static int
pg_wc_isspace(pg_wchar c)
{
switch (pg_regex_strategy)
{
case PG_REGEX_LOCALE_C:
return (c <= (pg_wchar) 127 &&
(pg_char_properties[c] & PG_ISSPACE));
case PG_REGEX_LOCALE_WIDE:
#ifdef USE_WIDE_UPPER_LOWER
if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
return iswspace((wint_t) c);
#endif
/* FALL THRU */
case PG_REGEX_LOCALE_1BYTE:
return (c <= (pg_wchar) UCHAR_MAX &&
isspace((unsigned char) c));
case PG_REGEX_LOCALE_WIDE_L:
#if defined(HAVE_LOCALE_T) && defined(USE_WIDE_UPPER_LOWER)
if (sizeof(wchar_t) >= 4 || c <= (pg_wchar) 0xFFFF)
return iswspace_l((wint_t) c, pg_regex_locale);
#endif
/* FALL THRU */
case PG_REGEX_LOCALE_1BYTE_L:
#ifdef HAVE_LOCALE_T
return (c <= (pg_wchar) UCHAR_MAX &&
isspace_l((unsigned char) c, pg_regex_locale));
#endif
break;
}
return 0; /* can't get here, but keep compiler quiet */
}
void testValues() {
f = 2;
int result;
result = iswspace_l(anychar(), locale());
//@ assert f == 2;
//@ assert vacuous: \false;
}
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);
}
double
_wcstod_l (struct _reent *ptr, const wchar_t *nptr, wchar_t **endptr,
locale_t loc)
{
static const mbstate_t initial;
mbstate_t mbs;
double val;
char *buf, *end;
const wchar_t *wcp;
size_t len;
while (iswspace_l(*nptr, loc))
nptr++;
/*
* Convert the supplied numeric wide char. string to multibyte.
*
* We could attempt to find the end of the numeric portion of the
* wide char. string to avoid converting unneeded characters but
* choose not to bother; optimising the uncommon case where
* the input string contains a lot of text after the number
* duplicates a lot of strtod()'s functionality and slows down the
* most common cases.
*/
wcp = nptr;
mbs = initial;
if ((len = _wcsnrtombs_l(ptr, NULL, &wcp, (size_t) -1, 0, &mbs, loc))
== (size_t) -1) {
if (endptr != NULL)
*endptr = (wchar_t *)nptr;
return (0.0);
}
if ((buf = _malloc_r(ptr, len + 1)) == NULL)
return (0.0);
mbs = initial;
_wcsnrtombs_l(ptr, buf, &wcp, (size_t) -1, len + 1, &mbs, loc);
/* Let strtod() do most of the work for us. */
val = _strtod_l(ptr, buf, &end, loc);
/*
* We only know where the number ended in the _multibyte_
* representation of the string. If the caller wants to know
* where it ended, count multibyte characters to find the
* corresponding position in the wide char string.
*/
if (endptr != NULL) {
/* The only valid multibyte char in a float converted by
strtod/wcstod is the radix char. What we do here is,
figure out if the radix char was in the valid leading
float sequence in the incoming string. If so, the
multibyte float string is strlen(radix char) - 1 bytes
longer than the incoming wide char string has characters.
To fix endptr, reposition end as if the radix char was
just one byte long. The resulting difference (end - buf)
is then equivalent to the number of valid wide characters
in the input string. */
len = strlen (__localeconv_l (loc)->decimal_point);
if (len > 1) {
char *d = strstr (buf,
__localeconv_l (loc)->decimal_point);
if (d && d < end)
end -= len - 1;
}
*endptr = (wchar_t *)nptr + (end - buf);
}
_free_r(ptr, buf);
return (val);
}
void shorten_name(const char *name,
char short_name[512], char shortest_name[512])
{
wchar_t w_name[512];
wchar_t w_short_name[512];
wchar_t w_shortest_name[512];
const wchar_t *cur_word, *wchar_ptr;
wchar_t *cur_short_word, *cur_shortest_word;
int unabbrev = 0;
int i, len, new_len, capital;
if (!name)
return;
mbsrtowcs_l(w_name, &name, ARRAY_SIZE(w_name), NULL, l);
/* TODO: also skip anything in parenthesis from the short names */
/* TODO: instead of calling wcscasecmp_l all the time it'd be more
* effective to lower case w_name once and use plain wcscmp or mem
* compare since the phrases we search for are all lower case already.
