int main( void )
{
TESTCASE(iswcntrl(L'\0'));
TESTCASE(iswcntrl(L'\n'));
TESTCASE(iswcntrl(L'\v'));
TESTCASE(!iswcntrl(L'\t'));
TESTCASE(!iswcntrl(L'a'));
return TEST_RESULTS;
}
int get_trait (qse_wcint_t code)
{
int trait = 0;
if (iswupper(code)) trait |= TRAIT_UPPER;
if (iswlower(code)) trait |= TRAIT_LOWER;
if (iswalpha(code)) trait |= TRAIT_ALPHA;
if (iswdigit(code)) trait |= TRAIT_DIGIT;
if (iswxdigit(code)) trait |= TRAIT_XDIGIT;
if (iswalnum(code)) trait |= TRAIT_ALNUM;
if (iswspace(code)) trait |= TRAIT_SPACE;
if (iswprint(code)) trait |= TRAIT_PRINT;
if (iswgraph(code)) trait |= TRAIT_GRAPH;
if (iswcntrl(code)) trait |= TRAIT_CNTRL;
if (iswpunct(code)) trait |= TRAIT_PUNCT;
if (iswblank(code)) trait |= TRAIT_BLANK;
/*
if (iswascii(code)) trait |= TRAIT_ASCII;
if (isphonogram(code)) trait |= TRAIT_PHONO;
if (isideogram(code)) trait |= TRAIT_IDEOG;
if (isenglish(code)) trait |= TRAIT_ENGLI;
*/
return trait;
}
static int getboundedstring_cb(lua_State* L)
{
size_t size;
const char* start = luaL_checklstring(L, 1, &size);
const char* send = start + size;
int width = luaL_checkinteger(L, 2);
const char* s = start;
while (s < send)
{
const char* p = s;
wchar_t c = readu8(&s);
if (!iswcntrl(c))
{
width -= emu_wcwidth(c);
if (width < 0)
{
send = p;
break;
}
}
}
lua_pushlstring(L, start, send - start);
return 1;
}
int iswctype(wint_t wc, wctype_t type) {
switch (type) {
case WCTYPE_ALNUM:
return iswalnum(wc);
case WCTYPE_ALPHA:
return iswalpha(wc);
case WCTYPE_BLANK:
return iswblank(wc);
case WCTYPE_CNTRL:
return iswcntrl(wc);
case WCTYPE_DIGIT:
return iswdigit(wc);
case WCTYPE_GRAPH:
return iswgraph(wc);
case WCTYPE_LOWER:
return iswlower(wc);
case WCTYPE_PRINT:
return iswprint(wc);
case WCTYPE_PUNCT:
return iswpunct(wc);
case WCTYPE_SPACE:
return iswspace(wc);
case WCTYPE_UPPER:
return iswupper(wc);
case WCTYPE_XDIGIT:
return iswxdigit(wc);
}
return 0;
}
int BLC_PREFIX(iswctype)(wint_t wc, wctype_t desc)
{
switch (desc) {
case wctype_alnum:
return iswalnum(wc);
case wctype_alpha:
return iswalpha(wc);
case wctype_blank:
return iswblank(wc);
case wctype_cntrl:
return iswcntrl(wc);
case wctype_digit:
return iswdigit(wc);
case wctype_graph:
return iswgraph(wc);
case wctype_lower:
return iswlower(wc);
case wctype_print:
return iswprint(wc);
case wctype_punct:
return iswpunct(wc);
case wctype_space:
return iswspace(wc);
case wctype_upper:
return iswupper(wc);
case wctype_xdigit:
return iswxdigit(wc);
default:
return 0;
}
}
void
test1()
{
int i;
for (i = 0; i < 256; i++) {
printf(" %02x: ", i);
check_bool(isalnum(i), iswalnum(i), '1');
check_bool(isalpha(i), iswalpha(i), '2');
check_bool(isblank(i), iswblank(i), '3');
check_bool(iscntrl(i), iswcntrl(i), '4');
check_bool(isdigit(i), iswdigit(i), '5');
check_bool(isgraph(i), iswgraph(i), '6');
check_bool(islower(i), iswlower(i), '6');
check_bool(isprint(i), iswprint(i), '7');
check_bool(ispunct(i), iswpunct(i), '8');
check_bool(isspace(i), iswspace(i), '9');
check_bool(isupper(i), iswupper(i), 'a');
check_bool(isxdigit(i), iswxdigit(i), 'b');
check_value(tolower(i), towlower(i), 'c');
check_value(toupper(i), towupper(i), 'd');
if (i % 8 == 7)
printf("\n");
}
printf("%\n");
}
int
main ()
{
/* Check that the isw* functions exist as functions or as macros. */
(void) iswalnum (0);
(void) iswalpha (0);
#if 0 /* not portable: missing on mingw */
