[Libreoffice-commits] .: sal/Library_sal_textenc.mk sal/qa sal/textenc
Libreoffice Gerrit user
logerrit at kemper.freedesktop.org
Tue Nov 27 05:31:53 PST 2012
sal/Library_sal_textenc.mk | 1
sal/qa/rtl/textenc/rtl_tencinfo.cxx | 2
sal/qa/rtl/textenc/rtl_textcvt.cxx | 81 ++---
sal/textenc/convertisciidevangari.cxx | 496 ++++++++++++++++++++++++++++++++++
sal/textenc/convertisciidevangari.hxx | 34 ++
sal/textenc/convertisciidevangari.tab | 35 ++
sal/textenc/tables.cxx | 5
7 files changed, 611 insertions(+), 43 deletions(-)
New commits:
commit bfeeed3e986f3ce5090d5a03c50546cbda3b99e6
Author: Caolán McNamara <caolanm at redhat.com>
Date: Mon Nov 26 16:22:49 2012 +0000
implement a new iscii (devangari) <-> unicode converter
this time with support for the multi-byte encodings possible
in ISCII
Change-Id: I1dc09e8836676ab614b531e8dc10f91a90b7c4fd
diff --git a/sal/Library_sal_textenc.mk b/sal/Library_sal_textenc.mk
index 5d5d40e..972f0ee 100644
--- a/sal/Library_sal_textenc.mk
+++ b/sal/Library_sal_textenc.mk
@@ -41,6 +41,7 @@ $(eval $(call gb_Library_add_exception_objects,sal_textenc,\
sal/textenc/convertbig5hkscs \
sal/textenc/converteuctw \
sal/textenc/convertgb18030 \
+ sal/textenc/convertisciidevangari \
sal/textenc/convertiso2022cn \
sal/textenc/convertiso2022jp \
sal/textenc/convertiso2022kr \
diff --git a/sal/qa/rtl/textenc/rtl_tencinfo.cxx b/sal/qa/rtl/textenc/rtl_tencinfo.cxx
index 7d3ade9..70e2f2e 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 3c8c33e..ba7074f 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 },
diff --git a/sal/textenc/convertisciidevangari.cxx b/sal/textenc/convertisciidevangari.cxx
new file mode 100644
index 0000000..8adeb4b
--- /dev/null
+++ b/sal/textenc/convertisciidevangari.cxx
@@ -0,0 +1,496 @@
+/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
+/*
+ * This file is part of the LibreOffice project.
+ *
+ * This Source Code Form is subject to the terms of the Mozilla Public
+ * License, v. 2.0. If a copy of the MPL was not distributed with this
+ * file, You can obtain one at http://mozilla.org/MPL/2.0/.
+ */
+
+#include "converter.hxx"
+#include "convertisciidevangari.hxx"
+#include "convertsinglebytetobmpunicode.hxx"
+#include <rtl/textcvt.h>
+
+using namespace sal::detail::textenc;
+using namespace rtl::textenc;
+
+struct IsciiDevanagariToUnicode
+{
+ sal_uInt8 m_cPrevChar;
+ IsciiDevanagariToUnicode()
+ : m_cPrevChar(0)
+ {
+ }
+ void reset()
+ {
+ m_cPrevChar = 0;
+ }
+ sal_Size convert(char const* pSrcBuf, sal_Size nSrcBytes,
+ sal_Unicode* pDestBuf, sal_Size nDestChars, sal_uInt32 nFlags,
+ sal_uInt32* pInfo, sal_Size* pSrcCvtBytes);
