diff options
| -rw-r--r-- | src/nvim/globals.h | 24 | ||||
| -rw-r--r-- | src/nvim/mbyte.c | 18 |
2 files changed, 22 insertions, 20 deletions
diff --git a/src/nvim/globals.h b/src/nvim/globals.h index 301a2c1663..f81fb43eaf 100644 --- a/src/nvim/globals.h +++ b/src/nvim/globals.h @@ -788,8 +788,28 @@ EXTERN int vr_lines_changed INIT(= 0); /* #Lines changed by "gR" so far */ /// Encoding used when 'fencs' is set to "default" EXTERN char_u *fenc_default INIT(= NULL); -// To speed up BYTELEN() we keep a table with the byte lengths for utf-8 -EXTERN char utf8len_tab[256]; +// To speed up BYTELEN(); keep a lookup table to quickly get the length in +// bytes of a UTF-8 character from the first byte of a UTF-8 string. Bytes +// which are illegal when used as the first byte have a 1. The NUL byte has +// length 1. +EXTERN char utf8len_tab[256] INIT(= { + 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, + 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, + 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, + 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, + 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, + 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, + 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, + 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, + 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, + 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, + 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, + 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, + 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, + 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 6, 6, 1, 1, +}); # if defined(USE_ICONV) && defined(DYNAMIC_ICONV) /* Pointers to functions and variables to be loaded at runtime */ diff --git a/src/nvim/mbyte.c b/src/nvim/mbyte.c index 7be0be7106..2ecd86974e 100644 --- a/src/nvim/mbyte.c +++ b/src/nvim/mbyte.c @@ -69,24 +69,6 @@ struct interval { #endif /* - * Lookup table to quickly get the length in bytes of a UTF-8 character from - * the first byte of a UTF-8 string. - * Bytes which are illegal when used as the first byte have a 1. - * The NUL byte has length 1. - */ -char utf8len_tab[256] = -{ - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, - 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, - 3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6,1,1, -}; - -/* * Like utf8len_tab above, but using a zero for illegal lead bytes. */ static uint8_t utf8len_tab_zero[256] = |