mirror of
https://codeberg.org/grunfink/snac2.git
synced 2024-11-15 01:55:03 +00:00
Backport from xs.
This commit is contained in:
parent
53a906b3bd
commit
4105e737e6
4 changed files with 73 additions and 38 deletions
57
xs.h
57
xs.h
|
@ -59,6 +59,7 @@ xs_val *xs_insert_m(xs_val *data, int offset, const char *mem, int size);
|
||||||
#define xs_append_m(data, mem, size) xs_insert_m(data, xs_size(data) - 1, mem, size)
|
#define xs_append_m(data, mem, size) xs_insert_m(data, xs_size(data) - 1, mem, size)
|
||||||
|
|
||||||
xs_str *xs_str_new(const char *str);
|
xs_str *xs_str_new(const char *str);
|
||||||
|
xs_str *xs_str_new_sz(const char *mem, int sz);
|
||||||
xs_str *xs_str_wrap_i(const char *prefix, xs_str *str, const char *suffix);
|
xs_str *xs_str_wrap_i(const char *prefix, xs_str *str, const char *suffix);
|
||||||
#define xs_str_prepend_i(str, prefix) xs_str_wrap_i(prefix, str, NULL)
|
#define xs_str_prepend_i(str, prefix) xs_str_wrap_i(prefix, str, NULL)
|
||||||
#define xs_str_cat(str, suffix) xs_str_wrap_i(NULL, str, suffix)
|
#define xs_str_cat(str, suffix) xs_str_wrap_i(NULL, str, suffix)
|
||||||
|
@ -72,6 +73,8 @@ int xs_starts_and_ends(const char *prefix, const char *str, const char *suffix);
|
||||||
#define xs_startswith(str, prefix) xs_starts_and_ends(prefix, str, NULL)
|
#define xs_startswith(str, prefix) xs_starts_and_ends(prefix, str, NULL)
|
||||||
#define xs_endswith(str, suffix) xs_starts_and_ends(NULL, str, suffix)
|
#define xs_endswith(str, suffix) xs_starts_and_ends(NULL, str, suffix)
|
||||||
xs_str *xs_crop_i(xs_str *str, int start, int end);
|
xs_str *xs_crop_i(xs_str *str, int start, int end);
|
||||||
|
xs_str *xs_lstrip_chars_i(xs_str *str, const char *chars);
|
||||||
|
xs_str *xs_rstrip_chars_i(xs_str *str, const char *chars);
|
||||||
xs_str *xs_strip_chars_i(xs_str *str, const char *chars);
|
xs_str *xs_strip_chars_i(xs_str *str, const char *chars);
|
||||||
#define xs_strip_i(str) xs_strip_chars_i(str, " \r\n\t\v\f")
|
#define xs_strip_i(str) xs_strip_chars_i(str, " \r\n\t\v\f")
|
||||||
xs_str *xs_tolower_i(xs_str *str);
|
xs_str *xs_tolower_i(xs_str *str);
|
||||||
|
@ -424,6 +427,17 @@ xs_str *xs_str_new(const char *str)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
xs_str *xs_str_new_sz(const char *mem, int sz)
|
||||||
|
/* creates a new string from a memory block, adding an asciiz */
|
||||||
|
{
|
||||||
|
xs_str *s = xs_realloc(NULL, _xs_blk_size(sz + 1));
|
||||||
|
memcpy(s, mem, sz);
|
||||||
|
s[sz] = '\0';
|
||||||
|
|
||||||
|
return s;
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
xs_str *xs_str_wrap_i(const char *prefix, xs_str *str, const char *suffix)
|
xs_str *xs_str_wrap_i(const char *prefix, xs_str *str, const char *suffix)
|
||||||
/* wraps str with prefix and suffix */
|
/* wraps str with prefix and suffix */
|
||||||
{
|
{
|
||||||
|
@ -546,29 +560,39 @@ xs_str *xs_crop_i(xs_str *str, int start, int end)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
xs_str *xs_strip_chars_i(xs_str *str, const char *chars)
|
xs_str *xs_lstrip_chars_i(xs_str *str, const char *chars)
|
||||||
/* strips the string of chars from the start and the end */
|
/* strips all chars from the start of str */
|
||||||
{
|
{
|
||||||
XS_ASSERT_TYPE(str, XSTYPE_STRING);
|
|
||||||
|
|
||||||
int n;
|
int n;
|
||||||
|
|
||||||
/* strip first from the end */
|
|