+};
+
+struct UnicodeToIsciiDevanagari
+{
+ sal_Unicode m_cPrevChar;
+ sal_Unicode m_cHighSurrogate;
+ UnicodeToIsciiDevanagari()
+ : m_cPrevChar(0)
+ , m_cHighSurrogate(0)
+ {
+ }
+ void reset()
+ {
+ m_cPrevChar = 0;
+ m_cHighSurrogate = 0;
+ }
+ sal_Size convert(sal_Unicode const* pSrcBuf, sal_Size nSrcChars,
+ char* pDestBuf, sal_Size nDestBytes, sal_uInt32 nFlags,
+ sal_uInt32 * pInfo, sal_Size * pSrcCvtChars);
+};
+
+static const sal_Unicode IsciiDevanagariMap[256] =
+{
+ 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
+};
+
+sal_Size IsciiDevanagariToUnicode::convert(
+ char const* pSrcBuf, sal_Size nSrcBytes,
+ sal_Unicode* pDestBuf, sal_Size nDestChars, sal_uInt32 nFlags,
+ sal_uInt32* pInfo, sal_Size* pSrcCvtBytes)
+{
+ sal_uInt32 nInfo = 0;
+ sal_Size nConverted = 0;
+ sal_Unicode* pDestBufPtr = pDestBuf;
+ sal_Unicode* pDestBufEnd = pDestBuf + nDestChars;
+
+ while (nConverted < nSrcBytes)
+ {
+ if (pDestBufPtr == pDestBufEnd)
+ {
+ nInfo |= RTL_TEXTTOUNICODE_INFO_DESTBUFFERTOSMALL;
+ break;
+ }
+
+ sal_Unicode cChar;
+ sal_uInt8 nIn = static_cast<sal_uInt8>(pSrcBuf[nConverted]);
+ sal_uInt8 nNext = nConverted < nSrcBytes + 1 ? static_cast<sal_uInt8>(pSrcBuf[nConverted+1]) : 0;
+ bool bNormal = true;
+ bool bDouble = false;
+ //halant + halant E8 E8 -> halant + ZWNJ 094D 200C
+ //halant + nukta E8 E9 halant + ZWJ 094D 200D
+ if (m_cPrevChar == 0xE8 && nIn == 0xE8)
+ {
+ cChar = 0x200C;
+ bNormal = false;
+ }
+ else if (m_cPrevChar == 0xE8 && nIn == 0xE9)
+ {
+ cChar = 0x200D;
+ bNormal = false;
+ }
+ else if (nNext == 0xE9)
+ {
+ bNormal = false;
+ bDouble = true;
+ switch(nIn)
+ {
+ case 0xA1:
+ cChar = 0x0950;
+ break;
+ case 0xA6:
+ cChar = 0x090C;
+ break;
+ case 0xA7:
+ cChar = 0x0961;
+ break;
+ case 0xAA:
+ cChar = 0x0960;
+ break;
+ case 0xB3:
+ cChar = 0x0958;
+ break;
+ case 0xB4:
+ cChar = 0x0959;
+ break;
+ case 0xB5:
+ cChar = 0x095A;
+ break;
+ case 0xBA:
+ cChar = 0x095B;
+ break;
+ case 0xBF:
+ cChar = 0x095C;
+ break;
+ case 0xC0:
+ cChar = 0x095D;
+ break;
+ case 0xC9:
+ cChar = 0x095E;
+ break;
+ case 0xDB:
+ cChar = 0x0962;
+ break;
+ case 0xDC:
+ cChar = 0x0963;
+ break;
+ case 0xDF:
+ cChar = 0x0944;
+ break;
+ case 0xEA:
+ cChar = 0x093D;
+ break;
+ default:
+ bNormal = true;
+ bDouble = false;
+ break;
+ };
+ }
+
+ if (bNormal)
+ cChar = IsciiDevanagariMap[nIn];
+
+ bool bUndefined = cChar == 0xffff;
+
+ if (bUndefined)
+ {
+ BadInputConversionAction eAction = handleBadInputTextToUnicodeConversion(
+ bUndefined, true, 0, nFlags, &pDestBufPtr, pDestBufEnd,
+ &nInfo);
+ if (eAction == BAD_INPUT_CONTINUE)
+ continue;
