[1.47.09]

Fix: lookup in *_list occasionally find the wrong word.
Languages changes: hi, ne, sl.

git-svn-id: https://espeak.svn.sourceforge.net/svnroot/espeak/trunk@351 d46cf337-b52f-0410-862d-fd96e6ae7743

src/dictionary.cpp

@@ -2980,8 +2980,9 @@ int TransposeAlphabet(Translator *tr, char *text)
 			*p2++ = (acc << (8-bits));
 		}
 		*p2 = 0;
-		strcpy(text, buf);
-		return((p2 - buf) | 0x40);  // bit 6 indicates compressed characters
+		ix = p2 - buf;
+		memcpy(text, buf, ix);
+		return(ix | 0x40);  // bit 6 indicates compressed characters
 	}
 	else
 	{

src/extras.cpp

@@ -1684,7 +1684,7 @@ void ConvertToUtf8()
 
 	while(!feof(f_in))
 	{
-		c = fgetc(f_in);
+		c = fgetc(f_in) & 0xff;
 		if(c >= 0xa0)
 			c = translator->charset_a0[c-0xa0];
 
@@ -1696,7 +1696,7 @@ void ConvertToUtf8()
 
 	wxLogStatus(_T("Written to: ")+fname+_T("_1"));
 
-}  // end of ConvertToItf8
+}  // end of ConvertToUtf8
 
 //******************************************************************************************************
 

src/readclause.cpp

@@ -92,6 +92,7 @@ static const unsigned short punct_chars[] = {',','.','?','!',':',';',
   0x061f,  // Arabic ?
   0x06d4,  // Arabic .
 
+  0x0df4,  // Singhalese Kunddaliya
   0x0f0d,  // Tibet Shad
   0x0f0e,
 
@@ -142,6 +143,7 @@ static const unsigned int punct_attributes [] = { 0,
   CLAUSE_QUESTION,   // Arabic question mark
   CLAUSE_PERIOD,     // Arabic full stop
 
+  CLAUSE_PERIOD+0x8000,     // Singhalese period
   CLAUSE_PERIOD+0x8000,     // Tibet period
   CLAUSE_PARAGRAPH,
 

src/synthdata.cpp

@@ -35,8 +35,8 @@
 #include "translate.h"
 #include "wave.h"
 
-const char *version_string = "1.47.08  26.Apr.13";
-const int version_phdata  = 0x014701;
+const char *version_string = "1.47.09  29.Apr.13";
+const int version_phdata  = 0x014709;
 
 int option_device_number = -1;
 FILE *f_logespeak = NULL;

src/tr_languages.cpp

@@ -79,7 +79,7 @@ ALPHABET alphabets [] = {
     {"_ar",    OFFSET_ARABIC,   0x600, 0x6ff,  0, 0},
     {"_dv",    OFFSET_THAANA,   0x780, 0x7bf,  0, 0},
     {"_hi",    OFFSET_DEVANAGARI, 0x900, 0x97f,L('h','i'), AL_WORDS},
-    {"_bn",    OFFSET_BENGALI,  0x0980, 0x9ff, L('b','n'), 0},
+    {"_bn",    OFFSET_BENGALI,  0x0980, 0x9ff, L('b','n'), AL_WORDS},
     {"_gur",   OFFSET_GURMUKHI, 0xa00, 0xa7f,  L('p','a'), AL_WORDS},
     {"_gu",    OFFSET_GUJARATI, 0xa80, 0xaff,  0, 0},
     {"_or",    OFFSET_ORIYA,    0xb00, 0xb7f,  0, 0},
@@ -87,7 +87,7 @@ ALPHABET alphabets [] = {
     {"_te",    OFFSET_TELUGU,   0xc00, 0xc7f,  L('t','e'), 0},
     {"_kn",    OFFSET_KANNADA,  0xc80, 0xcff,  L('k','n'), AL_WORDS},
     {"_ml",    OFFSET_MALAYALAM,0xd00, 0xd7f,  L('m','l'), AL_WORDS},
-    {"_si",    OFFSET_SINHALA,  0xd80, 0xdff,  0, 0},
+    {"_si",    OFFSET_SINHALA,  0xd80, 0xdff,  L('s','i'), AL_WORDS},
     {"_th",    OFFSET_THAI,     0xe00, 0xe7f,  0, 0},
     {"_lo",    OFFSET_LAO,      0xe80, 0xeff,  0, 0},
     {"_ti",    OFFSET_TIBET,    0xf00, 0xfff,  0, 0},