||||||
for (n = strlen(str); n > 0 && strchr(chars, str[n - 1]); n--);
|
|
||||||
str[n] = '\0';
|
|
||||||
|
|
||||||
if (str[0]) {
|
|
||||||
/* now strip from the beginning */
|
|
||||||
for (n = 0; str[n] && strchr(chars, str[n]); n++);
|
for (n = 0; str[n] && strchr(chars, str[n]); n++);
|
||||||
|
|
||||||
if (n)
|
if (n)
|
||||||
str = xs_collapse(str, 0, n);
|
str = xs_collapse(str, 0, n);
|
||||||
}
|
|
||||||
|
|
||||||
return str;
|
return str;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
xs_str *xs_rstrip_chars_i(xs_str *str, const char *chars)
|
||||||
|
/* strips all chars from the end of str */
|
||||||
|
{
|
||||||
|
int n;
|
||||||
|
|
||||||
|
for (n = strlen(str); n > 0 && strchr(chars, str[n - 1]); n--);
|
||||||
|
str[n] = '\0';
|
||||||
|
|
||||||
|
return str;
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
xs_str *xs_strip_chars_i(xs_str *str, const char *chars)
|
||||||
|
/* strips the string of chars from the start and the end */
|
||||||
|
{
|
||||||
|
return xs_lstrip_chars_i(xs_rstrip_chars_i(str, chars), chars);
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
xs_str *xs_tolower_i(xs_str *str)
|
xs_str *xs_tolower_i(xs_str *str)
|
||||||
/* convert to lowercase */
|
/* convert to lowercase */
|
||||||
{
|
{
|
||||||
|
@ -859,11 +883,9 @@ xs_list *xs_split_n(const char *str, const char *sep, int times)
|
||||||
list = xs_list_new();
|
list = xs_list_new();
|
||||||
|
|
||||||
while (times > 0 && (ss = strstr(str, sep)) != NULL) {
|
while (times > 0 && (ss = strstr(str, sep)) != NULL) {
|
||||||
/* add the first part (without the asciiz) */
|
/* create a new string with this slice and add it to the list */
|
||||||
list = xs_list_append_m(list, str, ss - str);
|
xs *s = xs_str_new_sz(str, ss - str);
|
||||||
|
list = xs_list_append(list, s);
|
||||||
/* add the asciiz */
|
|
||||||
list = xs_insert_m(list, xs_size(list) - 1, "", 1);
|
|
||||||
|
|
||||||
/* skip past the separator */
|
/* skip past the separator */
|
||||||
str = ss + sz;
|
str = ss + sz;
|
||||||
|
@ -1131,8 +1153,7 @@ int xs_data_size(const xs_data *value)
|
||||||
void xs_data_get(const xs_data *value, void *data)
|
void xs_data_get(const xs_data *value, void *data)
|
||||||
/* copies the raw data stored inside value into data */
|
/* copies the raw data stored inside value into data */
|
||||||
{
|
{
|
||||||
int size = _xs_get_24b(value + 1) - 4;
|
memcpy(data, &value[4], xs_data_size(value));
|
||||||
memcpy(data, &value[4], size);
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
|
|
@ -33,12 +33,12 @@ xs_list *xs_regex_split_n(const char *str, const char *rx, int count)
|
||||||
|
|
||||||
while (count > 0 && !regexec(&re, (p = str + offset), 1, &rm, offset > 0 ? REG_NOTBOL : 0)) {
|
while (count > 0 && !regexec(&re, (p = str + offset), 1, &rm, offset > 0 ? REG_NOTBOL : 0)) {
|
||||||
/* add first the leading part of the string */
|
/* add first the leading part of the string */
|
||||||
list = xs_list_append_m(list, p, rm.rm_so);
|
xs *s1 = xs_str_new_sz(p, rm.rm_so);
|
||||||
list = xs_insert_m(list, xs_size(list) - 1, "", 1);
|
list = xs_list_append(list, s1);
|
||||||
|
|
||||||
/* add now the matched text as the separator */
|
/* add now the matched text as the separator */
|
||||||
list = xs_list_append_m(list, p + rm.rm_so, rm.rm_eo - rm.rm_so);
|
xs *s2 = xs_str_new_sz(p + rm.rm_so, rm.rm_eo - rm.rm_so);