+ if (eAction == BAD_INPUT_STOP)
+ break;
+ else if (eAction == BAD_INPUT_NO_OUTPUT)
+ {
+ nInfo |= RTL_TEXTTOUNICODE_INFO_DESTBUFFERTOSMALL;
+ break;
+ }
+ }
+ ++nConverted;
+ if (bDouble)
+ ++nConverted;
+
+ *pDestBufPtr++ = cChar;
+ m_cPrevChar = bNormal ? nIn : 0;
+ }
+
+ if (pInfo)
+ *pInfo = nInfo;
+ if (pSrcCvtBytes)
+ *pSrcCvtBytes = nConverted;
+
+ return pDestBufPtr - pDestBuf;
+}
+
+BmpUnicodeToSingleByteRange const unicodeToISCIIEncoding[] =
+{
+ { 0x0000, 0x007F - 0x0000, 0x00 }, { 0x0901, 0x0903 - 0x0901, 0xA1 },
+ { 0x0905, 0x090B - 0x0905, 0xA4 }, { 0x090D, 0x090D - 0x090D, 0xAE },
+ { 0x090E, 0x0910 - 0x090E, 0xAB }, { 0x0911, 0x0911 - 0x0911, 0xB2 },
+ { 0x0912, 0x0914 - 0x0912, 0xAF }, { 0x0915, 0x092F - 0x0915, 0xB3 },
+ { 0x0930, 0x0939 - 0x0930, 0xCF }, { 0x093C, 0x093C - 0x093C, 0xE9 },
+ { 0x093E, 0x0943 - 0x093E, 0xDA }, { 0x0945, 0x0945 - 0x0945, 0xE3 },
+ { 0x0946, 0x0948 - 0x0946, 0xE0 }, { 0x0949, 0x0949 - 0x0949, 0xE7 },
+ { 0x094A, 0x094C - 0x094A, 0xE4 }, { 0x094D, 0x094D - 0x094D, 0xE8 },
+ { 0x095F, 0x095F - 0x095F, 0xCE }, { 0x0964, 0x0964 - 0x0964, 0xEA },
+ { 0x0966, 0x096F - 0x0966, 0xF1 }
+};
+
+sal_Size UnicodeToIsciiDevanagari::convert(sal_Unicode const* pSrcBuf, sal_Size nSrcChars,
+ char* pDestBuf, sal_Size nDestBytes, sal_uInt32 nFlags,
+ sal_uInt32 * pInfo, sal_Size* pSrcCvtChars)
+{
+ size_t entries = SAL_N_ELEMENTS(unicodeToISCIIEncoding);
+ BmpUnicodeToSingleByteRange const * ranges = unicodeToISCIIEncoding;
+
+ sal_Unicode cHighSurrogate = m_cHighSurrogate;
+ sal_uInt32 nInfo = 0;
+ sal_Size nConverted = 0;
+ sal_Char* pDestBufPtr = pDestBuf;
+ sal_Char* pDestBufEnd = pDestBuf + nDestBytes;
+ for (; nConverted < nSrcChars; ++nConverted)
+ {
+ bool bUndefined = true;
+ sal_uInt32 c = *pSrcBuf++;
+ sal_Char cSpecialChar = 0;
+ if (cHighSurrogate == 0)
+ {
+ if (ImplIsHighSurrogate(c))
+ {
+ cHighSurrogate = static_cast< sal_Unicode >(c);
+ continue;
+ }
+ }
+ else if (ImplIsLowSurrogate(c))
+ {
+ c = ImplCombineSurrogates(cHighSurrogate, c);
+ }
+ else
+ {
+ bUndefined = false;
+ goto bad_input;
+ }
+ if (ImplIsLowSurrogate(c) || ImplIsNoncharacter(c))
+ {
+ bUndefined = false;
+ goto bad_input;
+ }
+
+ //halant + halant E8 E8 -> halant + ZWNJ 094D 200C
+ //halant + nukta E8 E9 halant + ZWJ 094D 200D
+ if (m_cPrevChar == 0x094D && c == 0x200C)
+ cSpecialChar = 0xE8;
+ else if (m_cPrevChar == 0x094D && c == 0x200D)
+ cSpecialChar = 0xE9;
+ if (cSpecialChar)
+ {
+ if (pDestBufEnd - pDestBufPtr < 1)
+ {
+ nInfo |= RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
+ break;
+ }
+ *pDestBufPtr++ = cSpecialChar;
+ m_cPrevChar = 0;
+ goto done;
