦ ਧ ਨ ਪ ਫ ਬ ਭ ਮ ਯ ਰ ਲ ਵ ਸ਼ ਸ਼ ਸ ਹ ਲ਼ ਕ੍ਸ਼ ਜ੍ਞ".split(/\s/),
+        symbols: "੦ ੧ ੨ ੩ ੪ ੫ ੬ ੭ ੮ ੯ ॐ ऽ । ॥".split(/\s/),
+        other: " ਖ ਗ ਜ ਡ  ਫ  ".split(/\s/),
       },
 
       # Kannada
@@ -117,13 +116,13 @@ module Sanscript
       # Sanskrit-complete.
       #
       kannada: {
-        vowels: "ಅ ಆ ಇ ಈ ಉ ಊ ಋ ೠ ಌ ೡ ಎ ಏ ಐ ಒ ಓ ಔ".w_split,
-        vowel_marks: "ಾ ಿ ೀ ು ೂ ೃ ೄ ೢ ೣ ೆ ೇ ೈ ೊ ೋ ೌ".w_split,
-        other_marks: "ಂ ಃ ँ".w_split,
+        vowels: "ಅ ಆ ಇ ಈ ಉ ಊ ಋ ೠ ಌ ೡ ಎ ಏ ಐ ಒ ಓ ಔ".split(/\s/),
+        vowel_marks: "ಾ ಿ ೀ ು ೂ ೃ ೄ ೢ ೣ ೆ ೇ ೈ ೊ ೋ ೌ".split(/\s/),
+        other_marks: "ಂ ಃ ँ".split(/\s/),
         virama: ["್"],
-        consonants: "ಕ ಖ ಗ ಘ ಙ ಚ ಛ ಜ ಝ ಞ ಟ ಠ ಡ ಢ ಣ ತ ಥ ದ ಧ ನ ಪ ಫ ಬ ಭ ಮ ಯ ರ ಲ ವ ಶ ಷ ಸ ಹ ಳ ಕ್ಷ ಜ್ಞ".w_split,
-        symbols: "೦ ೧ ೨ ೩ ೪ ೫ ೬ ೭ ೮ ೯ ಓಂ ಽ । ॥".w_split,
-        other: "      ಫ  ಱ".w_split,
+        consonants: "ಕ ಖ ಗ ಘ ಙ ಚ ಛ ಜ ಝ ಞ ಟ ಠ ಡ ಢ ಣ ತ ಥ ದ ಧ ನ ಪ ಫ ಬ ಭ ಮ ಯ ರ ಲ ವ ಶ ಷ ಸ ಹ ಳ ಕ್ಷ ಜ್ಞ".split(/\s/),
+        symbols: "೦ ೧ ೨ ೩ ೪ ೫ ೬ ೭ ೮ ೯ ಓಂ ಽ । ॥".split(/\s/),
+        other: "      ಫ  ಱ".split(/\s/),
       },
 
       # Malayalam
@@ -131,13 +130,13 @@ module Sanscript
       # Sanskrit-complete.
       #
       malayalam: {
-        vowels: "അ ആ ഇ ഈ ഉ ഊ ഋ ൠ ഌ ൡ എ ഏ ഐ ഒ ഓ ഔ".w_split,
-        vowel_marks: "ാ ി ീ ു ൂ ൃ ൄ ൢ ൣ െ േ ൈ ൊ ോ ൌ".w_split,
-        other_marks: "ം ഃ ँ".w_split,
+        vowels: "അ ആ ഇ ഈ ഉ ഊ ഋ ൠ ഌ ൡ എ ഏ ഐ ഒ ഓ ഔ".split(/\s/),
+        vowel_marks: "ാ ി ീ ു ൂ ൃ ൄ ൢ ൣ െ േ ൈ ൊ ോ ൌ".split(/\s/),
+        other_marks: "ം ഃ ँ".split(/\s/),
         virama: ["്"],
-        consonants: "ക ഖ ഗ ഘ ങ ച ഛ ജ ഝ ഞ ട ഠ ഡ ഢ ണ ത ഥ ദ ധ ന പ ഫ ബ ഭ മ യ ര ല വ ശ ഷ സ ഹ ള ക്ഷ ജ്ഞ".w_split,
-        symbols: "൦ ൧ ൨ ൩ ൪ ൫ ൬ ൭ ൮ ൯ ഓം ഽ । ॥".w_split,
-        other: "        റ".w_split,
+        consonants: "ക ഖ ഗ ഘ ങ ച ഛ ജ ഝ ഞ ട ഠ ഡ ഢ ണ ത ഥ ദ ധ ന പ ഫ ബ ഭ മ യ ര ല വ ശ ഷ സ ഹ ള ക്ഷ ജ്ഞ".split(/\s/),
+        symbols: "൦ ൧ ൨ ൩ ൪ ൫ ൬ ൭ ൮ ൯ ഓം ഽ । ॥".split(/\s/),
+        other: "        റ".split(/\s/),
       },
 
