Ukrainian: Provide convenience mappings

Author: tindzk

README.md

@@ -72,11 +72,28 @@ The second change to National 2010 is that we try to restore soft signs and apos
 
 This feature is experimental and can be disabled by setting `apostrophes` to `false`.
 
+#### Convenience mappings
+Another modification was to provide the following mappings:
+
+* c → ц
+* q → щ
+* w → ш
+* x → х
+
+Note that these mappings are phonetically inaccurate. However, using them still has a few advantages:
+
+* Every letter of the Latin alphabet is covered
+* When the user types *ch*, we can map the first letter to *ц*, then replace it by *ч*
+* *w* has a similar shape to *ш*
+* *q* and *w* are located next to each other on the English keyboard, *щ* is therefore easy to find
+* *x* has the same shape as its Cyrillic counterpart
+
 ### Credits
 The rules and examples were adapted from the following libraries:
 
 * [translit-english-ukrainian](https://github.com/MarkovSergii/translit-english-ukrainian)
 * [translit-ua](https://github.com/dchaplinsky/translit-ua)
+* [translit.net](http://translit.net/)
 
 ## Licence
 translit-scala is licensed under the terms of the Apache v2.0 licence.

shared/src/main/scala/translit/Ukrainian.scala

@@ -12,6 +12,7 @@ object Ukrainian extends Language {
     'g' -> 'ґ',
     'h' -> 'г',
     'i' -> 'і',
+    'j' -> 'й',
     'k' -> 'к',
     'l' -> 'л',
     'm' -> 'м',
@@ -24,8 +25,14 @@ object Ukrainian extends Language {
     'u' -> 'у',
     'v' -> 'в',
     'y' -> 'и',
-    'j' -> 'й',
-    'z' -> 'з'
+    'z' -> 'з',
+
+    // Mappings for more convenient typing. Allows us to cover every letter of
+    // the Latin alphabet
+    'c' -> 'ц',
+    'q' -> 'щ',
+    'w' -> 'ш',
+    'x' -> 'х'
   )
 
   val biGrams = Map(
@@ -117,10 +124,6 @@ object Ukrainian extends Language {
       val result = if (text(ofs - 2).isUpper) cyrillic.toUpper else cyrillic
 
       (0, result)
-    } else if ('c' == text(ofs - 1).toLower) {
-      // Replace Latin `c` to avoid confusion as its Cyrillic counterpart has a
-      // different byte code
-      (0, 'ø')
     } else {
       (0, text(ofs - 1))
     }

shared/src/test/scala/translit/UkrainianSpec.scala

@@ -246,14 +246,14 @@ class UkrainianSpec extends FunSuite {
   }
 
   test("s vs c") {
-    assert(Ukrainian.latinToCyrillic("vlacnym") == "влаøним")
+    assert(Ukrainian.latinToCyrillic("vlacnym") == "влацним")
     assert(Ukrainian.latinToCyrillic("vlasnym") == "власним")
   }
 
   test("Offsets") {
     assert(Ukrainian.latinToCyrillicOfs("shch", 0) == (0, 'с'))
     assert(Ukrainian.latinToCyrillicOfs("shch", 1) == (-1, 'ш'))
-    assert(Ukrainian.latinToCyrillicOfs("shch", 2) == (0, 'ø'))
+    assert(Ukrainian.latinToCyrillicOfs("shch", 2) == (0, 'ц'))
     assert(Ukrainian.latinToCyrillicOfs("shch", 3) == (-2, 'щ'))
     assert(Ukrainian.latinToCyrillicOfs("yeshch", 5) == (-2, 'щ'))
 
@@ -273,4 +273,9 @@ class UkrainianSpec extends FunSuite {
 
     assert(Ukrainian.latinToCyrillicOfs("zgh", 2) == (-1, 'г'))
   }
+
+  test("Convenience mappings") {
+    assert(Ukrainian.latinToCyrillic("Puzata Xata") == "Пузата Хата")
+    assert(Ukrainian.latinToCyrillic("cqwx") == "цщшх")
+  }
 }