implement a new iscii (devangari) <-> unicode converter

this time with support for the multi-byte encodings possible
in ISCII

Change-Id: I1dc09e8836676ab614b531e8dc10f91a90b7c4fd

2 files changed, 42 insertions, 41 deletions

diff --git a/sal/qa/rtl/textenc/rtl_tencinfo.cxx b/sal/qa/rtl/textenc/rtl_tencinfo.cxx
index 7d3ade94ae56..70e2f2e13564 100644
--- a/sal/qa/rtl/textenc/rtl_tencinfo.cxx
+++ b/sal/qa/rtl/textenc/rtl_tencinfo.cxx
@@ -509,8 +509,8 @@ namespace
         CPPUNIT_TEST( MimeCharsetFromTextEncoding_BIG5_HKSCS );
         CPPUNIT_TEST( MimeCharsetFromTextEncoding_TIS_620 );
         CPPUNIT_TEST( MimeCharsetFromTextEncoding_KOI8_U );
-#if 0
         CPPUNIT_TEST( MimeCharsetFromTextEncoding_ISCII_DEVANAGARI );
+#if 0
         CPPUNIT_TEST( MimeCharsetFromTextEncoding_JAVA_UTF8 );
 #endif
 
diff --git a/sal/qa/rtl/textenc/rtl_textcvt.cxx b/sal/qa/rtl/textenc/rtl_textcvt.cxx
index 3c8c33e156bb..ba7074f26ec3 100644
--- a/sal/qa/rtl/textenc/rtl_textcvt.cxx
+++ b/sal/qa/rtl/textenc/rtl_textcvt.cxx
@@ -134,12 +134,13 @@ void testSingleByteCharSet(SingleByteCharSet const & rSet) {
                  | RTL_TEXTTOUNICODE_FLAGS_MBUNDEFINED_ERROR
                  | RTL_TEXTTOUNICODE_FLAGS_INVALID_ERROR),
                 &nInfo, &nConverted);
+
+            sal_uInt32 nExpectedInfo = (RTL_TEXTTOUNICODE_INFO_ERROR | RTL_TEXTTOUNICODE_INFO_UNDEFINED);
+
             CPPUNIT_ASSERT_MESSAGE(
                 "failure #9",
                 (nSize == 0
-                 && (nInfo
-                     == (RTL_TEXTTOUNICODE_INFO_ERROR
-                         | RTL_TEXTTOUNICODE_INFO_UNDEFINED))
+                 && (nInfo == nExpectedInfo)
                  && nConverted == 0));
             rtl_destroyTextToUnicodeContext(aConverter, aContext);
             rtl_destroyTextToUnicodeConverter(aConverter);
@@ -1098,41 +1099,6 @@ void Test::testSingleByte() {
                 0x0425,0x0418,0x0419,0x041A,0x041B,0x041C,0x041D,0x041E,
                 0x041F,0x042F,0x0420,0x0421,0x0422,0x0423,0x0416,0x0412,
                 0x042C,0x042B,0x0417,0x0428,0x042D,0x0429,0x0427,0x042A } },
-#if 0
-            { RTL_TEXTENCODING_ISCII_DEVANAGARI,
-              { 0x0000,0x0001,0x0002,0x0003,0x0004,0x0005,0x0006,0x0007,
-                0x0008,0x0009,0x000A,0x000B,0x000C,0x000D,0x000E,0x000F,
-                0x0010,0x0011,0x0012,0x0013,0x0014,0x0015,0x0016,0x0017,
-                0x0018,0x0019,0x001A,0x001B,0x001C,0x001D,0x001E,0x001F,
-                0x0020,0x0021,0x0022,0x0023,0x0024,0x0025,0x0026,0x0027,
-                0x0028,0x0029,0x002A,0x002B,0x002C,0x002D,0x002E,0x002F,
-                0x0030,0x0031,0x0032,0x0033,0x0034,0x0035,0x0036,0x0037,
-                0x0038,0x0039,0x003A,0x003B,0x003C,0x003D,0x003E,0x003F,
-                0x0040,0x0041,0x0042,0x0043,0x0044,0x0045,0x0046,0x0047,
-                0x0048,0x0049,0x004A,0x004B,0x004C,0x004D,0x004E,0x004F,
-                0x0050,0x0051,0x0052,0x0053,0x0054,0x0055,0x0056,0x0057,
-                0x0058,0x0059,0x005A,0x005B,0x005C,0x005D,0x005E,0x005F,
-                0x0060,0x0061,0x0062,0x0063,0x0064,0x0065,0x0066,0x0067,
-                0x0068,0x0069,0x006A,0x006B,0x006C,0x006D,0x006E,0x006F,
-                0x0070,0x0071,0x0072,0x0073,0x0074,0x0075,0x0076,0x0077,
-                0x0078,0x0079,0x007A,0x007B,0x007C,0x007D,0x007E,0x007F,
-                0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,
-                0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,
-                0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,
-                0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,
-                0xFFFF,0x0901,0x0902,0x0903,0x0905,0x0906,0x0907,0x0908,
-                0x0909,0x090A,0x090B,0x090E,0x090F,0x0910,0x090D,0x0912,