+ }
+ switch (c)
+ {
+ case 0x0950:
+ cSpecialChar = 0xA1;
+ break;
+ case 0x090C:
+ cSpecialChar = 0xA6;
+ break;
+ case 0x0961:
+ cSpecialChar = 0xA7;
+ break;
+ case 0x0960:
+ cSpecialChar = 0xAA;
+ break;
+ case 0x0958:
+ cSpecialChar = 0xB3;
+ break;
+ case 0x0959:
+ cSpecialChar = 0xB4;
+ break;
+ case 0x095A:
+ cSpecialChar = 0xB5;
+ break;
+ case 0x095B:
+ cSpecialChar = 0xBA;
+ break;
+ case 0x095C:
+ cSpecialChar = 0xBF;
+ break;
+ case 0x095D:
+ cSpecialChar = 0xC0;
+ break;
+ case 0x095E:
+ cSpecialChar = 0xC9;
+ break;
+ case 0x0962:
+ cSpecialChar = 0xDB;
+ break;
+ case 0x0963:
+ cSpecialChar = 0xDC;
+ break;
+ case 0x0944:
+ cSpecialChar = 0xDF;
+ break;
+ case 0x093D:
+ cSpecialChar = 0xEA;
+ break;
+ default:
+ break;
+ }
+ if (cSpecialChar)
+ {
+ if (pDestBufEnd - pDestBufPtr < 2)
+ {
+ nInfo |= RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
+ break;
+ }
+ *pDestBufPtr++ = cSpecialChar;
+ *pDestBufPtr++ = 0xE9;
+ m_cPrevChar = 0;
+ goto done;
+ }
+
+ // Linearly searching through the ranges if probably fastest, assuming
+ // that most converted characters belong to the ASCII subset:
+ for (size_t i = 0; i < entries; ++i)
+ {
+ if (c < ranges[i].unicode)
+ {
+ break;
+ }
+ else if (c <= sal::static_int_cast< sal_uInt32 >(
+ ranges[i].unicode + ranges[i].range))
+ {
+ if (pDestBufEnd - pDestBufPtr < 1)
+ {
+ goto no_output;
+ }
+ *pDestBufPtr++ = static_cast< sal_Char >(
+ ranges[i].byte + (c - ranges[i].unicode));
+ m_cPrevChar = c;
+ goto done;
+ }
+ }
+ goto bad_input;
+ done:
+ cHighSurrogate = 0;
+ continue;
+ bad_input:
+ switch (sal::detail::textenc::handleBadInputUnicodeToTextConversion(
+ bUndefined, c, nFlags, &pDestBufPtr, pDestBufEnd, &nInfo, 0,
+ 0, 0))
+ {
+ case sal::detail::textenc::BAD_INPUT_STOP:
+ cHighSurrogate = 0;
+ break;
+
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
+ cHighSurrogate = 0;
+ continue;
+
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
+ goto no_output;
+ }
+ break;
+ no_output:
+ --pSrcBuf;
+ nInfo |= RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
+ break;
+ }
+
+ if (cHighSurrogate != 0
+ && ((nInfo
+ & (RTL_UNICODETOTEXT_INFO_ERROR
+ | RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL))
+ == 0))
+ {
+ if ((nFlags & RTL_UNICODETOTEXT_FLAGS_FLUSH) != 0)
+ {
+ nInfo |= RTL_UNICODETOTEXT_INFO_SRCBUFFERTOSMALL;
+ }
+ else
+ {
+ switch (sal::detail::textenc::handleBadInputUnicodeToTextConversion(
+ false, 0, nFlags, &pDestBufPtr, pDestBufEnd, &nInfo, 0,
+ 0, 0))
+ {
+ case sal::detail::textenc::BAD_INPUT_STOP:
+ case sal::detail::textenc::BAD_INPUT_CONTINUE:
+ cHighSurrogate = 0;
