aboutsummaryrefslogtreecommitdiff
path: root/libcpp/charset.c
diff options
context:
space:
mode:
Diffstat (limited to 'libcpp/charset.c')
-rw-r--r--libcpp/charset.c115
1 files changed, 77 insertions, 38 deletions
diff --git a/libcpp/charset.c b/libcpp/charset.c
index 5db8fc1..225cdb4 100644
--- a/libcpp/charset.c
+++ b/libcpp/charset.c
@@ -642,6 +642,7 @@ init_iconv_desc (cpp_reader *pfile, const char *to, const char *from)
{
ret.func = convert_no_conversion;
ret.cd = (iconv_t) -1;
+ ret.width = -1;
return ret;
}
@@ -655,6 +656,7 @@ init_iconv_desc (cpp_reader *pfile, const char *to, const char *from)
{
ret.func = conversion_tab[i].func;
ret.cd = conversion_tab[i].fake_cd;
+ ret.width = -1;
return ret;
}
@@ -663,6 +665,7 @@ init_iconv_desc (cpp_reader *pfile, const char *to, const char *from)
{
ret.func = convert_using_iconv;
ret.cd = iconv_open (to, from);
+ ret.width = -1;
if (ret.cd == (iconv_t) -1)
{
@@ -683,6 +686,7 @@ init_iconv_desc (cpp_reader *pfile, const char *to, const char *from)
from, to);
ret.func = convert_no_conversion;
ret.cd = (iconv_t) -1;
+ ret.width = -1;
}
return ret;
}
@@ -716,7 +720,17 @@ cpp_init_iconv (cpp_reader *pfile)
wcset = default_wcset;
pfile->narrow_cset_desc = init_iconv_desc (pfile, ncset, SOURCE_CHARSET);
+ pfile->narrow_cset_desc.width = CPP_OPTION (pfile, char_precision);
+ pfile->char16_cset_desc = init_iconv_desc (pfile,
+ be ? "UTF-16BE" : "UTF-16LE",
+ SOURCE_CHARSET);
+ pfile->char16_cset_desc.width = 16;
+ pfile->char32_cset_desc = init_iconv_desc (pfile,
+ be ? "UTF-32BE" : "UTF-32LE",
+ SOURCE_CHARSET);
+ pfile->char32_cset_desc.width = 32;
pfile->wide_cset_desc = init_iconv_desc (pfile, wcset, SOURCE_CHARSET);
+ pfile->wide_cset_desc.width = CPP_OPTION (pfile, wchar_precision);
}
/* Destroy iconv(3) descriptors set up by cpp_init_iconv, if necessary. */
@@ -1051,15 +1065,13 @@ _cpp_valid_ucn (cpp_reader *pfile, const uchar **pstr,
An advanced pointer is returned. Issues all relevant diagnostics. */
static const uchar *
convert_ucn (cpp_reader *pfile, const uchar *from, const uchar *limit,
- struct _cpp_strbuf *tbuf, bool wide)
+ struct _cpp_strbuf *tbuf, struct cset_converter cvt)
{
cppchar_t ucn;
uchar buf[6];
uchar *bufp = buf;
size_t bytesleft = 6;
int rval;
- struct cset_converter cvt
- = wide ? pfile->wide_cset_desc : pfile->narrow_cset_desc;
struct normalize_state nst = INITIAL_NORMALIZE_STATE;
from++; /* Skip u/U. */
@@ -1086,14 +1098,15 @@ convert_ucn (cpp_reader *pfile, const uchar *from, const uchar *limit,
function issues no diagnostics and never fails. */
static void
emit_numeric_escape (cpp_reader *pfile, cppchar_t n,
- struct _cpp_strbuf *tbuf, bool wide)
+ struct _cpp_strbuf *tbuf, struct cset_converter cvt)
{
- if (wide)
+ size_t width = cvt.width;
+
+ if (width != CPP_OPTION (pfile, char_precision))
{
/* We have to render this into the target byte order, which may not
be our byte order. */
bool bigend = CPP_OPTION (pfile, bytes_big_endian);
- size_t width = CPP_OPTION (pfile, wchar_precision);
size_t cwidth = CPP_OPTION (pfile, char_precision);
size_t cmask = width_to_mask (cwidth);
size_t nbwc = width / cwidth;
@@ -1136,12 +1149,11 @@ emit_numeric_escape (cpp_reader *pfile, cppchar_t n,
number. You can, e.g. generate surrogate pairs this way. */
static const uchar *
convert_hex (cpp_reader *pfile, const uchar *from, const uchar *limit,
- struct _cpp_strbuf *tbuf, bool wide)
+ struct _cpp_strbuf *tbuf, struct cset_converter cvt)
{
cppchar_t c, n = 0, overflow = 0;
int digits_found = 0;
- size_t width = (wide ? CPP_OPTION (pfile, wchar_precision)
- : CPP_OPTION (pfile, char_precision));
+ size_t width = cvt.width;
size_t mask = width_to_mask (width);
if (CPP_WTRADITIONAL (pfile))
@@ -1174,7 +1186,7 @@ convert_hex (cpp_reader *pfile, const uchar *from, const uchar *limit,
n &= mask;
}
- emit_numeric_escape (pfile, n, tbuf, wide);
+ emit_numeric_escape (pfile, n, tbuf, cvt);
return from;
}