* Might also want to take "collation" into account (wcsxfrm_l the
* string once and use memcmp instead of wcscoll_l).
*/
cur_word = w_name;
cur_short_word = w_short_name;
cur_shortest_word = w_shortest_name;
while (1) {
while (*cur_word && !iswalnum_l(*cur_word, l))
*cur_short_word ++ = *cur_shortest_word ++ = *cur_word ++;
if (!*cur_word)
break;
/* TODO: use a hash of some kind instead of iterating over arrays */
/* Go through possible abbreviations from top to bottom */
for (i = 0; i < ARRAY_SIZE(abbrevs); i += 2)
if (!wcsncasecmp_l(abbrevs[i], cur_word, wcslen(abbrevs[i]), l)) {
len = wcslen(abbrevs[i]);
/* Check that we matched a full word */
if (iswalnum_l(cur_word[len], l))
continue;
capital = iswupper_l(*cur_word, l);
cur_word += len;
new_len = wcslen(abbrevs[i + 1]);
memcpy(cur_short_word, abbrevs[i + 1],
new_len * sizeof(wchar_t));
/*
* If original was capitalised then capitalise the abbreviation
* as well, if it was lower case.
*/
if (capital)
*cur_short_word = towupper_l(*cur_short_word, l);
/* Make sure shortest_word doesn't end up being empty */
if (!*cur_word && !unabbrev) {
memcpy(cur_shortest_word, cur_short_word,
new_len * sizeof(wchar_t));
cur_shortest_word += new_len;
}
cur_short_word += new_len;
/*
* Avoid excess whitespace in short and shortest
* when a word is replaced with "".
* TODO: this may require more complicated logic to get
* the corner cases right.
*/
if (new_len == 0) {
if (cur_short_word > w_short_name &&
iswspace_l(cur_short_word[-1], l))
cur_short_word --;
if (cur_shortest_word > w_shortest_name &&
iswspace_l(cur_shortest_word[-1], l))
cur_shortest_word --;
}
/*if (new_len != len)*/
break;
}
if (i < ARRAY_SIZE(abbrevs))
continue;
/* Go through possible given names from top to bottom */
for (i = 0; i < ARRAY_SIZE(given_names); i ++)
if (!wcsncasecmp_l(given_names[i], cur_word,
wcslen(given_names[i]), l)) {
len = wcslen(given_names[i]);
/* Check that we matched a full word */
if (iswalnum_l(cur_word[len], l))
continue;
/*
* If this is the final part of the name, and it matches a
* given name then that's most likely somebody's surname which
* happens to also be a possibble given name. In that case
* do not abbreviate or omit it.
*/
if (!cur_word[len])
continue;
cur_word += len;
*cur_short_word++ = given_names[i][0];
*cur_short_word++ = L'.';
/*
* Avoid excess whitespace in shortest when a word is
* replaced with "".
* TODO: this may require more complicated logic to get
* the corner cases right.
*/
if (cur_shortest_word > w_shortest_name &&
iswspace_l(cur_shortest_word[-1], l))
cur_shortest_word --;
break;
}
if (i < ARRAY_SIZE(given_names))
continue;
/* Nothing matched, copy the current word as-is */
while (iswalnum_l(*cur_word, l))
*cur_short_word ++ = *cur_shortest_word ++ = *cur_word ++;
unabbrev += 1;
}
*cur_short_word = 0;
*cur_shortest_word = 0;
wchar_ptr = w_short_name;
wcsrtombs_l(short_name, &wchar_ptr, 512, NULL, l);
wchar_ptr = w_shortest_name;
wcsrtombs_l(shortest_name, &wchar_ptr, 512, NULL, l);
}
/*
* Convert a wide string to a long long integer.
*/
long long
_wcstoll_l (struct _reent *rptr, const wchar_t *nptr, wchar_t **endptr,
int base, locale_t loc)
{
register const wchar_t *s = nptr;
register unsigned long long acc;
register int c;
register unsigned long long cutoff;
register int neg = 0, any, cutlim;
/*
* Skip white space and pick up leading +/- sign if any.