+ break;
+
+ case sal::detail::textenc::BAD_INPUT_NO_OUTPUT:
+ nInfo |= RTL_UNICODETOTEXT_INFO_DESTBUFFERTOSMALL;
+ break;
+ }
+ }
+ }
+ m_cHighSurrogate = cHighSurrogate;
+ if (pInfo)
+ *pInfo = nInfo;
+ if (pSrcCvtChars)
+ *pSrcCvtChars = nConverted;
+
+ return pDestBufPtr - pDestBuf;
+}
+
+sal_Size ImplConvertIsciiDevanagariToUnicode(void const*,
+ void* pContext, char const* pSrcBuf, sal_Size nSrcBytes,
+ sal_Unicode* pDestBuf, sal_Size nDestChars, sal_uInt32 nFlags,
+ sal_uInt32* pInfo, sal_Size* pSrcCvtBytes)
+{
+ IsciiDevanagariToUnicode *pCtx =
+ static_cast<IsciiDevanagariToUnicode*>(pContext);
+ return pCtx->convert(pSrcBuf, nSrcBytes, pDestBuf, nDestChars, nFlags,
+ pInfo, pSrcCvtBytes);
+}
+
+sal_Size ImplConvertUnicodeToIsciiDevanagari(void const*,
+ void * pContext, sal_Unicode const * pSrcBuf, sal_Size nSrcChars,
+ char * pDestBuf, sal_Size nDestBytes, sal_uInt32 nFlags,
+ sal_uInt32 * pInfo, sal_Size * pSrcCvtChars)
+{
+ UnicodeToIsciiDevanagari *pCtx =
+ static_cast<UnicodeToIsciiDevanagari*>(pContext);
+ return pCtx->convert(pSrcBuf, nSrcChars,
+ pDestBuf, nDestBytes, nFlags, pInfo, pSrcCvtChars);
+}
+
+void *ImplCreateIsciiDevanagariToUnicodeContext()
+{
+ return new IsciiDevanagariToUnicode;
+}
+
+void ImplDestroyIsciiDevanagariToUnicodeContext(void * pContext)
+{
+ IsciiDevanagariToUnicode *pCtx =
+ static_cast<IsciiDevanagariToUnicode*>(pContext);
+ delete pCtx;
+}
+
+void ImplResetIsciiDevanagariToUnicodeContext(void * pContext)
+{
+ IsciiDevanagariToUnicode *pCtx =
+ static_cast<IsciiDevanagariToUnicode*>(pContext);
+ pCtx->reset();
+}
+
+void *ImplCreateUnicodeToIsciiDevanagariContext()
+{
+ return new UnicodeToIsciiDevanagari;
+}
+
+void ImplResetUnicodeToIsciiDevanagariContext(void * pContext)
+{
+ UnicodeToIsciiDevanagari *pCtx =
+ static_cast<UnicodeToIsciiDevanagari*>(pContext);
+ pCtx->reset();
+}
+
+void ImplDestroyUnicodeToIsciiDevanagariContext(void * pContext)
+{
+ UnicodeToIsciiDevanagari *pCtx =
+ static_cast<UnicodeToIsciiDevanagari*>(pContext);
+ delete pCtx;
+}
+
+/* vim:set shiftwidth=4 softtabstop=4 expandtab: */
diff --git a/sal/textenc/convertisciidevangari.hxx b/sal/textenc/convertisciidevangari.hxx
new file mode 100644
index 0000000..b3f5f30
--- /dev/null
+++ b/sal/textenc/convertisciidevangari.hxx
@@ -0,0 +1,34 @@
+/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
+/*
+ * This file is part of the LibreOffice project.
+ *
+ * This Source Code Form is subject to the terms of the Mozilla Public
+ * License, v. 2.0. If a copy of the MPL was not distributed with this
+ * file, You can obtain one at http://mozilla.org/MPL/2.0/.