       # Oriya
@@ -145,13 +144,13 @@ module Sanscript
       # Sanskrit-complete.
       #
       oriya: {
-        vowels: "ଅ ଆ ଇ ଈ ଉ ଊ ଋ ୠ ଌ ୡ  ଏ ଐ  ଓ ଔ".w_split,
-        vowel_marks: "ା ି ୀ ୁ ୂ ୃ ୄ ୢ ୣ  େ ୈ  ୋ ୌ".w_split,
-        other_marks: "ଂ ଃ ଁ".w_split,
+        vowels: "ଅ ଆ ଇ ଈ ଉ ଊ ଋ ୠ ଌ ୡ  ଏ ଐ  ଓ ଔ".split(/\s/),
+        vowel_marks: "ା ି ୀ ୁ ୂ ୃ ୄ ୢ ୣ  େ ୈ  ୋ ୌ".split(/\s/),
+        other_marks: "ଂ ଃ ଁ".split(/\s/),
         virama: ["୍"],
-        consonants: "କ ଖ ଗ ଘ ଙ ଚ ଛ ଜ ଝ ଞ ଟ ଠ ଡ ଢ ଣ ତ ଥ ଦ ଧ ନ ପ ଫ ବ ଭ ମ ଯ ର ଲ ଵ ଶ ଷ ସ ହ ଳ କ୍ଷ ଜ୍ଞ".w_split,
-        symbols: "୦ ୧ ୨ ୩ ୪ ୫ ୬ ୭ ୮ ୯ ଓଂ ଽ । ॥".w_split,
-        other: "    ଡ ଢ  ଯ ".w_split,
+        consonants: "କ ଖ ଗ ଘ ଙ ଚ ଛ ଜ ଝ ଞ ଟ ଠ ଡ ଢ ଣ ତ ଥ ଦ ଧ ନ ପ ଫ ବ ଭ ମ ଯ ର ଲ ଵ ଶ ଷ ସ ହ ଳ କ୍ଷ ଜ୍ଞ".split(/\s/),
+        symbols: "୦ ୧ ୨ ୩ ୪ ୫ ୬ ୭ ୮ ୯ ଓଂ ଽ । ॥".split(/\s/),
+        other: "    ଡ ଢ  ଯ ".split(/\s/),
       },
 
       # Tamil
@@ -160,13 +159,13 @@ module Sanscript
       # The most incomplete of the Sanskrit schemes here.
       #
       tamil: {
-        vowels: "அ ஆ இ ஈ உ ஊ     எ ஏ ஐ ஒ ஓ ஔ".w_split,
-        vowel_marks: "ா ி ீ ு ூ     ெ ே ை ொ ோ ௌ".w_split,
-        other_marks: "ஂ ஃ ".w_split,
+        vowels: "அ ஆ இ ஈ உ ஊ     எ ஏ ஐ ஒ ஓ ஔ".split(/\s/),
+        vowel_marks: "ா ி ீ ு ூ     ெ ே ை ொ ோ ௌ".split(/\s/),
+        other_marks: "ஂ ஃ ".split(/\s/),
         virama: ["்"],
-        consonants: "க க க க ங ச ச ஜ ச ஞ ட ட ட ட ண த த த த ந ப ப ப ப ம ய ர ல வ ஶ ஷ ஸ ஹ ள க்ஷ ஜ்ஞ".w_split,
-        symbols: "௦ ௧ ௨ ௩ ௪ ௫ ௬ ௭ ௮ ௯ ௐ ऽ । ॥".w_split,
-        other: "        ற".w_split,
+        consonants: "க க க க ங ச ச ஜ ச ஞ ட ட ட ட ண த த த த ந ப ப ப ப ம ய ர ல வ ஶ ஷ ஸ ஹ ள க்ஷ ஜ்ஞ".split(/\s/),
+        symbols: "௦ ௧ ௨ ௩ ௪ ௫ ௬ ௭ ௮ ௯ ௐ ऽ । ॥".split(/\s/),
+        other: "        ற".split(/\s/),
       },
 
