/* * PROGRAM: Firebird International support * MODULE: cv_icu.cpp * DESCRIPTION: Codeset conversion for ICU character sets. * * The contents of this file are subject to the Initial * Developer's Public License Version 1.0 (the "License"); * you may not use this file except in compliance with the * License. You may obtain a copy of the License at * http://www.ibphoenix.com/main.nfs?a=ibphoenix&page=ibp_idpl. * * Software distributed under the License is distributed AS IS, * WITHOUT WARRANTY OF ANY KIND, either express or implied. * See the License for the specific language governing rights * and limitations under the License. * * The Original Code was created by Adriano dos Santos Fernandes * for the Firebird Open Source RDBMS project. * * Copyright (c) 2004 Adriano dos Santos Fernandes * and all contributors signed below. * * All Rights Reserved. * Contributor(s): ______________________________________. */ #include "firebird.h" #include "../intl/ldcommon.h" #include "ld_proto.h" #include "cv_icu.h" #include "unicode/ucnv.h" namespace { struct CsConvertImpl { charset* cs; }; } static UConverter* create_converter(csconvert* cv, UErrorCode* status) { UConverter* conv = ucnv_open( static_cast(cv->csconvert_impl)->cs->charset_name, status); const void* oldContext; UConverterFromUCallback oldFromAction; ucnv_setFromUCallBack( conv, UCNV_FROM_U_CALLBACK_STOP, NULL, &oldFromAction, &oldContext, status); UConverterToUCallback oldToAction; ucnv_setToUCallBack( conv, UCNV_TO_U_CALLBACK_STOP, NULL, &oldToAction, &oldContext, status); fb_assert(U_SUCCESS(*status)); return conv; } static void convert_destroy(csconvert* cv) { delete static_cast(cv->csconvert_impl); } static ULONG unicode_to_icu(csconvert* cv, ULONG srcLen, const BYTE* src, ULONG dstLen, BYTE* dst, USHORT* errCode, ULONG* errPosition) { *errCode = 0; *errPosition = 0; if (dst == NULL) { return srcLen / sizeof(UChar) * static_cast(cv->csconvert_impl)->cs->charset_max_bytes_per_char; } UErrorCode status = U_ZERO_ERROR; UConverter* conv = create_converter(cv, &status); ULONG len = ucnv_fromUChars(conv, reinterpret_cast(dst), dstLen, Firebird::Aligner(src, srcLen), srcLen / sizeof(UChar), &status); if (!U_SUCCESS(status)) { len = INTL_BAD_STR_LENGTH; switch (status) { case U_INVALID_CHAR_FOUND: *errCode = CS_CONVERT_ERROR; break; case U_TRUNCATED_CHAR_FOUND: *errCode = CS_TRUNCATION_ERROR; break; default: fb_assert(false); *errCode = CS_CONVERT_ERROR; } } ucnv_close(conv); return len; } static ULONG icu_to_unicode(csconvert* cv, ULONG srcLen, const BYTE* src, ULONG dstLen, BYTE* dst, USHORT* errCode, ULONG* errPosition) { *errCode = 0; *errPosition = 0; if (dst == NULL) { return srcLen / static_cast(cv->csconvert_impl)->cs->charset_min_bytes_per_char * sizeof(UChar); } UErrorCode status = U_ZERO_ERROR; UConverter* conv = create_converter(cv, &status); ULONG len = ucnv_toUChars(conv, Firebird::OutAligner(dst, dstLen), dstLen / sizeof(UChar), reinterpret_cast(src), srcLen, &status); if (!U_SUCCESS(status)) { len = INTL_BAD_STR_LENGTH; if (status == U_INVALID_CHAR_FOUND) *errCode = CS_BAD_INPUT; else if (status == U_TRUNCATED_CHAR_FOUND) *errCode = CS_TRUNCATION_ERROR; else { fb_assert(false); *errCode = CS_BAD_INPUT; } } else len *= sizeof(UChar); ucnv_close(conv); return len; } void CVICU_convert_init(charset* cs) { cs->charset_to_unicode.csconvert_version = CSCONVERT_VERSION_1; cs->charset_to_unicode.csconvert_name = "ICU->UNICODE"; cs->charset_to_unicode.csconvert_fn_convert = icu_to_unicode; cs->charset_to_unicode.csconvert_fn_destroy = convert_destroy; cs->charset_to_unicode.csconvert_impl = new CsConvertImpl(); static_cast(cs->charset_to_unicode.csconvert_impl)->cs = cs; cs->charset_from_unicode.csconvert_version = CSCONVERT_VERSION_1; cs->charset_from_unicode.csconvert_name = "UNICODE->ICU"; cs->charset_from_unicode.csconvert_fn_convert = unicode_to_icu; cs->charset_from_unicode.csconvert_fn_destroy = convert_destroy; cs->charset_from_unicode.csconvert_impl = new CsConvertImpl(); static_cast(cs->charset_from_unicode.csconvert_impl)->cs = cs; }