File: unicode-util.c

package info (click to toggle)
notmuch 0.39-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 7,104 kB
  • sloc: sh: 21,888; ansic: 14,897; lisp: 9,061; cpp: 7,990; python: 6,221; perl: 391; makefile: 231; javascript: 34; ruby: 13
file content (43 lines) | stat: -rw-r--r-- 979 bytes parent folder | download | duplicates (4)
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
#include "unicode-util.h"

/* Based on Xapian::Unicode::is_wordchar, to avoid forcing clients to
 * link directly to libxapian.
 */

static bool
unicode_is_wordchar (notmuch_unichar ch)
{
    switch (g_unichar_type (ch)) {
    case G_UNICODE_UPPERCASE_LETTER:
    case G_UNICODE_LOWERCASE_LETTER:
    case G_UNICODE_TITLECASE_LETTER:
    case G_UNICODE_MODIFIER_LETTER:
    case G_UNICODE_OTHER_LETTER:
    case G_UNICODE_NON_SPACING_MARK:
    case G_UNICODE_ENCLOSING_MARK:
    case G_UNICODE_SPACING_MARK:
    case G_UNICODE_DECIMAL_NUMBER:
    case G_UNICODE_LETTER_NUMBER:
    case G_UNICODE_OTHER_NUMBER:
    case G_UNICODE_CONNECT_PUNCTUATION:
	return true;
    default:
	return false;
    }
}

bool
unicode_word_utf8 (const char *utf8_str)
{
    gunichar *decoded = g_utf8_to_ucs4_fast (utf8_str, -1, NULL);
    const gunichar *p = decoded;
    bool ret;

    while (*p && unicode_is_wordchar (*p))
	p++;

    ret =  (*p == '\0');

    g_free (decoded);
    return ret;
}