       # Telugu
@@ -174,13 +173,13 @@ module Sanscript
       # Sanskrit-complete.
       #
       telugu: {
-        vowels: "అ ఆ ఇ ఈ ఉ ఊ ఋ ౠ ఌ ౡ ఎ ఏ ఐ ఒ ఓ ఔ".w_split,
-        vowel_marks: "ా ి ీ ు ూ ృ ౄ ౢ ౣ ె ే ై ొ ో ౌ".w_split,
-        other_marks: "ం ః ఁ".w_split,
+        vowels: "అ ఆ ఇ ఈ ఉ ఊ ఋ ౠ ఌ ౡ ఎ ఏ ఐ ఒ ఓ ఔ".split(/\s/),
+        vowel_marks: "ా ి ీ ు ూ ృ ౄ ౢ ౣ ె ే ై ొ ో ౌ".split(/\s/),
+        other_marks: "ం ః ఁ".split(/\s/),
         virama: ["్"],
-        consonants: "క ఖ గ ఘ ఙ చ ఛ జ ఝ ఞ ట ఠ డ ఢ ణ త థ ద ధ న ప ఫ బ భ మ య ర ల వ శ ష స హ ళ క్ష జ్ఞ".w_split,
-        symbols: "౦ ౧ ౨ ౩ ౪ ౫ ౬ ౭ ౮ ౯ ఓం ఽ । ॥".w_split,
-        other: "        ఱ".w_split,
+        consonants: "క ఖ గ ఘ ఙ చ ఛ జ ఝ ఞ ట ఠ డ ఢ ణ త థ ద ధ న ప ఫ బ భ మ య ర ల వ శ ష స హ ళ క్ష జ్ఞ".split(/\s/),
+        symbols: "౦ ౧ ౨ ౩ ౪ ౫ ౬ ౭ ౮ ౯ ఓం ఽ । ॥".split(/\s/),
+        other: "        ఱ".split(/\s/),
       },
 
       # International Alphabet of Sanskrit Transliteration
@@ -188,11 +187,11 @@ module Sanscript
       # The most "professional" Sanskrit romanization scheme.
       #
       iast: {
-        vowels: "a ā i ī u ū ṛ ṝ ḷ ḹ  e ai  o au".w_split,
+        vowels: "a ā i ī u ū ṛ ṝ ḷ ḹ  e ai  o au".split(/\s/),
         other_marks: ["ṃ", "ḥ", "~"],
         virama: [""],
-        consonants: "k kh g gh ṅ c ch j jh ñ ṭ ṭh ḍ ḍh ṇ t th d dh n p ph b bh m y r l v ś ṣ s h ḻ kṣ jñ".w_split,
-        symbols: "0 1 2 3 4 5 6 7 8 9 oṃ ' | ||".w_split,
+        consonants: "k kh g gh ṅ c ch j jh ñ ṭ ṭh ḍ ḍh ṇ t th d dh n p ph b bh m y r l v ś ṣ s h ḻ kṣ jñ".split(/\s/),
+        symbols: "0 1 2 3 4 5 6 7 8 9 oṃ ' | ||".split(/\s/),
       },
 