+ */
+
+#include <sal/types.h>
+
+sal_Size ImplConvertIsciiDevanagariToUnicode(void const * pData,
+ void * pContext, char const * pSrcBuf, sal_Size nSrcBytes,
+ sal_Unicode * pDestBuf, sal_Size nDestChars, sal_uInt32 nFlags,
+ sal_uInt32 * pInfo, sal_Size * pSrcCvtBytes);
+
+sal_Size ImplConvertUnicodeToIsciiDevanagari(void const * pData,
+ void * pContext, sal_Unicode const * pSrcBuf, sal_Size nSrcChars,
+ char * pDestBuf, sal_Size nDestBytes, sal_uInt32 nFlags,
+ sal_uInt32 * pInfo, sal_Size * pSrcCvtChars);
+
+void *ImplCreateIsciiDevanagariToUnicodeContext();
+
+void ImplDestroyIsciiDevanagariToUnicodeContext(void * pContext);
+
+void ImplResetIsciiDevanagariToUnicodeContext(void * pContext);
+
+void *ImplCreateUnicodeToIsciiDevanagariContext();
+
+void ImplResetUnicodeToIsciiDevanagariContext(void * pContext);
+
+void ImplDestroyUnicodeToIsciiDevanagariContext(void * pContext);
+
+/* vim:set shiftwidth=4 softtabstop=4 expandtab: */
diff --git a/sal/textenc/convertisciidevangari.tab b/sal/textenc/convertisciidevangari.tab
new file mode 100644
index 0000000..6c4a24b
--- /dev/null
+++ b/sal/textenc/convertisciidevangari.tab
@@ -0,0 +1,35 @@
+/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
+/*
+ * This file is part of the LibreOffice project.
+ *
+ * This Source Code Form is subject to the terms of the Mozilla Public
+ * License, v. 2.0. If a copy of the MPL was not distributed with this
+ * file, You can obtain one at http://mozilla.org/MPL/2.0/.
+ */
+
+#include "sal/config.h"
+
+#include "rtl/tencinfo.h"
+#include "rtl/textenc.h"
+
+#include "convertisciidevangari.hxx"
+
+static ImplTextEncodingData const aImplIsciiDevanagariTextEncodingData
+ = { { NULL,
+ &ImplConvertIsciiDevanagariToUnicode,
+ &ImplConvertUnicodeToIsciiDevanagari,
+ &ImplCreateIsciiDevanagariToUnicodeContext,
+ &ImplDestroyIsciiDevanagariToUnicodeContext,
+ &ImplResetIsciiDevanagariToUnicodeContext,
+ &ImplCreateUnicodeToIsciiDevanagariContext,
+ &ImplResetUnicodeToIsciiDevanagariContext,
+ &ImplDestroyUnicodeToIsciiDevanagariContext },
+ 1,
+ 2,
+ 2,
+ 1,
+ NULL,
+ "x-iscii-de ",
+ RTL_TEXTENCODING_INFO_ASCII | RTL_TEXTENCODING_INFO_MULTIBYTE };
+
+/* vim:set shiftwidth=4 softtabstop=4 expandtab: */
diff --git a/sal/textenc/tables.cxx b/sal/textenc/tables.cxx
index 7400abb..bdb391e 100644
--- a/sal/textenc/tables.cxx
+++ b/sal/textenc/tables.cxx
@@ -100,13 +100,14 @@ static sal_uInt16 const aImplDoubleByteIdentifierTab[1] = { 0 };
#include "tcvttcn6.tab"
#include "tcvtuni1.tab"
+#include "convertadobe.tab"
#include "convertbig5hkscs.tab"
#include "converteuctw.tab"
#include "convertgb18030.tab"
+#include "convertisciidevangari.tab"
#include "convertiso2022cn.tab"
#include "convertiso2022jp.tab"
#include "convertiso2022kr.tab"
-#include "convertadobe.tab"
extern "C" SAL_DLLPUBLIC_EXPORT ImplTextEncodingData const *
sal_getFullTextEncodingData( rtl_TextEncoding nEncoding )
@@ -208,7 +209,7 @@ extern "C" SAL_DLLPUBLIC_EXPORT ImplTextEncodingData const *
&aImplBig5HkscsTextEncodingData, /* BIG5_HKSCS */
&aImplTis620TextEncodingData, /* TIS_620 */
&aImplKoi8UTextEncodingData, /* KOI8_U */
- NULL, /* TODO! ISCII_DEVANAGARI */
+ &aImplIsciiDevanagariTextEncodingData, /* ISCII_DEVANAGARI */
NULL, /* JAVA_UTF8, see above */
&adobeStandardEncodingData, /* ADOBE_STANDARD */
&adobeSymbolEncodingData, /* ADOBE_SYMBOL */
More information about the Libreoffice-commits
mailing list