sanscript 0.4.1 → 0.4.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: a3a0e34eb01c4a5d8e016b323a192fb6de6f82e8
-  data.tar.gz: db4799dc5bf50b86724b19ff139105f307706720
+  metadata.gz: 978f081a49e46e4cade8a7cdef95ebdb89f7daac
+  data.tar.gz: e46caf2df596e745398a6a5ac86d2c11ed0c666d
 SHA512:
-  metadata.gz: 4e13bc3d149f056346bd61ebcfd4abc0798af91998b9f89440b780f6c1ee9f0e79319f157d60e0831a1521e95ffecd0fdc4edb1bf6010da0c5f0a0b8cf36a618
-  data.tar.gz: 4a4f770e5dc1d8c637814b5fb21a5fbbb14c0512d228235d7b8f5cf02b94f9b27112e79758e63306f182d74016dc51cae1b2a0b37ad6d68bab3da3ca83a38af2
+  metadata.gz: e0f01c0322755e57c5690799660e810cc7d85271c5b6ef185ce21b13f516c396f1ae8e090529ecbfa8fd8a9bfcce8519f15d4d3291188d6bc1f83279c0b59071
+  data.tar.gz: f87954bc573383f2ddf530274ef69dbe32e67ab49d3f49e6db90790abafef51e51c8596c22d044ae40b4907921c38fc26182342f0c96008492aec938e56afbc9

data/lib/sanscript/transliterate.rb

@@ -240,8 +240,8 @@ module Sanscript
           token_buffer << data.slice!(0, map[:max_token_length] - token_buffer.length)
 
           # Match all token substrings to our map.
-          (0...map[:max_token_length]).each do |j|
-            token = token_buffer[0, map[:max_token_length] - j]
+          map[:max_token_length].downto(1) do |j|
+            token = token_buffer[0, j]
 
             if !control_char && token == "##"
               transliteration_enabled = !transliteration_enabled
@@ -280,17 +280,15 @@ module Sanscript
                 end
                 had_consonant = map[:consonants].key?(token)
               end
-              token_buffer.slice!(0, map[:max_token_length] - j)
+              token_buffer.slice!(0, j)
               break
-            elsif j == map[:max_token_length] - 1
+            elsif j == 1 # Last iteration
               if had_consonant
                 had_consonant = false
                 buf << map[:virama] unless options[:syncope]
               end
               buf << token
               token_buffer.slice!(0, 1)
-              # 'break' is redundant here, "j == ..." is true only on
-              # the last iteration.
             end
           end
         end
@@ -313,6 +311,10 @@ module Sanscript
         until data.empty?
           token = data.slice(0, 2)
           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)
             next
@@ -323,6 +325,10 @@ module Sanscript
             data.slice!(0, 2)
             next
           elsif transliteration_enabled && token == "{#"
+            if had_roman_consonant
+              buf << "a"
+              had_roman_consonant = false
+            end
             transliteration_enabled = false
             control_char = true
             buf << token

data/lib/sanscript/transliterate/schemes.rb

@@ -25,7 +25,7 @@ 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,
+        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,
         virama: ["্"],
@@ -107,7 +107,7 @@ module Sanscript
         vowel_marks: "ਾ ਿ ੀ ੁ ੂ      ੇ ੈ  ੋ ੌ".w_split,
         other_marks: "ਂ ਃ ਁ".w_split,
         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,
+        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,
       },
@@ -258,7 +258,7 @@ module Sanscript
         vowels: "a aa i ii u uu .r .rr .li .ll  e ai  o au".w_split,
         other_marks: ".m .h ".w_split,
         virama: [""],
-        consonants: 'k kh g gh "n c ch j jh ~n .t .th .d .d .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,
+        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,
       },
 

data/lib/sanscript/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 module Sanscript
   # The version number
-  VERSION = "0.4.1"
+  VERSION = "0.4.3"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: sanscript
 version: !ruby/object:Gem::Version
-  version: 0.4.1
+  version: 0.4.3
 platform: ruby
 authors:
 - Tim Bellefleur
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-07-22 00:00:00.000000000 Z
+date: 2016-07-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler