/*
* Decodes a string in RFC 3986 percent-encoded representation.
*/
int
percent_decode(const char *in, size_t ilen, char *out, size_t *olen)
{
size_t len;
for (len = 0; ilen && *in; --ilen, ++in) {
if (*in != '%') {
if (++len < *olen)
*out++ = *in;
} else if (ilen >= 3 && is_xdigit(in[1]) && is_xdigit(in[2])) {
if (++len < *olen)
*out++ = unhex(in[1]) << 4 | unhex(in[2]);
in += 2;
} else {
errno = EINVAL;
return (-1);
}
}
if (len < *olen)
*out = '\0';
if (len >= *olen) {
/* overflow */
*olen = len;
errno = ENOSPC;
return (-1);
}
*olen = len;
return (0);
}
uint32_t
convert_string_to_hexadecimal(_IN_ const char *str)
{
uint32_t value = 0;
uint32_t multiplier = 1;
for (const char *p = str + strlen(str) - 1; p >= str; p --) {
int c = *p;
if (!is_xdigit(c)) {
FDC_ASSERT(p == str + 1 && c == 'x' && str[0] == '0',
str[0], str[1]);
break;
}
if (is_digit(c)) {
value += (c - '0') * multiplier;
} else {
value += (to_lower(c) - 'a' + 10) * multiplier;
}
multiplier *= 16;
}
return value;
}
static bool
number(struct scanner *s, int64_t *out, int *out_tok)
{
bool is_float = false, is_hex = false;
const char *start = s->s + s->pos;
char *end;
if (lit(s, "0x")) {
while (is_xdigit(peek(s))) next(s);
is_hex = true;
}
else {
while (is_digit(peek(s))) next(s);
is_float = chr(s, '.');
while (is_digit(peek(s))) next(s);
}
if (s->s + s->pos == start)
return false;
errno = 0;
if (is_hex)
*out = strtoul(start, &end, 16);
else if (is_float)
*out = strtod(start, &end);
else
*out = strtoul(start, &end, 10);
if (errno != 0 || s->s + s->pos != end)
*out_tok = ERROR_TOK;
else
*out_tok = (is_float ? FLOAT : INTEGER);
return true;
}
unsigned long simple_strtoul(const char *cp,char **endp,unsigned int base)
{
unsigned long result = 0,value;
if (!base) {
base = 10;
if (*cp == '0') {
base = 8;
cp++;
if ((*cp == 'x') && is_xdigit(cp[1])) {
cp++;
base = 16;
}
}
}
while (is_xdigit(*cp) && (value = is_digit(*cp) ? *cp-'0' : (is_lower(*cp)
? toupper(*cp) : *cp)-'A'+10) < base) {
result = result*base + value;
cp++;
}
if (endp)
*endp = (char *)cp;
return result;
}
//input: *c=='[' **pc==':'
static u16 bracket_class(u8 *c,u8 **pc,u8 **sc,u8 not,u8 sc_folded)
{
u8 char_class[CHAR_CLASS_MAX+1];//don't forget the 0 terminating char
u16 r=bracket_char_class_get(c,pc,not,sc_folded,&char_class[0]);
if(r!=OK) return r;
if((STREQ(char_class,"alnum")&&is_alnum(**sc))
||(STREQ(char_class,"alpha")&&is_alpha(**sc))
||(STREQ(char_class,"blank")&&is_blank(**sc))
||(STREQ(char_class,"cntrl")&&is_cntrl(**sc))
||(STREQ(char_class,"digit")&&is_digit(**sc))
||(STREQ(char_class,"graph")&&is_graph(**sc))
||(STREQ(char_class,"lower")&&is_lower(**sc))
||(STREQ(char_class,"print")&&is_print(**sc))
||(STREQ(char_class,"punct")&&is_punct(**sc))
||(STREQ(char_class,"space")&&is_space(**sc))
||(STREQ(char_class,"upper")&&is_upper(**sc))