@@ -1187,12 +1199,11 @@ convert_hex (cpp_reader *pfile, const uchar *from, const uchar *limit,
number. */
static const uchar *
convert_oct (cpp_reader *pfile, const uchar *from, const uchar *limit,
- struct _cpp_strbuf *tbuf, bool wide)
+ struct _cpp_strbuf *tbuf, struct cset_converter cvt)
{
size_t count = 0;
cppchar_t c, n = 0;
- size_t width = (wide ? CPP_OPTION (pfile, wchar_precision)
- : CPP_OPTION (pfile, char_precision));
+ size_t width = cvt.width;
size_t mask = width_to_mask (width);
bool overflow = false;
@@ -1213,7 +1224,7 @@ convert_oct (cpp_reader *pfile, const uchar *from, const uchar *limit,
n &= mask;
}
- emit_numeric_escape (pfile, n, tbuf, wide);
+ emit_numeric_escape (pfile, n, tbuf, cvt);
return from;
}
@@ -1224,7 +1235,7 @@ convert_oct (cpp_reader *pfile, const uchar *from, const uchar *limit,
pointer. Handles all relevant diagnostics. */
static const uchar *
convert_escape (cpp_reader *pfile, const uchar *from, const uchar *limit,
- struct _cpp_strbuf *tbuf, bool wide)
+ struct _cpp_strbuf *tbuf, struct cset_converter cvt)
{
/* Values of \a \b \e \f \n \r \t \v respectively. */
#if HOST_CHARSET == HOST_CHARSET_ASCII
@@ -1236,23 +1247,21 @@ convert_escape (cpp_reader *pfile, const uchar *from, const uchar *limit,
#endif
uchar c;
- struct cset_converter cvt
- = wide ? pfile->wide_cset_desc : pfile->narrow_cset_desc;
c = *from;
switch (c)
{
/* UCNs, hex escapes, and octal escapes are processed separately. */
case 'u': case 'U':
- return convert_ucn (pfile, from, limit, tbuf, wide);
+ return convert_ucn (pfile, from, limit, tbuf, cvt);
case 'x':
- return convert_hex (pfile, from, limit, tbuf, wide);
+ return convert_hex (pfile, from, limit, tbuf, cvt);
break;
case '0': case '1': case '2': case '3':
case '4': case '5': case '6': case '7':
- return convert_oct (pfile, from, limit, tbuf, wide);
+ return convert_oct (pfile, from, limit, tbuf, cvt);
/* Various letter escapes. Get the appropriate host-charset
value into C. */
@@ -1312,6 +1321,27 @@ convert_escape (cpp_reader *pfile, const uchar *from, const uchar *limit,
return from + 1;
}
+/* TYPE is a token type. The return value is the conversion needed to
+ convert from source to execution character set for the given type. */
+static struct cset_converter
+converter_for_type (cpp_reader *pfile, enum cpp_ttype type)
+{
+ switch (type)
+ {
+ default:
+ return pfile->narrow_cset_desc;
+ case CPP_CHAR16:
+ case CPP_STRING16:
+ return pfile->char16_cset_desc;
+ case CPP_CHAR32:
+ case CPP_STRING32:
+ return pfile->char32_cset_desc;
+ case CPP_WCHAR:
+ case CPP_WSTRING:
+ return pfile->wide_cset_desc;
+ }
+}
+
/* FROM is an array of cpp_string structures of length COUNT. These
are to be converted from the source to the execution character set,
escape sequences translated, and finally all are to be
@@ -1320,13 +1350,12 @@ convert_escape (cpp_reader *pfile, const uchar *from, const uchar *limit,
false for failure. */
bool
cpp_interpret_string (cpp_reader *pfile, const cpp_string *from, size_t count,
- cpp_string *to, bool wide)
+ cpp_string *to, enum cpp_ttype type)
{
struct _cpp_strbuf tbuf;
const uchar *p, *base, *limit;
size_t i;
- struct cset_converter cvt
- = wide ? pfile->wide_cset_desc : pfile->narrow_cset_desc;
+ struct cset_converter cvt = converter_for_type (pfile, type);
tbuf.asize = MAX (OUTBUF_BLOCK_SIZE, from->len);
tbuf.text = XNEWVEC (uchar, tbuf.asize);
@@ -1335,7 +1364,7 @@ cpp_interpret_string (cpp_reader *pfile, const cpp_string *from, size_t count,
for (i = 0; i < count; i++)
{
p = from[i].text;
- if (*p == 'L') p++;
+ if (*p == 'L' || *p == 'u' || *p == 'U') p++;
p++; /* Skip leading quote. */
limit = from[i].text + from[i].len - 1; /* Skip trailing quote. */
@@ -1354,12 +1383,12 @@ cpp_interpret_string (cpp_reader *pfile, const cpp_string *from, size_t count,
if (p == limit)
break;
- p = convert_escape (pfile, p + 1, limit, &tbuf, wide);
+ p = convert_escape (pfile, p + 1, limit, &tbuf, cvt);