(void) iswblank (0);
#endif
(void) iswcntrl (0);
(void) iswdigit (0);
(void) iswgraph (0);
(void) iswlower (0);
(void) iswprint (0);
(void) iswpunct (0);
(void) iswspace (0);
(void) iswupper (0);
(void) iswxdigit (0);
/* Check that the isw* functions map WEOF to 0. */
ASSERT (!iswalnum (e));
ASSERT (!iswalpha (e));
#if 0 /* not portable: missing on mingw */
ASSERT (!iswblank (e));
#endif
ASSERT (!iswcntrl (e));
ASSERT (!iswdigit (e));
ASSERT (!iswgraph (e));
ASSERT (!iswlower (e));
ASSERT (!iswprint (e));
ASSERT (!iswpunct (e));
ASSERT (!iswspace (e));
ASSERT (!iswupper (e));
ASSERT (!iswxdigit (e));
/* Check that the tow* functions exist as functions or as macros. */
(void) towlower (0);
(void) towupper (0);
/* Check that the tow* functions map WEOF to WEOF. */
ASSERT (towlower (e) == e);
ASSERT (towupper (e) == e);
return 0;
}
int iswcntrl_l(wint_t c, struct __locale_t *locale)
{
/* Silence warning */
_CRT_UNUSED(locale);
/* We're using a locale-independent representation of upper/lower case
based on Unicode data. Thus, the locale doesn't matter. */
return iswcntrl (c);
}
int iswpunct(wint_t wc)
{
if (iswcntrl(wc) || iswalnum(wc) || iswspace(wc))
return 0;
// It's a printable character
// thats not alpha-numeric, or a space
// so its a punctuation character
return 1;
}
bool iswcntrl(wstring _String)
{
for (wstring::const_iterator iter = _String.begin(); iter != _String.end(); iter++)
{
if (!iswcntrl(*iter))
{
return false;
}
}
return true;
}
int
main (void)
{
/* Check that the isw* functions exist as functions or as macros. */
(void) iswalnum (0);
(void) iswalpha (0);
(void) iswcntrl (0);
(void) iswdigit (0);
(void) iswgraph (0);
(void) iswlower (0);
(void) iswprint (0);
(void) iswpunct (0);
(void) iswspace (0);
(void) iswupper (0);
(void) iswxdigit (0);
/* Check that the isw* functions map WEOF to 0. */
ASSERT (!iswalnum (e));
ASSERT (!iswalpha (e));
ASSERT (!iswcntrl (e));
ASSERT (!iswdigit (e));
ASSERT (!iswgraph (e));
ASSERT (!iswlower (e));
ASSERT (!iswprint (e));
ASSERT (!iswpunct (e));
ASSERT (!iswspace (e));
ASSERT (!iswupper (e));
ASSERT (!iswxdigit (e));
/* Check that the tow* functions exist as functions or as macros. */
(void) towlower (0);
(void) towupper (0);
/* Check that the tow* functions map WEOF to WEOF. */
ASSERT (towlower (e) == e);
ASSERT (towupper (e) == e);
return 0;
}
libedit_private int
ct_chr_class(wchar_t c)
{
if (c == '\t')
return CHTYPE_TAB;
else if (c == '\n')
return CHTYPE_NL;
else if (c < 0x100 && iswcntrl(c))
return CHTYPE_ASCIICTL;
else if (iswprint(c))
return CHTYPE_PRINT;
else
return CHTYPE_NONPRINT;
}
static int
scanner_error(mvc *lc, int cur)
{
switch (cur) {
case EOF:
(void) sql_error(lc, 1, "unexpected end of input");
return -1; /* EOF needs -1 result */
default:
/* on Windows at least, iswcntrl returns TRUE for
* U+FEFF, but we just want consistent error
* messages */
(void) sql_error(lc, 1, "unexpected%s character (U+%04X)", iswcntrl(cur) && cur != 0xFEFF ? " control" : "", cur);
}
return LEX_ERROR;
}
static int match_class (lua_WChar c, lua_WChar cl) {
int res;
switch (towlower(cl)) {
case 'a' : res = iswalpha(c); break;
case 'c' : res = iswcntrl(c); break;
case 'd' : res = iswdigit(c); break;
case 'l' : res = iswlower(c); break;
case 'p' : res = iswpunct(c); break;
case 's' : res = iswspace(c); break;
case 'u' : res = iswupper(c); break;