-                0x0913,0x0914,0x0911,0x0915,0x0916,0x0917,0x0918,0x0919,
-                0x091A,0x091B,0x091C,0x091D,0x091E,0x091F,0x0920,0x0921,
-                0x0922,0x0923,0x0924,0x0925,0x0926,0x0927,0x0928,0x0929,
-                0x092A,0x092B,0x092C,0x092D,0x092E,0x092F,0x095F,0x0930,
-                0x0931,0x0932,0x0933,0x0934,0x0935,0x0936,0x0937,0x0938,
-                0x0939,0xFFFF,0x093E,0x093F,0x0940,0x0941,0x0942,0x0943,
-                0x0946,0x0947,0x0948,0x0945,0x094A,0x094B,0x094C,0x0949,
-                0x094D,0x093C,0x0964,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,
-                0xFFFF,0x0966,0x0967,0x0968,0x0969,0x096A,0x096B,0x096C,
-                0x096D,0x096E,0x096F,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF } },
-#endif
             { RTL_TEXTENCODING_ADOBE_STANDARD,
               { 0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,
                 0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,0xFFFF,
@@ -2498,6 +2464,43 @@ void Test::testComplex() {
               false,
               true,
               false,
+              RTL_UNICODETOTEXT_FLAGS_UNDEFINED_ERROR },
+            { RTL_TEXTENCODING_ISCII_DEVANAGARI,
+              RTL_CONSTASCII_STRINGPARAM(
+                  "\xD7\xE6\x20\xD4\xCF\xE8\xD6\x20"
+                  "\xC8\xD8\xD1\xE1\x20\xB3\xCA\xDC"
+                  "\xCF\xC4\xDA\xD7\x20\xD8\xDB\xA2"
+                  "\xC4\xDE\x20\xB1\xCF\x20\xCC\xDD"
+                  "\xD7\xD1\xCC\xDA\xC6\x20\xC4\xE5"
+                  "\xC6\xE5\xA2\x20\xB3\xE1\x20\xB3"
+                  "\xBD\xE8\xBD\xCF\xC8\xC6\x20\xB3"
+                  "\xE5\x20\xC9\xBD\xB3\xDA\xCF\x20"
+                  "\xB8\xDD\xB3\xE1\x20\xC3\xE1\x20"
+                  "\xEA"),
+              { 0x0938, 0x094C, 0x0020, 0x0935, 0x0930, 0x094D, 0x0937, 0x0020,
+                0x092A, 0x0939, 0x0932, 0x0947, 0x0020, 0x0915, 0x092C, 0x0940,
+                0x0930, 0x0926, 0x093E, 0x0938, 0x0020, 0x0939, 0x093F, 0x0902,
+                0x0926, 0x0942, 0x0020, 0x0914, 0x0930, 0x0020, 0x092E, 0x0941,
+                0x0938, 0x0932, 0x092E, 0x093E, 0x0928, 0x0020, 0x0926, 0x094B,
+                0x0928, 0x094B, 0x0902, 0x0020, 0x0915, 0x0947, 0x0020, 0x0915,
+                0x091F, 0x094D, 0x091F, 0x0930, 0x092A, 0x0928, 0x0020, 0x0915,
+                0x094B, 0x0020, 0x092B, 0x091F, 0x0915, 0x093E, 0x0930, 0x0020,
+                0x091A, 0x0941, 0x0915, 0x0947, 0x0020, 0x0925, 0x0947, 0x0020,
+                0x0964 },
+              73,
+              false,
+              true,
+              true,
+              false,
+              RTL_UNICODETOTEXT_FLAGS_UNDEFINED_ERROR },
+            { RTL_TEXTENCODING_ISCII_DEVANAGARI,
+              RTL_CONSTASCII_STRINGPARAM("\xE8\xE8\xE8\xE9\xA1\xE9\xEA\xE9"),
+              { 0x094D, 0x200C, 0x094D, 0x200D, 0x0950, 0x93D },
+              6,
+              false,
+              true,
+              true,
+              false,
               RTL_UNICODETOTEXT_FLAGS_UNDEFINED_ERROR }
         };
     for (std::size_t i = 0; i < SAL_N_ELEMENTS(data); ++i) {
@@ -2870,10 +2873,8 @@ void Test::testInfo() {
         { RTL_TEXTENCODING_IBM_861, RTL_TEXTENCODING_INFO_MIME, true },
         { RTL_TEXTENCODING_IBM_863, RTL_TEXTENCODING_INFO_MIME, true },
         { RTL_TEXTENCODING_IBM_865, RTL_TEXTENCODING_INFO_MIME, true },
-#if 0
         { RTL_TEXTENCODING_ISCII_DEVANAGARI, RTL_TEXTENCODING_INFO_ASCII, true },
         { RTL_TEXTENCODING_ISCII_DEVANAGARI, RTL_TEXTENCODING_INFO_MIME, false },
-#endif
         { RTL_TEXTENCODING_ADOBE_STANDARD, RTL_TEXTENCODING_INFO_ASCII, false },
         { RTL_TEXTENCODING_ADOBE_STANDARD, RTL_TEXTENCODING_INFO_MIME, true },
         { RTL_TEXTENCODING_ADOBE_STANDARD, RTL_TEXTENCODING_INFO_SYMBOL, false },