in_cd_ = iconv_open(ucs4_codeset, encoding.c_str());
if (in_cd_ == (iconv_t)(-1)) {
fprintf(stderr, "Error %d returned from iconv_open(in_cd_): %s\n",
- errno, strerror(errno));
+ errno, strerror(errno));
fflush(stderr);
throw lyx::iconv_codecvt_facet_exception();
}
out_cd_ = iconv_open(encoding.c_str(), ucs4_codeset);
if (out_cd_ == (iconv_t)(-1)) {
fprintf(stderr, "Error %d returned from iconv_open(out_cd_): %s\n",
- errno, strerror(errno));
+ errno, strerror(errno));
fflush(stderr);
throw lyx::iconv_codecvt_facet_exception();
}
if (in_cd_ != (iconv_t)(-1))
if (iconv_close(in_cd_) == -1) {
fprintf(stderr, "Error %d returned from iconv_close(in_cd_): %s\n",
- errno, strerror(errno));
+ errno, strerror(errno));
fflush(stderr);
}
if (out_cd_ != (iconv_t)(-1))
if (iconv_close(out_cd_) == -1) {
fprintf(stderr, "Error %d returned from iconv_close(out_cd_): %s\n",
- errno, strerror(errno));
+ errno, strerror(errno));
fflush(stderr);
}
}
&inbytesleft, &to_next, &outbytesleft);
if (retval == base::error) {
fprintf(stderr,
- "Error %d returned from iconv when converting from %s to %s: %s\n",
- errno, ucs4_codeset, encoding_.c_str(),
- strerror(errno));
+ "Error %d returned from iconv when converting from %s to %s: %s\n",
+ errno, ucs4_codeset, encoding_.c_str(),
+ strerror(errno));
fputs("Converted input:", stderr);
for (intern_type const * i = from; i < from_next; ++i) {
unsigned int const c = *i;
&outbytesleft);
if (retval == base::error) {
fprintf(stderr,
- "Error %d returned from iconv when converting from %s to %s: %s\n",
- errno, encoding_.c_str(), ucs4_codeset,
- strerror(errno));
+ "Error %d returned from iconv when converting from %s to %s: %s\n",
+ errno, encoding_.c_str(), ucs4_codeset,
+ strerror(errno));
fputs("Converted input:", stderr);
for (extern_type const * i = from; i < from_next; ++i) {
// extern_type may be signed, avoid output of
}
virtual int do_max_length() const throw()
{
+ // FIXME: this information should be transferred to lib/encodings
// UTF8 uses at most 4 bytes to represent one UCS4 code point
// (see RFC 3629). RFC 2279 specifies 6 bytes, but that
// information is outdated, and RFC 2279 has been superseded by
// RFC 3629.
+ // The CJK encodings use (different) multibyte representation as well.
// All other encodings encode one UCS4 code point in one byte
// (and can therefore only encode a subset of UCS4)
- return encoding_ == "UTF-8" ? 4 : 1;
+ // Note that BIG5 and SJIS do not work with LaTeX (see lib/encodings).
+ // Furthermore, all encodings that use shifting (like SJIS) do not work with
+ // iconv_codecvt_facet.
+ if (encoding_ == "UTF-8" ||
+ encoding_ == "GB" ||
+ encoding_ == "EUC-TW")
+ return 4;
+ else if (encoding_ == "EUC-JP")
+ return 3;
+ else if (encoding_ == "BIG5" ||
+ encoding_ == "EUC-KR" ||
+ encoding_ == "EUC-CN" ||
+ encoding_ == "SJIS" ||
+ encoding_ == "GBK" ||
+ encoding_ == "JIS" )
+ return 2;
+ else
+ return 1;
}
private:
/// Do the actual conversion. The interface is equivalent to that of
imbue(locale);
}
-
+
idocfstream::idocfstream(const char* s, std::ios_base::openmode mode,
- string const & encoding)
+ string const & encoding)
: base()
{
// We must imbue the stream before openening the file
odocfstream::odocfstream(const char* s, std::ios_base::openmode mode,
- string const & encoding)
+ string const & encoding)
: base()
{
// We must imbue the stream before openening the file
}
-#if (!defined(HAVE_WCHAR_T) || SIZEOF_WCHAR_T != 4) && defined(__GNUC__)
+#if ! defined(USE_WCHAR_T) && defined(__GNUC__)
// We get undefined references to these virtual methods. This looks like
// a bug in gcc. The implementation here does not do anything useful, since
// it is overriden in iconv_codecvt_facet.