       # ITRANS
@@ -204,17 +203,17 @@ module Sanscript
       # '_' is a "null" letter, which allows adjacent vowels.
       #
       itrans: {
-        vowels: "a A i I u U RRi RRI LLi LLI  e ai  o au".w_split,
+        vowels: "a A i I u U RRi RRI LLi LLI  e ai  o au".split(/\s/),
         other_marks: ["M", "H", ".N"],
         virama: [""],
-        consonants: "k kh g gh ~N ch Ch j jh ~n T Th D Dh N t th d dh n p ph b bh m y r l v sh Sh s h L kSh j~n".w_split,
-        symbols: "0 1 2 3 4 5 6 7 8 9 OM .a | ||".w_split,
+        consonants: "k kh g gh ~N ch Ch j jh ~n T Th D Dh N t th d dh n p ph b bh m y r l v sh Sh s h L kSh j~n".split(/\s/),
+        symbols: "0 1 2 3 4 5 6 7 8 9 OM .a | ||".split(/\s/),
         candra: [".c"],
         zwj: ["{}"],
         skip: ["_"],
         accent: ["\\'", "\\_"],
-        combo_accent: "\\'H \\_H \\'M \\_M".w_split,
-        other: "q K G z .D .Dh f Y R".w_split,
+        combo_accent: "\\'H \\_H \\'M \\_M".split(/\s/),
+        other: "q K G z .D .Dh f Y R".split(/\s/),
       },
 
       # Harvard-Kyoto
@@ -222,11 +221,11 @@ module Sanscript
       # A simple 1:1 mapping.
       #
       hk: {
-        vowels: "a A i I u U R RR lR lRR  e ai  o au".w_split,
-        other_marks: "M H ~".w_split,
+        vowels: "a A i I u U R RR lR lRR  e ai  o au".split(/\s/),
+        other_marks: "M H ~".split(/\s/),
         virama: [""],
-        consonants: "k kh g gh G c ch j jh J T Th D Dh N t th d dh n p ph b bh m y r l v z S s h L kS jJ".w_split,
-        symbols: "0 1 2 3 4 5 6 7 8 9 OM ' | ||".w_split,
+        consonants: "k kh g gh G c ch j jh J T Th D Dh N t th d dh n p ph b bh m y r l v z S s h L kS jJ".split(/\s/),
+        symbols: "0 1 2 3 4 5 6 7 8 9 OM ' | ||".split(/\s/),
       },
 
       # National Library at Kolkata
@@ -243,11 +242,11 @@ module Sanscript
       # scheme in use today and is especially suited to computer processing.
       #
       slp1: {
-        vowels: "a A i I u U f F x X  e E  o O".w_split,
-        other_marks: "M H ~".w_split,
+        vowels: "a A i I u U f F x X  e E  o O".split(/\s/),
+        other_marks: "M H ~".split(/\s/),
         virama: [""],
-        consonants: "k K g G N c C j J Y w W q Q R t T d D n p P b B m y r l v S z s h L kz jY".w_split,
-        symbols: "0 1 2 3 4 5 6 7 8 9 oM ' | ||".w_split,
+        consonants: "k K g G N c C j J Y w W q Q R t T d D n p P b B m y r l v S z s h L kz jY".split(/\s/),
+        symbols: "0 1 2 3 4 5 6 7 8 9 oM ' | ||".split(/\s/),
       },
 
       # Velthuis
@@ -255,11 +254,11 @@ module Sanscript
       # A case-insensitive Sanskrit encoding.
       #
       velthuis: {
-        vowels: "a aa i ii u uu .r .rr .li .ll  e ai  o au".w_split,
-        other_marks: ".m .h ".w_split,
+        vowels: "a aa i ii u uu .r .rr .li .ll  e ai  o au".split(/\s/),
+        other_marks: ".m .h ".split(/\s/),
         virama: [""],
-        consonants: 'k kh g gh "n c ch j jh ~n .t .th .d .dh .n t th d dh n p ph b bh m y r l v ~s .s s h L k.s j~n'.w_split,
-        symbols: "0 1 2 3 4 5 6 7 8 9 o.m ' | ||".w_split,
+        consonants: 'k kh g gh "n c ch j jh ~n .t .th .d .dh .n t th d dh n p ph b bh m y r l v ~s .s s h L k.s j~n'.split(/\s/),
+        symbols: "0 1 2 3 4 5 6 7 8 9 o.m ' | ||".split(/\s/),
       },
 