case 'w' : res = iswalnum(c); break;
case 'x' : res = iswxdigit(c); break;
case 'z' : res = (c == '\0'); break;
default: return (cl == c);
}
return (iswlower(cl) ? res : !res);
}
static int getstringwidth_cb(lua_State* L)
{
size_t size;
const char* s = luaL_checklstring(L, 1, &size);
const char* send = s + size;
int width = 0;
while (s < send)
{
wchar_t c = readu8(&s);
if (!iswcntrl(c))
width += emu_wcwidth(c);
}
lua_pushnumber(L, width);
return 1;
}
/* Determine if the given character is of the specified type. */
_WCRTLINK int iswctype( wint_t wc, wctype_t desc )
{
switch( desc ) {
case WCTYPE_ALNUM: return( iswalnum( wc ) );
case WCTYPE_ALPHA: return( iswalpha( wc ) );
case WCTYPE_BLANK: return( iswblank( wc ) );
case WCTYPE_CNTRL: return( iswcntrl( wc ) );
case WCTYPE_DIGIT: return( iswdigit( wc ) );
case WCTYPE_GRAPH: return( iswgraph( wc ) );
case WCTYPE_LOWER: return( iswlower( wc ) );
case WCTYPE_PRINT: return( iswprint( wc ) );
case WCTYPE_PUNCT: return( iswpunct( wc ) );
case WCTYPE_SPACE: return( iswspace( wc ) );
case WCTYPE_UPPER: return( iswupper( wc ) );
case WCTYPE_XDIGIT: return( iswxdigit( wc ) );
default: return( 0 );
}
}
static int write_cb(lua_State* L)
{
int x = luaL_checkint(L, 1);
int y = luaL_checkint(L, 2);
size_t size;
const char* s = luaL_checklstring(L, 3, &size);
const char* send = s + size;
while (s < send)
{
wchar_t c = readu8(&s);
dpy_writechar(x, y, c);
if (!iswcntrl(c))
x += emu_wcwidth(c);
}
return 0;
}
static wchar_t *
cpbReadScreen (size_t *length, int fromColumn, int fromRow, int toColumn, int toRow) {
wchar_t *newBuffer = NULL;
int columns = toColumn - fromColumn + 1;
int rows = toRow - fromRow + 1;
if ((columns >= 1) && (rows >= 1) && (beginOffset >= 0)) {
wchar_t fromBuffer[rows * columns];
if (readScreenText(fromColumn, fromRow, columns, rows, fromBuffer)) {
wchar_t toBuffer[rows * (columns + 1)];
wchar_t *toAddress = toBuffer;
const wchar_t *fromAddress = fromBuffer;
int row;
for (row=fromRow; row<=toRow; row+=1) {
int column;
for (column=fromColumn; column<=toColumn; column+=1) {
wchar_t character = *fromAddress++;
if (iswcntrl(character) || iswspace(character)) character = WC_C(' ');
*toAddress++ = character;
}
if (row != toRow) *toAddress++ = WC_C('\r');
}
/* make a new permanent buffer of just the right size */
{
size_t newLength = toAddress - toBuffer;
if ((newBuffer = cpbAllocateCharacters(newLength))) {
wmemcpy(newBuffer, toBuffer, (*length = newLength));
}
}
}
}
return newBuffer;
}
static void TranslateToDos(doscp_t *toDos, const char *in, char *out, int count,
char *end, Case_t *Case, int *mangled)
{
wchar_t buffer[12];
wchar_t *s=buffer;
wchar_t *t=buffer;
/* first convert to wchar, so we get to use towupper etc. */
native_to_wchar(in, buffer, count, end, mangled);
buffer[count]='\0';
*Case = NONE;
for( ; *s ; s++) {
/* skip spaces & dots */
if(*s == ' ' || *s == '.') {
*mangled |= 3;
continue;
}
if (iswcntrl(*s)) {
/* "control" characters */
*mangled |= 3;
*t = '_';
} else if (iswlower(*s)) {
*t = towupper(*s);
if(*Case == UPPER && !mtools_no_vfat)
*mangled |= 1;
else
*Case = LOWER;
} else if (iswupper(*s)) {
*t = *s;
if(*Case == LOWER && !mtools_no_vfat)
*mangled |= 1;
else
*Case = UPPER;
} else
*t = *s;
t++;
}
wchar_to_dos(toDos, buffer, out, t - buffer, mangled);
}
int
main ()
{
/* Check that the isw* functions exist as functions or as macros. */
