| 1 | #include "unicode_config.h" |
| 2 | #include "unicode.h" |
| 3 | |
| 4 | #include "eastasianwidth.h" |
| 5 | #include "linebreaktab_internal.h" |
| 6 | |
| 7 | #include <stdlib.h> |
| 8 | |
| 9 | int unicode_wcwidth(unicode_char c) |
| 10 | { |
| 11 | size_t b=0; |
| 12 | size_t e=sizeof(unicode_wcwidth_tab)/sizeof(unicode_wcwidth_tab[0]); |
| 13 | |
| 14 | while (b < e) |
| 15 | { |
| 16 | size_t n=b + (e-b)/2; |
| 17 | |
| 18 | if (c >= unicode_wcwidth_tab[n][0]) |
| 19 | { |
| 20 | if (c <= unicode_wcwidth_tab[n][1]) |
| 21 | return 2; |
| 22 | b=n+1; |
| 23 | } |
| 24 | else |
| 25 | { |
| 26 | e=n; |
| 27 | } |
| 28 | } |
| 29 | |
| 30 | switch (unicode_lb_lookup(c)) { |
| 31 | case UNICODE_LB_BK: |
| 32 | case UNICODE_LB_CR: |
| 33 | case UNICODE_LB_LF: |
| 34 | case UNICODE_LB_CM: |
| 35 | case UNICODE_LB_NL: |
| 36 | case UNICODE_LB_WJ: |
| 37 | case UNICODE_LB_ZW: |
| 38 | return 0; |
| 39 | default: |
| 40 | break; |
| 41 | } |
| 42 | return 1; |
| 43 | } |
| 44 | |
| 45 | int unicode_isspace(unicode_char ch) |
| 46 | { |
| 47 | if (ch == 9) |
| 48 | return 1; |
| 49 | |
| 50 | switch (unicode_lb_lookup(ch)) { |
| 51 | case UNICODE_LB_BK: |
| 52 | case UNICODE_LB_CR: |
| 53 | case UNICODE_LB_LF: |
| 54 | case UNICODE_LB_NL: |
| 55 | case UNICODE_LB_SP: |
| 56 | return 1; |
| 57 | } |
| 58 | |
| 59 | return 0; |
| 60 | } |
| 61 | |
| 62 | size_t unicode_wcwidth_str(const unicode_char *c) |
| 63 | { |
| 64 | size_t w=0; |
| 65 | |
| 66 | while (*c) |
| 67 | w += unicode_wcwidth(*c++); |
| 68 | |
| 69 | |
| 70 | return w; |
| 71 | } |