# HG changeset patch # User Bruno Haible # Date 1169858371 0 # Node ID a972bb402af386ff80a6e07b3bffca086836b18e # Parent 3d820a985c8853758bbc24f709b4c936f2e4acd8 New module 'uniconv/u8-conv-from-enc'. diff --git a/lib/uniconv/u8-conv-from-enc.c b/lib/uniconv/u8-conv-from-enc.c new file mode 100644 --- /dev/null +++ b/lib/uniconv/u8-conv-from-enc.c @@ -0,0 +1,90 @@ +/* Conversion to UTF-8 from legacy encodings. + Copyright (C) 2002, 2006-2007 Free Software Foundation, Inc. + + This program is free software; you can redistribute it and/or modify it + under the terms of the GNU Library General Public License as published + by the Free Software Foundation; either version 2, or (at your option) + any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Library General Public License for more details. + + You should have received a copy of the GNU Library General Public + License along with this program; if not, write to the Free Software + Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, + USA. */ + +/* Written by Bruno Haible . */ + +#include + +/* Specification. */ +#include "uniconv.h" + +#include +#include +#include + +#include "c-strcaseeq.h" +#include "striconveha.h" +#include "unistr.h" + +int +u8_conv_from_encoding (const char *fromcode, + enum iconv_ilseq_handler handler, + const char *src, size_t srclen, + size_t *offsets, + uint8_t **resultp, size_t *lengthp) +{ + if (STRCASEEQ (fromcode, "UTF-8", 'U','T','F','-','8',0,0,0,0)) + { + /* Conversion from UTF-8 to UTF-8. No need to go through iconv(). */ + uint8_t *result; + + if (u8_check ((const uint8_t *) src, srclen)) + { + errno = EILSEQ; + return -1; + } + + if (offsets != NULL) + { + size_t i; + + for (i = 0; i < srclen; ) + { + int count = u8_mblen (src + i, srclen - i); + /* We can rely on count > 0 because of the previous u8_check. */ + if (count <= 0) + abort (); + offsets[i] = i; + i++; + while (--count > 0) + offsets[i++] = (size_t)(-1); + } + } + + /* Memory allocation. */ + if (*resultp != NULL && *lengthp >= srclen) + result = *resultp; + else + { + result = (uint8_t *) malloc (srclen); + if (result == NULL) + { + errno = ENOMEM; + return -1; + } + } + + memcpy ((char *) result, src, srclen); + *resultp = result; + *lengthp = srclen; + return 0; + } + else + return mem_iconveha (src, srclen, fromcode, "UTF-8", true, handler, + offsets, (char **) resultp, lengthp); +} diff --git a/modules/uniconv/u8-conv-from-enc b/modules/uniconv/u8-conv-from-enc new file mode 100644 --- /dev/null +++ b/modules/uniconv/u8-conv-from-enc @@ -0,0 +1,27 @@ +Description: +Conversion to UTF-8 from legacy encodings. + +Files: +lib/uniconv/u8-conv-from-enc.c + +Depends-on: +uniconv/base +c-strcaseeq +striconveha +unistr/u8-check +unistr/u8-mblen + +configure.ac: + +Makefile.am: +lib_SOURCES += uniconv/u8-conv-from-enc.c + +Include: +"uniconv.h" + +License: +LGPL + +Maintainer: +Bruno Haible +