iswalnum (0);
iswalpha (0);
#if 0 /* not portable: missing on mingw */
iswblank (0);
#endif
iswcntrl (0);
iswdigit (0);
iswgraph (0);
iswlower (0);
iswprint (0);
iswpunct (0);
iswspace (0);
iswupper (0);
iswxdigit (0);
return 0;
}
void wctype_check_functions(wint_t i, wctype_t t, wctrans_t tr, locale_t l)
{
(void)iswalnum(i);
(void)iswalnum_l(i, l);
(void)iswalpha(i);
(void)iswalpha_l(i, l);
(void)iswblank(i);
(void)iswblank_l(i, l);
(void)iswcntrl(i);
(void)iswcntrl_l(i, l);
(void)iswctype(i, t);
(void)iswctype_l(i, t, l);
(void)iswdigit(i);
(void)iswdigit_l(i, l);
(void)iswgraph(i);
(void)iswgraph_l(i, l);
(void)iswlower(i);
(void)iswlower_l(i, l);
(void)iswprint(i);
(void)iswprint_l(i, l);
(void)iswpunct(i);
(void)iswpunct_l(i, l);
(void)iswspace(i);
(void)iswspace_l(i, l);
(void)iswupper(i);
(void)iswupper_l(i, l);
(void)iswxdigit(i);
(void)iswxdigit_l(i, l);
(void)towctrans(i, tr);
(void)towctrans_l(i, tr, l);
(void)towlower(i);
(void)towlower_l(i, l);
(void)towupper(i);
(void)towupper_l(i, l);
(void)wctrans((const char *)1234);
(void)wctrans_l((const char *)1234, l);
(void)wctype((const char *)1234);
(void)wctype_l((const char *)1234, l);
}
bool NWChar::IsControl(wchar_t c)
{
return iswcntrl(c);
}
/* Returns the number of columns needed to represent the multibyte
character string pointed to by STRING of length NBYTES. If a
non-printable character occurs, and MBSW_REJECT_UNPRINTABLE is
specified, -1 is returned. */
int
mbsnwidth (const char *string, size_t nbytes, int flags)
{
const char *p = string;
const char *plimit = p + nbytes;
int width;
width = 0;
if (MB_CUR_MAX > 1)
{
while (p < plimit)
switch (*p)
{
case ' ': case '!': case '"': case '#': case '%':
case '&': case '\'': case '(': case ')': case '*':
case '+': case ',': case '-': case '.': case '/':
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
case ':': case ';': case '<': case '=': case '>':
case '?':
case 'A': case 'B': case 'C': case 'D': case 'E':
case 'F': case 'G': case 'H': case 'I': case 'J':
case 'K': case 'L': case 'M': case 'N': case 'O':
case 'P': case 'Q': case 'R': case 'S': case 'T':
case 'U': case 'V': case 'W': case 'X': case 'Y':
case 'Z':
case '[': case '\\': case ']': case '^': case '_':
case 'a': case 'b': case 'c': case 'd': case 'e':
case 'f': case 'g': case 'h': case 'i': case 'j':
case 'k': case 'l': case 'm': case 'n': case 'o':
case 'p': case 'q': case 'r': case 's': case 't':
case 'u': case 'v': case 'w': case 'x': case 'y':
case 'z': case '{': case '|': case '}': case '~':
/* These characters are printable ASCII characters. */
p++;
width++;
break;
default:
/* If we have a multibyte sequence, scan it up to its end. */
{
mbstate_t mbstate;
memset (&mbstate, 0, sizeof mbstate);
do
{
wchar_t wc;
size_t bytes;
int w;
bytes = mbrtowc (&wc, p, plimit - p, &mbstate);
if (bytes == (size_t) -1)
/* An invalid multibyte sequence was encountered. */
{
if (!(flags & MBSW_REJECT_INVALID))
{
p++;
width++;
break;
}
else
return -1;
}
if (bytes == (size_t) -2)
/* An incomplete multibyte character at the end. */
{
if (!(flags & MBSW_REJECT_INVALID))
{
p = plimit;
width++;
break;
}
else
return -1;
}
if (bytes == 0)
/* A null wide character was encountered. */
bytes = 1;
w = wcwidth (wc);
if (w >= 0)
/* A printable multibyte character. */
{
if (w > INT_MAX - width)