       # WX
@@ -267,11 +266,11 @@ module Sanscript
       # As terse as SLP1.
       #
       wx: {
-        vowels: "a A i I u U q Q L   e E  o O".w_split,
-        other_marks: "M H z".w_split,
+        vowels: "a A i I u U q Q L   e E  o O".split(/\s/),
+        other_marks: "M H z".split(/\s/),
         virama: [""],
-        consonants: "k K g G f c C j J F t T d D N w W x X n p P b B m y r l v S R s h  kR jF".w_split,
-        symbols: "0 1 2 3 4 5 6 7 8 9 oM ' | ||".w_split,
+        consonants: "k K g G f c C j J F t T d D N w W x X n p P b B m y r l v S R s h  kR jF".split(/\s/),
+        symbols: "0 1 2 3 4 5 6 7 8 9 oM ' | ||".split(/\s/),
       },
     }
 
@@ -307,7 +306,7 @@ module Sanscript
         "\\_" => ["\\`"],
         "\\_H" => ["\\`H"],
         "\\'M" => ["\\'.m", "\\'.n"],
-        "\\_M" => "\\_.m \\_.n \\`M \\`.m \\`.n".w_split,
+        "\\_M" => "\\_.m \\_.n \\`M \\`.m \\`.n".split(/\s/),
         ".a" => ["~"],
         "|" => ["."],
         "||" => [".."],

data/lib/sanscript/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 module Sanscript
   # The version number
-  VERSION = "0.4.3"
+  VERSION = "0.5.0"
 end

data/sanscript.gemspec

@@ -29,5 +29,5 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "benchmark-ips", "~> 2.6"
   spec.add_development_dependency "yard", "~> 0.9"
 
-  spec.add_runtime_dependency "ice_nine", "~> 0.11"
+  spec.add_runtime_dependency "ragabash", "~> 0.1"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: sanscript
 version: !ruby/object:Gem::Version
-  version: 0.4.3
+  version: 0.5.0
 platform: ruby
 authors:
 - Tim Bellefleur
@@ -109,19 +109,19 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0.9'
 - !ruby/object:Gem::Dependency
-  name: ice_nine
+  name: ragabash
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.11'
+        version: '0.1'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.11'
+        version: '0.1'
 description: 
 email:
 - nomoon@phoebus.ca
@@ -146,7 +146,7 @@ files:
 - lib/sanscript/detect.rb
 - lib/sanscript/detect/ruby24.rb
 - lib/sanscript/detect/ruby2x.rb
-- lib/sanscript/refinements.rb
+- lib/sanscript/exceptions.rb
 - lib/sanscript/transliterate.rb
 - lib/sanscript/transliterate/schemes.rb
 - lib/sanscript/version.rb

data/lib/sanscript/refinements.rb

@@ -1,95 +0,0 @@
-# frozen_string_literal: true
-require "ice_nine"
-
-module Sanscript
-  # A set of helpful refinements for duplication and deep freezing.
-  module Refinements
-    refine Object do
-      def deep_dup
-        dup
-      rescue TypeError
-        self
-      end
-
-      def deep_freeze
-        IceNine.deep_freeze(self)
-      end
-    end
-
-    refine NilClass do
-      def deep_dup
-        self
-      end
-    end
-
-    refine FalseClass do
-      def deep_dup
-        self
-      end
-    end
-
-    refine TrueClass do
-      def deep_dup
-        self
-      end
-    end
-
-    refine Symbol do
-      def deep_dup
-        self
-      end
-    end
-
-    refine Numeric do
-      def deep_dup
-        self
-      end
-    end
-
-    # Necessary to re-override Numeric
-    require "bigdecimal"
-    refine BigDecimal do
-      def deep_dup
-        dup
-      end
-    end
-
-    refine String do
-      def w_split
-        split(/\s/)
-      end
-    end
-
-    refine Array do
-      def deep_dup
-        map { |value| value.deep_dup } # rubocop:disable Style/SymbolProc
-      end
-    end
-
-    refine Hash do
-      def deep_dup
-        hash = dup
-        each_pair do |key, value|
-          if ::String === key # rubocop:disable Style/CaseEquality
-            hash[key] = value.deep_dup
-          else
-            hash.delete(key)
-            hash[key.deep_dup] = value.deep_dup
-          end
-        end
-        hash
-      end
-    end
-
-    refine Set do
-      def deep_dup
-        set_a = to_a
-        set_a.map! do |val|
-          next val if ::String === val # rubocop:disable Style/CaseEquality
-          val.deep_dup
-        end
-        self.class[set_a]
-      end
-    end
-  end
-end