||(STREQ(char_class,"xdigit")&&is_xdigit(**sc)))
return bracket_matched(c,pc,not);
*c=*(*pc)++;
return OK;
}
static void
output_tables (const char *filename, const char *version)
{
FILE *stream;
unsigned int ch;
stream = fopen (filename, "w");
if (stream == NULL)
{
fprintf (stderr, "cannot open '%s' for writing\n", filename);
exit (1);
}
fprintf (stream, "escape_char /\n");
fprintf (stream, "comment_char %%\n");
fprintf (stream, "\n");
fprintf (stream, "%% Generated automatically by gen-unicode-ctype for Unicode %s.\n",
version);
fprintf (stream, "\n");
fprintf (stream, "LC_IDENTIFICATION\n");
fprintf (stream, "title \"Unicode %s FDCC-set\"\n", version);
fprintf (stream, "source \"UnicodeData.txt, PropList.txt\"\n");
fprintf (stream, "address \"\"\n");
fprintf (stream, "contact \"\"\n");
fprintf (stream, "email \"[email protected]\"\n");
fprintf (stream, "tel \"\"\n");
fprintf (stream, "fax \"\"\n");
fprintf (stream, "language \"\"\n");
fprintf (stream, "territory \"Earth\"\n");
fprintf (stream, "revision \"%s\"\n", version);
{
time_t now;
char date[11];
now = time (NULL);
strftime (date, sizeof (date), "%Y-%m-%d", gmtime (&now));
fprintf (stream, "date \"%s\"\n", date);
}
fprintf (stream, "category \"unicode:2001\";LC_CTYPE\n");
fprintf (stream, "END LC_IDENTIFICATION\n");
fprintf (stream, "\n");
/* Verifications. */
for (ch = 0; ch < 0x110000; ch++)
{
/* toupper restriction: "Only characters specified for the keywords
lower and upper shall be specified. */
if (to_upper (ch) != ch && !(is_lower (ch) || is_upper (ch)))
fprintf (stderr,
"%s is not upper|lower but toupper(0x%04X) = 0x%04X\n",
ucs_symbol (ch), ch, to_upper (ch));
/* tolower restriction: "Only characters specified for the keywords
lower and upper shall be specified. */
if (to_lower (ch) != ch && !(is_lower (ch) || is_upper (ch)))
fprintf (stderr,
"%s is not upper|lower but tolower(0x%04X) = 0x%04X\n",
ucs_symbol (ch), ch, to_lower (ch));
/* alpha restriction: "Characters classified as either upper or lower
shall automatically belong to this class. */
if ((is_lower (ch) || is_upper (ch)) && !is_alpha (ch))
fprintf (stderr, "%s is upper|lower but not alpha\n", ucs_symbol (ch));
/* alpha restriction: "No character specified for the keywords cntrl,
digit, punct or space shall be specified." */
if (is_alpha (ch) && is_cntrl (ch))
fprintf (stderr, "%s is alpha and cntrl\n", ucs_symbol (ch));
if (is_alpha (ch) && is_digit (ch))
fprintf (stderr, "%s is alpha and digit\n", ucs_symbol (ch));
if (is_alpha (ch) && is_punct (ch))
fprintf (stderr, "%s is alpha and punct\n", ucs_symbol (ch));
if (is_alpha (ch) && is_space (ch))
fprintf (stderr, "%s is alpha and space\n", ucs_symbol (ch));
/* space restriction: "No character specified for the keywords upper,
lower, alpha, digit, graph or xdigit shall be specified."