}
}
/* NUL-terminate the 'to' buffer and translate it to a cpp_string
structure. */
- emit_numeric_escape (pfile, 0, &tbuf, wide);
+ emit_numeric_escape (pfile, 0, &tbuf, cvt);
tbuf.text = XRESIZEVEC (uchar, tbuf.text, tbuf.len);
to->text = tbuf.text;
to->len = tbuf.len;
@@ -1375,7 +1404,8 @@ cpp_interpret_string (cpp_reader *pfile, const cpp_string *from, size_t count,
in a string, but do not perform character set conversion. */
bool
cpp_interpret_string_notranslate (cpp_reader *pfile, const cpp_string *from,
- size_t count, cpp_string *to, bool wide)
+ size_t count, cpp_string *to,
+ enum cpp_ttype type ATTRIBUTE_UNUSED)
{
struct cset_converter save_narrow_cset_desc = pfile->narrow_cset_desc;
bool retval;
@@ -1383,7 +1413,7 @@ cpp_interpret_string_notranslate (cpp_reader *pfile, const cpp_string *from,
pfile->narrow_cset_desc.func = convert_no_conversion;
pfile->narrow_cset_desc.cd = (iconv_t) -1;
- retval = cpp_interpret_string (pfile, from, count, to, wide);
+ retval = cpp_interpret_string (pfile, from, count, to, CPP_STRING);
pfile->narrow_cset_desc = save_narrow_cset_desc;
return retval;
@@ -1462,13 +1492,14 @@ narrow_str_to_charconst (cpp_reader *pfile, cpp_string str,
/* Subroutine of cpp_interpret_charconst which performs the conversion
to a number, for wide strings. STR is the string structure returned
by cpp_interpret_string. PCHARS_SEEN and UNSIGNEDP are as for
- cpp_interpret_charconst. */
+ cpp_interpret_charconst. TYPE is the token type. */
static cppchar_t
wide_str_to_charconst (cpp_reader *pfile, cpp_string str,
- unsigned int *pchars_seen, int *unsignedp)
+ unsigned int *pchars_seen, int *unsignedp,
+ enum cpp_ttype type)
{
bool bigend = CPP_OPTION (pfile, bytes_big_endian);
- size_t width = CPP_OPTION (pfile, wchar_precision);
+ size_t width = converter_for_type (pfile, type).width;
size_t cwidth = CPP_OPTION (pfile, char_precision);
size_t mask = width_to_mask (width);
size_t cmask = width_to_mask (cwidth);
@@ -1490,7 +1521,7 @@ wide_str_to_charconst (cpp_reader *pfile, cpp_string str,
/* Wide character constants have type wchar_t, and a single
character exactly fills a wchar_t, so a multi-character wide
character constant is guaranteed to overflow. */
- if (off > 0)
+ if (str.len > nbwc * 2)
cpp_error (pfile, CPP_DL_WARNING,
"character constant too long for its type");
@@ -1498,13 +1529,20 @@ wide_str_to_charconst (cpp_reader *pfile, cpp_string str,
sign- or zero-extend to the full width of cppchar_t. */
if (width < BITS_PER_CPPCHAR_T)
{
- if (CPP_OPTION (pfile, unsigned_wchar) || !(result & (1 << (width - 1))))
+ if (type == CPP_CHAR16 || type == CPP_CHAR32
+ || CPP_OPTION (pfile, unsigned_wchar)
+ || !(result & (1 << (width - 1))))
result &= mask;
else
result |= ~mask;
}
- *unsignedp = CPP_OPTION (pfile, unsigned_wchar);
+ if (type == CPP_CHAR16 || type == CPP_CHAR32
+ || CPP_OPTION (pfile, unsigned_wchar))
+ *unsignedp = 1;
+ else
+ *unsignedp = 0;
+
*pchars_seen = 1;
return result;
}
@@ -1518,20 +1556,21 @@ cpp_interpret_charconst (cpp_reader *pfile, const cpp_token *token,
unsigned int *pchars_seen, int *unsignedp)
{
cpp_string str = { 0, 0 };
- bool wide = (token->type == CPP_WCHAR);
+ bool wide = (token->type != CPP_CHAR);
cppchar_t result;
- /* an empty constant will appear as L'' or '' */
+ /* an empty constant will appear as L'', u'', U'' or '' */
if (token->val.str.len == (size_t) (2 + wide))
{
cpp_error (pfile, CPP_DL_ERROR, "empty character constant");
return 0;
}
- else if (!cpp_interpret_string (pfile, &token->val.str, 1, &str, wide))
+ else if (!cpp_interpret_string (pfile, &token->val.str, 1, &str, token->type))
return 0;
if (wide)
- result = wide_str_to_charconst (pfile, str, pchars_seen, unsignedp);
+ result = wide_str_to_charconst (pfile, str, pchars_seen, unsignedp,
+ token->type);
else
result = narrow_str_to_charconst (pfile, str, pchars_seen, unsignedp);
generated by cgit v1.1 at 2025-05-29 12:29:35 +0000