ru: document the special characters

dictsource/ru_rules

@@ -3,13 +3,13 @@
 // This file is UTF8 encoded
 
 // Special characters:
-// A  vowel:   а о у ы э  е ё и ю я
-// B  soft consonant:  ь й ч щ
-// C  any consonant:
-// F  consonant, not hard: ??
-// G  voiced: б в г д ж з
-// H  hard consonant:  ъ ж ц ш
-// Y  iotated vowel, softsign:  ь е ё и ю я
+// A  vowel:			а е ё и о у ы э ю я ә ө ұ ү і
+// B  soft consonant:		ь й ч щ
+// C  any consonant:		б в г д ж з й к л м н п р с т ф х ц ч ш щ ъ ь қ ң һ
+// F  consonant, not hard:	б в г д з й к л м н п р с т ф х ч щ ь
+// G  voiced:			б в г д ж з
+// H  hard consonant:		ъ ж ц ш
+// Y  iotated vowel, softsign:	ь ю я ё
 
 
 .group а

src/libespeak-ng/tr_languages.c

@@ -373,17 +373,21 @@ static const unsigned int replace_cyrillic_latin[] =
   0x45c, 0x107,
   0 }; // ѓ  ѕ  ќ
 
-static const unsigned char ru_vowels[] = { 0x10, 0x15, 0x31, 0x18, 0x1e, 0x23, 0x2b, 0x2d, 0x2e, 0x2f,  0xb9, 0xc9, 0x91, 0x8f, 0x36, 0 };  // also kazakh
-static const unsigned char ru_consonants[] = { 0x11, 0x12, 0x13, 0x14, 0x16, 0x17, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1f, 0x20, 0x21, 0x22, 0x24, 0x25, 0x26, 0x27, 0x28, 0x29, 0x2a, 0x2c, 0x73, 0x7b, 0x83, 0x9b, 0 };
+static const unsigned char ru_vowels[] = { // (also kazakh) offset by 0x420 -- а е ё и о у ы э ю я ә ө ұ ү і
+	0x10, 0x15, 0x31, 0x18, 0x1e, 0x23, 0x2b, 0x2d, 0x2e, 0x2f,  0xb9, 0xc9, 0x91, 0x8f, 0x36, 0
+};
+static const unsigned char ru_consonants[] = { // б в г д ж з й к л м н п р с т ф х ц ч ш щ ъ ь қ ң һ
+	0x11, 0x12, 0x13, 0x14, 0x16, 0x17, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1f, 0x20, 0x21, 0x22, 0x24, 0x25, 0x26, 0x27, 0x28, 0x29, 0x2a, 0x2c, 0x73, 0x7b, 0x83, 0x9b, 0
+};
 
 static void SetCyrillicLetters(Translator *tr)
 {
 	// character codes offset by 0x420
-	static const char ru_soft[] = { 0x2c, 0x19, 0x27, 0x29, 0 };   // letter group B  [k ts; s;]
-	static const char ru_hard[] = { 0x2a, 0x16, 0x26, 0x28, 0 };   // letter group H  [S Z ts]
-	static const char ru_nothard[] = { 0x11, 0x12, 0x13, 0x14, 0x17, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1f, 0x20, 0x21, 0x22, 0x24, 0x25, 0x27, 0x29, 0x2c, 0 };
-	static const char ru_voiced[] = { 0x11, 0x12, 0x13, 0x14, 0x16, 0x17, 0 };    // letter group G  (voiced obstruents)
-	static const char ru_ivowels[] = { 0x2c, 0x2e, 0x2f, 0x31, 0 };   // letter group Y  (iotated vowels & soft-sign)
+	static const char ru_soft[] = { 0x2c, 0x19, 0x27, 0x29, 0 }; // letter group B  [k ts; s;] -- ь й ч щ
+	static const char ru_hard[] = { 0x2a, 0x16, 0x26, 0x28, 0 }; // letter group H  [S Z ts] -- ъ ж ц ш
+	static const char ru_nothard[] = { 0x11, 0x12, 0x13, 0x14, 0x17, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1f, 0x20, 0x21, 0x22, 0x24, 0x25, 0x27, 0x29, 0x2c, 0 }; // б в г д з й к л м н п р с т ф х ч щ ь
+	static const char ru_voiced[] = { 0x11, 0x12, 0x13, 0x14, 0x16, 0x17, 0 };    // letter group G  (voiced obstruents) -- б в г д ж з
+	static const char ru_ivowels[] = { 0x2c, 0x2e, 0x2f, 0x31, 0 };   // letter group Y  (iotated vowels & soft-sign) -- ь ю я ё
 	tr->encoding = ESPEAKNG_ENCODING_KOI8_R;
 	tr->transpose_min = 0x430;  // convert cyrillic from unicode into range 0x01 to 0x22
 	tr->transpose_max = 0x451;