upper, lower, alpha already checked above. */
if (is_space (ch) && is_digit (ch))
fprintf (stderr, "%s is space and digit\n", ucs_symbol (ch));
if (is_space (ch) && is_graph (ch))
fprintf (stderr, "%s is space and graph\n", ucs_symbol (ch));
if (is_space (ch) && is_xdigit (ch))
fprintf (stderr, "%s is space and xdigit\n", ucs_symbol (ch));
/* cntrl restriction: "No character specified for the keywords upper,
lower, alpha, digit, punct, graph, print or xdigit shall be
specified." upper, lower, alpha already checked above. */
if (is_cntrl (ch) && is_digit (ch))
fprintf (stderr, "%s is cntrl and digit\n", ucs_symbol (ch));
if (is_cntrl (ch) && is_punct (ch))
fprintf (stderr, "%s is cntrl and punct\n", ucs_symbol (ch));
if (is_cntrl (ch) && is_graph (ch))
fprintf (stderr, "%s is cntrl and graph\n", ucs_symbol (ch));
if (is_cntrl (ch) && is_print (ch))
fprintf (stderr, "%s is cntrl and print\n", ucs_symbol (ch));
if (is_cntrl (ch) && is_xdigit (ch))
fprintf (stderr, "%s is cntrl and xdigit\n", ucs_symbol (ch));
/* punct restriction: "No character specified for the keywords upper,
lower, alpha, digit, cntrl, xdigit or as the <space> character shall
be specified." upper, lower, alpha, cntrl already checked above. */
if (is_punct (ch) && is_digit (ch))
fprintf (stderr, "%s is punct and digit\n", ucs_symbol (ch));
if (is_punct (ch) && is_xdigit (ch))
fprintf (stderr, "%s is punct and xdigit\n", ucs_symbol (ch));
if (is_punct (ch) && (ch == 0x0020))
fprintf (stderr, "%s is punct\n", ucs_symbol (ch));
/* graph restriction: "No character specified for the keyword cntrl
shall be specified." Already checked above. */
/* print restriction: "No character specified for the keyword cntrl
shall be specified." Already checked above. */
/* graph - print relation: differ only in the <space> character.
How is this possible if there are more than one space character?!
I think susv2/xbd/locale.html should speak of "space characters",
not "space character". */
if (is_print (ch) && !(is_graph (ch) || /* ch == 0x0020 */ is_space (ch)))
fprintf (stderr,
"%s is print but not graph|<space>\n", ucs_symbol (ch));
if (!is_print (ch) && (is_graph (ch) || ch == 0x0020))
fprintf (stderr,
"%s is graph|<space> but not print\n", ucs_symbol (ch));
}
fprintf (stream, "LC_CTYPE\n");
output_charclass (stream, "upper", is_upper);
output_charclass (stream, "lower", is_lower);
output_charclass (stream, "alpha", is_alpha);
output_charclass (stream, "digit", is_digit);
output_charclass (stream, "outdigit", is_outdigit);
output_charclass (stream, "blank", is_blank);
output_charclass (stream, "space", is_space);
output_charclass (stream, "cntrl", is_cntrl);
output_charclass (stream, "punct", is_punct);
output_charclass (stream, "xdigit", is_xdigit);
output_charclass (stream, "graph", is_graph);
output_charclass (stream, "print", is_print);
output_charclass (stream, "class \"combining\";", is_combining);
output_charclass (stream, "class \"combining_level3\";", is_combining_level3);
output_charmap (stream, "toupper", to_upper);
output_charmap (stream, "tolower", to_lower);
output_charmap (stream, "map \"totitle\";", to_title);
output_widthmap (stream);
fprintf (stream, "END LC_CTYPE\n");
if (ferror (stream) || fclose (stream))
{
fprintf (stderr, "error writing to '%s'\n", filename);
exit (1);
}
}
long int strtol(const char *str, char **endptr, int base)
{
const char *buf = str;
long int value = 0;
int sign = 1, k = 0;
if (base < 2 || base > 36)
{
return 0;
}
/* swallow white spaces */
while (*buf == ' ' || *buf == '\t')
{
++buf;
}
/* parse sign if any */
if (*buf == '-')
{
sign = -1;
++buf;
}
else if (*buf == '+')
{
sign = 1;
++buf;
}
/* parse base */
if (base == 0)
{
if (*buf == '0')
{
if (to_lower(*(++buf)) == 'x' && is_xdigit(buf[1]))
{
++buf;
base = 16;
}
else
{
base = 8;
}
}
else
{
base = 10;
}
}
else if (base == 16 && buf[0] == '0' && to_lower(buf[1]) == 'x')
{
str += 2;
}
/* parse alpha-numerical string */
while (is_alnum(*buf))
{
if (is_alpha(*buf))
{
k = to_lower(*buf) - 'a' + 10;
if (k > base)
{
break;
}
}
else
{
k = *buf - '0';
}
value = value * base + k;
++buf;
}
if (endptr != NULL)
{
*endptr = (char *)buf;
}
return sign * value;
}
const char* xdigit(const char* src) { return is_xdigit(*src) ? src + 1 : 0; }
inline bool is_xdigit<unicode::char_t> (unicode::char_t c)
{
return c.value <= 127 && is_xdigit(static_cast<char>(c.value));
}
