1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292
|
/* This is an inclusion for Curses.c */
/* Combined Normal/Wide-Character helper functions */
/* April 2014, Edgar Fu, Mathematisches Institut der Universitt Bonn,
<ef@math.uni-bonn.de>
*/
#include <wchar.h>
#if HAVE_PERL_UVCHR_TO_UTF8
#define UVCHR_TO_UTF8 uvchr_to_utf8
#elif HAVE_PERL_UV_TO_UTF8
#define UVCHR_TO_UTF8 uv_to_utf8
#else
#error CursesWide.c cannot be compiled on this system; no uv[chr]_to_utf8
#endif
static UV
utf8_to_uvchr_buf_x(U8 * s,
U8 * end,
STRLEN * lenP) {
#if HAVE_PERL_UTF8_TO_UVCHR_BUF
return utf8_to_uvchr_buf(s, end, lenP);
#elif HAVE_PERL_UTF8_TO_UVCHR
return utf8_to_uvchr(s, lenP);
#elif HAVE_PERL_UTF8_TO_UV
return utf8_to_uv(s, end - s, lenP, 0);
#else
#error CursesWide.c cannot compile because \
there is no utf8_to_uvchr_buf, etc.
#endif
}
static void
c_wchar2sv(SV * const sv,
wchar_t const wc) {
/*----------------------------------------------------------------------------
Set SV to a one-character (not -byte!) Perl string holding a given wide
character
-----------------------------------------------------------------------------*/
if (wc <= 0xff) {
char s[] = { wc, 0 };
sv_setpv(sv, s);
SvPOK_on(sv);
SvUTF8_off(sv);
} else {
char s[UTF8_MAXBYTES + 1] = { 0 };
char *s_end = (char *)UVCHR_TO_UTF8((U8 *)s, wc);
*s_end = 0;
sv_setpv(sv, s);
SvPOK_on(sv);
SvUTF8_on(sv);
}
}
static void
c_bstr2sv(SV * const sv,
unsigned char * const bs) {
/*----------------------------------------------------------------------------
Set SV to a Perl string holding a given byte string
-----------------------------------------------------------------------------*/
SvPOK_on(sv);
sv_setpv(sv, (char *)bs);
SvUTF8_off(sv);
}
static void
c_wstr2sv(SV * const sv,
wchar_t * const ws) {
/*----------------------------------------------------------------------------
Set SV to a Perl string holding a given wide string
-----------------------------------------------------------------------------*/
size_t const wsLen = wcslen(ws);
bool needUtf8;
unsigned int i;
for (i = 0, needUtf8 = false; ws[i]; ++i) {
if (ws[i] > 0xff)
needUtf8 = true;
}
SvPOK_on(sv);
if (needUtf8) {
U8 * u8;
U8 * u8Cursor;
unsigned int i;
u8 = (U8 *)sv_grow(sv, (wsLen + 1) * UTF8_MAXBYTES);
for (i = 0, u8Cursor = &u8[0]; ws[i]; ++i)
u8Cursor = UVCHR_TO_UTF8(u8Cursor, ws[i]);
*u8Cursor = 0;
SvCUR_set(sv, u8Cursor - &u8[0]);
SvUTF8_on(sv);
} else {
U8 * u8;
unsigned int i;
u8 = (U8 *)sv_grow(sv, wsLen + 1);
for (i = 0; ws[i]; ++i)
u8[i] = ws[i];
u8[i] = 0;
SvCUR_set(sv, wsLen);
SvUTF8_off(sv);
}
}
static void
c_sv2GetWchar(SV * const sv,
wchar_t * const wcP,
bool * const succeededP) {
/*----------------------------------------------------------------------------
Extract a wide character from a SV holding a one-character Perl string
Fails (returning *succeededP false) iff SV doesn't hold a string or the
string is not one character long.
-----------------------------------------------------------------------------*/
if (!SvPOK(sv))
*succeededP = false;
else {
U8 * s;
STRLEN sLen;
s = (U8 *)SvPV(sv, sLen);
if (sLen == 0)
*succeededP = false;
else {
if (SvUTF8(sv)) {
STRLEN len;
UV uv;
uv = utf8_to_uvchr_buf_x(s, s + sLen, &len);
if (len != sLen)
*succeededP = false;
else {
*succeededP = true;
*wcP = (wchar_t)uv;
}
} else {
if (sLen != 1)
*succeededP = false;
else {
*succeededP = true;
*wcP = s[0];
}
}
}
}
}
static unsigned char *
c_sv2bstr(SV * const sv,
size_t * const b_len,
int * const need_free) {
/*----------------------------------------------------------------------------
Extract a char (byte) string from a SV holding a Perl string
Fails (returning NULL) if SV doesn't hold a string or the string has
characters not fitting into a byte or doesn't UTF-8 decode
Set b_len to length of result.
Caller must free() result if we set need_free.
-----------------------------------------------------------------------------*/
U8 *s, *s_p, *s_end;
STRLEN s_len;
unsigned char *bs, *bs_p;
if (!SvPOK(sv)) {
*need_free = 0;
return NULL;
}
s = (U8 *)SvPV(sv, s_len);
s_p = s;
s_end = s + s_len;
if (SvUTF8(sv)) {
bs = malloc(s_len + 1);
/* number of bytes is an upper bound on the number of characters */
if (bs == NULL) croak("c_sv2bstr: malloc");
bs_p = bs;
while (s_p < s_end) {
if (UTF8_IS_INVARIANT(*s_p)) {
*bs_p++ = *s_p++;
} else {
STRLEN len;
UV uv = utf8_to_uvchr_buf_x(s_p, s_end, &len);
if (uv > 0xff) {
*need_free = 0;
*b_len = 0;
return NULL;
}
*bs_p++ = uv;
s_p += len;
}
}
if (s_p != s_end) {
*need_free = 0;
*b_len = 0;
return NULL;
}
*bs_p = 0;
*b_len = s_len;
*need_free = 1;
return bs;
} else {
*need_free = 0;
*b_len = s_len;
return (unsigned char *)s;
}
}
static wchar_t *
c_sv2wstr(SV * const sv,
size_t * const wLenP) {
/*----------------------------------------------------------------------------
Extract a wide char string from a SV holding a Perl string.
Fails (returning NULL) if SV doesn't hold a string or doesn't UTF-8
decode.
set *wLenP to length of result.
Caller must free result
-----------------------------------------------------------------------------*/
wchar_t * ws;
if (!SvPOK(sv))
ws = NULL;
else {
STRLEN sLen;
U8 * s;
s = (U8 *)SvPV(sv, sLen);
ws = malloc((sLen + 1) * sizeof(ws[0]));
/* number of bytes is an upper bound on the number of characters */
if (!ws)
croak("c_sv2wstr: malloc");
if (SvUTF8(sv)) {
U8 * sP;
U8 * sEnd;
unsigned int i;
sP = &s[0];
sEnd = &s[sLen];
i = 0;
while (sP < sEnd) {
if (UTF8_IS_INVARIANT(*sP)) {
ws[i++] = *sP++;
} else {
STRLEN len;
ws[i++] = utf8_to_uvchr_buf_x(sP, sEnd, &len);
sP += len;
}
}
if (sP != sEnd) {
free(ws);
*wLenP = 0;
ws = NULL;
} else {
ws[i] = 0;
*wLenP = sLen;
}
} else {
unsigned int i;
for (i = 0; i < sLen; ++i)
ws[i] = s[i];
ws[i] = 0;
*wLenP = sLen;
}
}
return ws;
}
|