goto overflow;
width += w;
}
else
/* An unprintable multibyte character. */
if (!(flags & MBSW_REJECT_UNPRINTABLE))
{
if (!iswcntrl (wc))
{
if (width == INT_MAX)
goto overflow;
width++;
}
}
else
return -1;
p += bytes;
}
while (! mbsinit (&mbstate));
}
break;
}
return width;
}
while (p < plimit)
{
unsigned char c = (unsigned char) *p++;
if (isprint (c))
{
if (width == INT_MAX)
goto overflow;
width++;
}
else if (!(flags & MBSW_REJECT_UNPRINTABLE))
{
if (!iscntrl (c))
{
if (width == INT_MAX)
goto overflow;
width++;
}
}
else
return -1;
}
return width;
overflow:
return INT_MAX;
}
const bool needs_escape(const wint_t _char)
{
// Escaping is needed for control characters,
// for double quote, and for backslash :
return iswcntrl(_char) || (_char == '"') || (_char == '\\');
}
int __iswcntrl_l(wint_t c, locale_t l) {
return iswcntrl(c);
}
/// <summary>Convert string into a list of phrases with contiguous formatting</summary>
/// <param name="str">string.</param>
/// <returns>List of phrases</returns>
PhraseList RichTextRenderer::GetPhrases(const RichString& str)
{
// space char as a RichCharacter
static RichCharacter space(' ', Colour::Default, NULL);
// lambda for assembling phrases
static function<void (PhraseList& list, const RichCharacter*)> buildPhrases = [](PhraseList& list, const RichCharacter* ch)
{
// Init: Start first phrase
if (list.empty())
list += RichPhrase(iswcntrl(ch->Char) ? space : *ch);
else
{
RichPhrase& current = list.back();
// CRLF: Replace with space
if (iswcntrl(ch->Char))
current += ' ';
// Create new phrase if colour/formatting changes
else if (ch->Colour != current.Colour
|| ch->Format != current.Format)
list += RichPhrase(*ch);
else
// Otherwise append to last phrase
current += ch->Char;
}
};
PhraseList phrases;
// Author: Manual insert
if (str.Author.length())
{
// Parse colours + formatting
for (auto& ch : RichStringParser(str.Author).Output.Characters)
buildPhrases(phrases, ch);
// Spacing phrase
phrases += RichPhrase(L" ", NULL, Colour::Default);
}
// Title: Manual insert
if (str.Title.length())
{
// Parse colours + formatting
for (auto& ch : RichStringParser(str.Title).Output.Characters)
buildPhrases(phrases, ch);
// Spacing phrase
phrases += RichPhrase(L" ", NULL, Colour::Default);
}
// Embolden author/title, if any
for (auto& p : phrases)
{
p.Format |= CFE_BOLD;
p.CustomFont = L"Times New Roman";
}
// Assemble phrases
for (const RichCharacter* ch : str.Characters)
buildPhrases(phrases, ch);
return phrases;
}
static int
processStream (FILE *inputStream, const char *inputName) {
mbstate_t inputState;
mbstate_t outputState;
memset(&inputState, 0, sizeof(inputState));
memset(&outputState, 0, sizeof(outputState));
while (!feof(inputStream)) {
char inputBuffer[0X1000];
size_t inputCount = fread(inputBuffer, 1, sizeof(inputBuffer), inputStream);
if (ferror(inputStream)) goto inputError;
if (!inputCount) break;
{
char *byte = inputBuffer;
while (inputCount) {
wchar_t character;
{
size_t result = mbrtowc(&character, byte, inputCount, &inputState);
if (result == (size_t)-2) break;
if (result == (size_t)-1) goto inputError;
if (!result) result = 1;
byte += result;
inputCount -= result;
}
if (!iswcntrl(character)) {
unsigned char dots = toDots(character);
if (dots || !iswspace(character)) {
if (opt_sixDots) dots &= ~(BRL_DOT_7 | BRL_DOT_8);
character = toCharacter(dots);