* If base is 0, allow 0x for hex and 0 for octal, else
* assume decimal; if base is already 16, allow 0x.
*/
do {
c = *s++;
} while (iswspace_l(c, loc));
if (c == L'-') {
neg = 1;
c = *s++;
} else if (c == L'+')
c = *s++;
if ((base == 0 || base == 16) &&
c == L'0' && (*s == L'x' || *s == L'X')) {
c = s[1];
s += 2;
base = 16;
}
if (base == 0)
base = c == L'0' ? 8 : 10;
/*
* Compute the cutoff value between legal numbers and illegal
* numbers. That is the largest legal value, divided by the
* base. An input number that is greater than this value, if
* followed by a legal input character, is too big. One that
* is equal to this value may be valid or not; the limit
* between valid and invalid numbers is then based on the last
* digit. For instance, if the range for longs is
* [-2147483648..2147483647] and the input base is 10,
* cutoff will be set to 214748364 and cutlim to either
* 7 (neg==0) or 8 (neg==1), meaning that if we have accumulated
* a value > 214748364, or equal but the next digit is > 7 (or 8),
* the number is too big, and we will return a range error.
*
* Set any if any `digits' consumed; make it negative to indicate
* overflow.
*/
cutoff = neg ? -(unsigned long long)LONG_LONG_MIN : LONG_LONG_MAX;
cutlim = cutoff % (unsigned long long)base;
cutoff /= (unsigned long long)base;
for (acc = 0, any = 0;; c = *s++) {
if (c >= L'0' && c <= L'9')
c -= L'0';
else if (c >= L'A' && c <= L'Z')
c -= L'A' - 10;
else if (c >= L'a' && c <= L'z')
c -= L'a' - 10;
else
break;
if (c >= base)
break;
if (any < 0 || acc > cutoff || (acc == cutoff && c > cutlim))
any = -1;
else {
any = 1;
acc *= base;
acc += c;
}
}
if (any < 0) {
acc = neg ? LONG_LONG_MIN : LONG_LONG_MAX;
__errno_r(rptr) = ERANGE;
} else if (neg)
acc = -acc;
if (endptr != 0)
*endptr = (wchar_t *) (any ? s - 1 : nptr);
return (acc);
}
/*
* Convert a wide string to an unsigned long long integer.
*/
unsigned long long
_wcstoull_l (struct _reent *rptr, const wchar_t *nptr, wchar_t **endptr,
int base, locale_t loc)
{
register const wchar_t *s = nptr;
register unsigned long long acc;
register int c;
register unsigned long long cutoff;
register int neg = 0, any, cutlim;
if(base < 0 || base == 1 || base > 36) {
rptr->_errno = EINVAL;
return(0ULL);
}
/*
* See strtol for comments as to the logic used.
*/
do {
c = *s++;
} while (iswspace_l(c, loc));
if (c == L'-') {
neg = 1;
c = *s++;
} else if (c == L'+')
c = *s++;
if ((base == 0 || base == 16) &&
c == L'0' && (*s == L'x' || *s == L'X')) {
c = s[1];
s += 2;
base = 16;
}
if (base == 0)
base = c == L'0' ? 8 : 10;
cutoff = (unsigned long long)ULLONG_MAX / (unsigned long long)base;
cutlim = (unsigned long long)ULLONG_MAX % (unsigned long long)base;
for (acc = 0, any = 0;; c = *s++) {
if (c >= L'0' && c <= L'9')
c -= L'0';
else if (c >= L'A' && c <= L'Z')
c -= L'A' - 10;
else if (c >= L'a' && c <= L'z')
c -= L'a' - 10;
else
break;
if (c >= base)
break;
if (any < 0 || acc > cutoff || (acc == cutoff && c > cutlim))
any = -1;
else {
any = 1;
acc *= base;
acc += c;
}
}
if (any < 0) {
acc = ULLONG_MAX;
rptr->_errno = ERANGE;
} else if (neg)
acc = -acc;
if (endptr != 0)
*endptr = (wchar_t *) (any ? s - 1 : nptr);
return (acc);
}
void runFailure() {
iswspace_l(invalid(), locale());
}
void runSuccess() {
iswspace_l(WEOF, locale());
iswspace_l(anychar(), locale());
}