|
||||||
list = xs_insert_m(list, xs_size(list) - 1, "", 1);
|
list = xs_list_append(list, s2);
|
||||||
|
|
||||||
/* move forward */
|
/* move forward */
|
||||||
offset += rm.rm_eo;
|
offset += rm.rm_eo;
|
||||||
|
|
40
xs_unicode.h
40
xs_unicode.h
|
@ -16,6 +16,7 @@
|
||||||
unsigned int xs_unicode_to_lower(unsigned int cpoint);
|
unsigned int xs_unicode_to_lower(unsigned int cpoint);
|
||||||
int xs_unicode_nfd(unsigned int cpoint, unsigned int *base, unsigned int *diac);
|
int xs_unicode_nfd(unsigned int cpoint, unsigned int *base, unsigned int *diac);
|
||||||
int xs_unicode_nfc(unsigned int base, unsigned int diac, unsigned int *cpoint);
|
int xs_unicode_nfc(unsigned int base, unsigned int diac, unsigned int *cpoint);
|
||||||
|
int xs_unicode_is_alpha(unsigned int cpoint);
|
||||||
|
|
||||||
#ifdef XS_IMPLEMENTATION
|
#ifdef XS_IMPLEMENTATION
|
||||||
|
|
||||||
|
@ -101,6 +102,15 @@ unsigned int xs_utf8_dec(char **str)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
static int int_range_cmp(const void *p1, const void *p2)
|
||||||
|
{
|
||||||
|
const unsigned int *a = p1;
|
||||||
|
const unsigned int *b = p2;
|
||||||
|
|
||||||
|
return *a < b[0] ? -1 : *a > b[1] ? 1 : 0;
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
/* intentionally dead simple */
|
/* intentionally dead simple */
|
||||||
|
|
||||||
static unsigned int xs_unicode_width_table[] = {
|
static unsigned int xs_unicode_width_table[] = {
|
||||||
|
@ -119,20 +129,12 @@ static unsigned int xs_unicode_width_table[] = {
|
||||||
int xs_unicode_width(unsigned int cpoint)
|
int xs_unicode_width(unsigned int cpoint)
|
||||||
/* returns the width in columns of a Unicode codepoint (somewhat simplified) */
|
/* returns the width in columns of a Unicode codepoint (somewhat simplified) */
|
||||||
{
|
{
|
||||||
unsigned int *p = xs_unicode_width_table;
|
unsigned int *r = bsearch(&cpoint, xs_unicode_width_table,
|
||||||
unsigned int *e = p + sizeof(xs_unicode_width_table) / sizeof(unsigned int);
|
sizeof(xs_unicode_width_table) / (sizeof(unsigned int) * 3),
|
||||||
|
sizeof(unsigned int) * 3,
|
||||||
|
int_range_cmp);
|
||||||
|
|
||||||
while (p < e) {
|
return r ? r[2] : 1;
|
||||||
if (cpoint < p[0])
|
|
||||||
return 1;
|
|
||||||
|
|
||||||
if (cpoint >= p[0] && cpoint <= p[1])
|
|
||||||
return p[2];
|
|
||||||
|
|
||||||
p += 3;
|
|
||||||
}
|
|
||||||
|
|
||||||
return 0;
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
@ -232,6 +234,18 @@ int xs_unicode_nfc(unsigned int base, unsigned int diac, unsigned int *cpoint)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
int xs_unicode_is_alpha(unsigned int cpoint)
|
||||||
|
/* checks if a codepoint is an alpha (i.e. a letter) */
|
||||||
|
{
|
||||||
|
unsigned int *r = bsearch(&cpoint, xs_unicode_alpha_table,
|
||||||
|
sizeof(xs_unicode_alpha_table) / (sizeof(unsigned int) * 2),
|
||||||
|
sizeof(unsigned int) * 2,
|
||||||
|
int_range_cmp);
|
||||||
|
|
||||||
|
return !!r;
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
#endif /* _XS_UNICODE_TBL_H */
|
#endif /* _XS_UNICODE_TBL_H */
|
||||||
|
|
||||||
#endif /* XS_IMPLEMENTATION */
|
#endif /* XS_IMPLEMENTATION */
|
||||||
|
|
|
@ -1 +1 @@
|
||||||
/* fdd04f1862e0d8bdebb7b438798914643895d43f */
|
/* 5bf06243b37eec60e48e53d87d4d147d01ad9924 */
|
||||||
|
|
Loading…
Reference in a new issue