}
}
if (!writeCharacter(&character, &outputState)) goto outputError;
}
}
}
if (!writeCharacter(NULL, &outputState)) goto outputError;
fflush(outputStream);
if (ferror(outputStream)) goto outputError;
if (!mbsinit(&inputState)) {
#ifdef EILSEQ
errno = EILSEQ;
#else /* EILSEQ */
errno = EINVAL;
#endif /* EILSEQ */
goto inputError;
}
return 1;
inputError:
logMessage(LOG_ERR, "input error: %s: %s", inputName, strerror(errno));
return 0;
outputError:
logMessage(LOG_ERR, "output error: %s: %s", outputName, strerror(errno));
return 0;
}
inline bool wcs_whitespace(const wchar_t c)
{
return (c) && (iswcntrl(c) || iswspace(c)); //return (c == L' ') || (c == L'\t') || (c == L'\n') || (c == L'\r');
}
int __wcwidth(__CONST wint_t ucs)
{
#ifdef _MB_CAPABLE
/* sorted list of non-overlapping intervals of East Asian Ambiguous
* characters, generated by "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" */
static const struct interval ambiguous[] = {
{ 0x00A1, 0x00A1 }, { 0x00A4, 0x00A4 }, { 0x00A7, 0x00A8 },
{ 0x00AA, 0x00AA }, { 0x00AE, 0x00AE }, { 0x00B0, 0x00B4 },
{ 0x00B6, 0x00BA }, { 0x00BC, 0x00BF }, { 0x00C6, 0x00C6 },
{ 0x00D0, 0x00D0 }, { 0x00D7, 0x00D8 }, { 0x00DE, 0x00E1 },
{ 0x00E6, 0x00E6 }, { 0x00E8, 0x00EA }, { 0x00EC, 0x00ED },
{ 0x00F0, 0x00F0 }, { 0x00F2, 0x00F3 }, { 0x00F7, 0x00FA },
{ 0x00FC, 0x00FC }, { 0x00FE, 0x00FE }, { 0x0101, 0x0101 },
{ 0x0111, 0x0111 }, { 0x0113, 0x0113 }, { 0x011B, 0x011B },
{ 0x0126, 0x0127 }, { 0x012B, 0x012B }, { 0x0131, 0x0133 },
{ 0x0138, 0x0138 }, { 0x013F, 0x0142 }, { 0x0144, 0x0144 },
{ 0x0148, 0x014B }, { 0x014D, 0x014D }, { 0x0152, 0x0153 },
{ 0x0166, 0x0167 }, { 0x016B, 0x016B }, { 0x01CE, 0x01CE },
{ 0x01D0, 0x01D0 }, { 0x01D2, 0x01D2 }, { 0x01D4, 0x01D4 },
{ 0x01D6, 0x01D6 }, { 0x01D8, 0x01D8 }, { 0x01DA, 0x01DA },
{ 0x01DC, 0x01DC }, { 0x0251, 0x0251 }, { 0x0261, 0x0261 },
{ 0x02C4, 0x02C4 }, { 0x02C7, 0x02C7 }, { 0x02C9, 0x02CB },
{ 0x02CD, 0x02CD }, { 0x02D0, 0x02D0 }, { 0x02D8, 0x02DB },
{ 0x02DD, 0x02DD }, { 0x02DF, 0x02DF }, { 0x0391, 0x03A1 },
{ 0x03A3, 0x03A9 }, { 0x03B1, 0x03C1 }, { 0x03C3, 0x03C9 },
{ 0x0401, 0x0401 }, { 0x0410, 0x044F }, { 0x0451, 0x0451 },
{ 0x2010, 0x2010 }, { 0x2013, 0x2016 }, { 0x2018, 0x2019 },
{ 0x201C, 0x201D }, { 0x2020, 0x2022 }, { 0x2024, 0x2027 },
{ 0x2030, 0x2030 }, { 0x2032, 0x2033 }, { 0x2035, 0x2035 },
{ 0x203B, 0x203B }, { 0x203E, 0x203E }, { 0x2074, 0x2074 },
{ 0x207F, 0x207F }, { 0x2081, 0x2084 }, { 0x20AC, 0x20AC },
{ 0x2103, 0x2103 }, { 0x2105, 0x2105 }, { 0x2109, 0x2109 },
{ 0x2113, 0x2113 }, { 0x2116, 0x2116 }, { 0x2121, 0x2122 },
{ 0x2126, 0x2126 }, { 0x212B, 0x212B }, { 0x2153, 0x2154 },
{ 0x215B, 0x215E }, { 0x2160, 0x216B }, { 0x2170, 0x2179 },
{ 0x2190, 0x2199 }, { 0x21B8, 0x21B9 }, { 0x21D2, 0x21D2 },
{ 0x21D4, 0x21D4 }, { 0x21E7, 0x21E7 }, { 0x2200, 0x2200 },
{ 0x2202, 0x2203 }, { 0x2207, 0x2208 }, { 0x220B, 0x220B },
{ 0x220F, 0x220F }, { 0x2211, 0x2211 }, { 0x2215, 0x2215 },
{ 0x221A, 0x221A }, { 0x221D, 0x2220 }, { 0x2223, 0x2223 },
{ 0x2225, 0x2225 }, { 0x2227, 0x222C }, { 0x222E, 0x222E },
{ 0x2234, 0x2237 }, { 0x223C, 0x223D }, { 0x2248, 0x2248 },
{ 0x224C, 0x224C }, { 0x2252, 0x2252 }, { 0x2260, 0x2261 },
{ 0x2264, 0x2267 }, { 0x226A, 0x226B }, { 0x226E, 0x226F },
{ 0x2282, 0x2283 }, { 0x2286, 0x2287 }, { 0x2295, 0x2295 },
{ 0x2299, 0x2299 }, { 0x22A5, 0x22A5 }, { 0x22BF, 0x22BF },
{ 0x2312, 0x2312 }, { 0x2460, 0x24E9 }, { 0x24EB, 0x254B },
{ 0x2550, 0x2573 }, { 0x2580, 0x258F }, { 0x2592, 0x2595 },
{ 0x25A0, 0x25A1 }, { 0x25A3, 0x25A9 }, { 0x25B2, 0x25B3 },
{ 0x25B6, 0x25B7 }, { 0x25BC, 0x25BD }, { 0x25C0, 0x25C1 },
{ 0x25C6, 0x25C8 }, { 0x25CB, 0x25CB }, { 0x25CE, 0x25D1 },
{ 0x25E2, 0x25E5 }, { 0x25EF, 0x25EF }, { 0x2605, 0x2606 },
{ 0x2609, 0x2609 }, { 0x260E, 0x260F }, { 0x2614, 0x2615 },
{ 0x261C, 0x261C }, { 0x261E, 0x261E }, { 0x2640, 0x2640 },
{ 0x2642, 0x2642 }, { 0x2660, 0x2661 }, { 0x2663, 0x2665 },
{ 0x2667, 0x266A }, { 0x266C, 0x266D }, { 0x266F, 0x266F },
{ 0x273D, 0x273D }, { 0x2776, 0x277F }, { 0xE000, 0xF8FF },
{ 0xFFFD, 0xFFFD }, { 0xF0000, 0xFFFFD }, { 0x100000, 0x10FFFD }
};
/* sorted list of non-overlapping intervals of non-spacing characters */
/* generated by "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c" */
static const struct interval combining[] = {
{ 0x0300, 0x036F }, { 0x0483, 0x0486 }, { 0x0488, 0x0489 },
{ 0x0591, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 },
{ 0x05C4, 0x05C5 }, { 0x05C7, 0x05C7 }, { 0x0600, 0x0603 },
{ 0x0610, 0x0615 }, { 0x064B, 0x065E }, { 0x0670, 0x0670 },
{ 0x06D6, 0x06E4 }, { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED },
{ 0x070F, 0x070F }, { 0x0711, 0x0711 }, { 0x0730, 0x074A },
{ 0x07A6, 0x07B0 }, { 0x07EB, 0x07F3 }, { 0x0901, 0x0902 },
{ 0x093C, 0x093C }, { 0x0941, 0x0948 }, { 0x094D, 0x094D },
{ 0x0951, 0x0954 }, { 0x0962, 0x0963 }, { 0x0981, 0x0981 },
{ 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 }, { 0x09CD, 0x09CD },
{ 0x09E2, 0x09E3 }, { 0x0A01, 0x0A02 }, { 0x0A3C, 0x0A3C },
{ 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D },
{ 0x0A70, 0x0A71 }, { 0x0A81, 0x0A82 }, { 0x0ABC, 0x0ABC },
{ 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 }, { 0x0ACD, 0x0ACD },
{ 0x0AE2, 0x0AE3 }, { 0x0B01, 0x0B01 }, { 0x0B3C, 0x0B3C },
{ 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B43 }, { 0x0B4D, 0x0B4D },
{ 0x0B56, 0x0B56 }, { 0x0B82, 0x0B82 }, { 0x0BC0, 0x0BC0 },
{ 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 }, { 0x0C46, 0x0C48 },
{ 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 }, { 0x0CBC, 0x0CBC },
{ 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD },
{ 0x0CE2, 0x0CE3 }, { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D },
{ 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 },
{ 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E },
{ 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC },
{ 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 },
{ 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E },
{ 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 },
{ 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 },
{ 0x1032, 0x1032 }, { 0x1036, 0x1037 }, { 0x1039, 0x1039 },
{ 0x1058, 0x1059 }, { 0x1160, 0x11FF }, { 0x135F, 0x135F },
{ 0x1712, 0x1714 }, { 0x1732, 0x1734 }, { 0x1752, 0x1753 },
{ 0x1772, 0x1773 }, { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD },
{ 0x17C6, 0x17C6 }, { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD },
{ 0x180B, 0x180D }, { 0x18A9, 0x18A9 }, { 0x1920, 0x1922 },
{ 0x1927, 0x1928 }, { 0x1932, 0x1932 }, { 0x1939, 0x193B },
{ 0x1A17, 0x1A18 }, { 0x1B00, 0x1B03 }, { 0x1B34, 0x1B34 },
{ 0x1B36, 0x1B3A }, { 0x1B3C, 0x1B3C }, { 0x1B42, 0x1B42 },
{ 0x1B6B, 0x1B73 }, { 0x1DC0, 0x1DCA }, { 0x1DFE, 0x1DFF },
{ 0x200B, 0x200F }, { 0x202A, 0x202E }, { 0x2060, 0x2063 },
{ 0x206A, 0x206F }, { 0x20D0, 0x20EF }, { 0x302A, 0x302F },
{ 0x3099, 0x309A }, { 0xA806, 0xA806 }, { 0xA80B, 0xA80B },
{ 0xA825, 0xA826 }, { 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F },
{ 0xFE20, 0xFE23 }, { 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB },
{ 0x10A01, 0x10A03 }, { 0x10A05, 0x10A06 }, { 0x10A0C, 0x10A0F },
{ 0x10A38, 0x10A3A }, { 0x10A3F, 0x10A3F }, { 0x1D167, 0x1D169 },
{ 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B }, { 0x1D1AA, 0x1D1AD },
{ 0x1D242, 0x1D244 }, { 0xE0001, 0xE0001 }, { 0xE0020, 0xE007F },
{ 0xE0100, 0xE01EF }
};
/* Test for NUL character */
if (ucs == 0)
return 0;
/* Test for printable ASCII characters */
if (ucs >= 0x20 && ucs < 0x7f)
return 1;
/* Test for control characters */
if (ucs < 0xa0)
return -1;
/* Test for surrogate pair values. */
if (ucs >= 0xd800 && ucs <= 0xdfff)
return -1;
/* binary search in table of ambiguous characters */
if (__locale_cjk_lang ()
&& bisearch(ucs, ambiguous,
sizeof(ambiguous) / sizeof(struct interval) - 1))
return 2;
/* binary search in table of non-spacing characters */
if (bisearch(ucs, combining,
sizeof(combining) / sizeof(struct interval) - 1))
return 0;
/* if we arrive here, ucs is not a combining or C0/C1 control character */
return 1 +
(ucs >= 0x1100 &&
(ucs <= 0x115f || /* Hangul Jamo init. consonants */
ucs == 0x2329 || ucs == 0x232a ||
(ucs >= 0x2e80 && ucs <= 0xa4cf &&
ucs != 0x303f) || /* CJK ... Yi */
(ucs >= 0xac00 && ucs <= 0xd7a3) || /* Hangul Syllables */
(ucs >= 0xf900 && ucs <= 0xfaff) || /* CJK Compatibility Ideographs */
(ucs >= 0xfe10 && ucs <= 0xfe19) || /* Vertical forms */
(ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */
(ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */
(ucs >= 0xffe0 && ucs <= 0xffe6) ||
(ucs >= 0x20000 && ucs <= 0x2fffd) ||
(ucs >= 0x30000 && ucs <= 0x3fffd)));
#else /* !_MB_CAPABLE */
if (iswprint (ucs))
return 1;
if (iswcntrl (ucs) || ucs == L'\0')
return 0;
return -1;
#endif /* _MB_CAPABLE */
}
void
test2()
{
unsigned char *s;
unsigned char *buf;
int i, j;
size_t n;
wchar_t c, d;
mbstate_t state;
s = malloc(256);
if (!s) {
bad++;
return;
}
buf = malloc(MB_CUR_MAX);
if (!buf) {
bad++;
free(s);
return;
}
for (i = 0; i < 256; i++)
s[i] = i+1;
j = 0;
mbrtowc(NULL, NULL, 1, &state);
printf(" %02x: ", 0);
while ((n = mbrtowc(&c, s+j, 256-j, &state)) == 1) {
printf(" %02x: ", s[j]);
check_bool(isalnum(s[j]), iswalnum(c), '1');
check_bool(isalpha(s[j]), iswalpha(c), '2');
check_bool(isblank(s[j]), iswblank(c), '3');
check_bool(iscntrl(s[j]), iswcntrl(c), '4');
check_bool(isdigit(s[j]), iswdigit(c), '5');
check_bool(isgraph(s[j]), iswgraph(c), '6');
check_bool(islower(s[j]), iswlower(c), '6');
check_bool(isprint(s[j]), iswprint(c), '7');
check_bool(ispunct(s[j]), iswpunct(c), '8');
check_bool(isspace(s[j]), iswspace(c), '9');
check_bool(isupper(s[j]), iswupper(c), 'a');
check_bool(isxdigit(s[j]), iswxdigit(c), 'b');
d = towlower(c);
if (wctomb(buf, d) == 1) {
check_value(tolower(s[j]), buf[0], 'c');
} else {
bad++;
}
d = towupper(c);
if (wctomb(buf, d) == 1) {
check_value(toupper(s[j]), buf[0], 'c');
} else {
bad++;
}
if (s[j] % 8 == 7)
printf("\n");
j++;
}
if (n != 0 || j != 255) {
bad++;
}
free(s);
free(buf);
}
