Patch 8.2.1536
Problem: Cannot get the class of a character; emoji widths are wrong in
some environments.
Solution: Add charclass(). Update some emoji widths. Add script to check
emoji widths.
Files: Filelist, runtime/doc/eval.txt, runtime/doc/usr_41.txt,
src/evalfunc.c, src/mbyte.c, src/proto/mbyte.pro,
src/testdir/emoji_list.vim, src/testdir/test_functions.vim
*** ../vim-8.2.1535/Filelist 2020-08-13 22:47:20.369992748 +0200
--- Filelist 2020-08-28 22:02:41.425978440 +0200
***************
*** 197,202 ****
--- 197,203 ----
src/testdir/samples/*.txt \
src/testdir/samples/test000 \
src/testdir/color_ramp.vim \
+ src/testdir/emoji_list.vim \
src/testdir/silent.wav \
src/testdir/popupbounce.vim \
src/proto.h \
*** ../vim-8.2.1535/runtime/doc/eval.txt 2020-08-28 21:04:20.498881375
+0200
--- runtime/doc/eval.txt 2020-08-28 22:07:17.464773040 +0200
***************
*** 2413,2418 ****
--- 2426,2432 ----
String status of channel {handle}
changenr() Number current change number
char2nr({expr} [, {utf8}]) Number ASCII/UTF8 value of first char in {expr}
+ charclass({string}) Number character class of {string}
chdir({dir}) String change current working directory
cindent({lnum}) Number C indent for line {lnum}
clearmatches([{win}]) none clear all matches
***************
*** 3504,3509 ****
--- 3522,3539 ----
Can also be used as a |method|: >
GetChar()->char2nr()
+
+ charclass({string}) *charclass()*
+ Return the character class of the first character in {string}.
+ The character class is one of:
+ 0 blank
+ 1 punctuation
+ 2 word character
+ 3 emoji
+ other specific Unicode class
+ The class is used in patterns and word motions.
+
+
chdir({dir}) *chdir()*
Change the current working directory to {dir}. The scope of
the directory change depends on the directory of the current
*** ../vim-8.2.1535/runtime/doc/usr_41.txt 2020-08-28 21:04:20.498881375
+0200
--- runtime/doc/usr_41.txt 2020-08-28 22:08:37.648420528 +0200
***************
*** 592,597 ****
--- 600,606 ----
strtrans() translate a string to make it printable
tolower() turn a string to lowercase
toupper() turn a string to uppercase
+ charclass() class of a character
match() position where a pattern matches in a string
matchend() position where a pattern match ends in a string
matchstr() match of a pattern in a string
*** ../vim-8.2.1535/src/evalfunc.c 2020-08-28 21:04:20.502881357 +0200
--- src/evalfunc.c 2020-08-28 21:18:30.577820602 +0200
***************
*** 564,569 ****
--- 564,570 ----
{"ch_status", 1, 2, FEARG_1, ret_string, JOB_FUNC(f_ch_status)},
{"changenr", 0, 0, 0, ret_number, f_changenr},
{"char2nr", 1, 2, FEARG_1, ret_number, f_char2nr},
+ {"charclass", 1, 1, FEARG_1, ret_number, f_charclass},
{"chdir", 1, 1, FEARG_1, ret_string, f_chdir},
{"cindent", 1, 1, FEARG_1, ret_number, f_cindent},
{"clearmatches", 0, 1, FEARG_1, ret_void, f_clearmatches},
*** ../vim-8.2.1535/src/mbyte.c 2020-08-28 21:04:20.502881357 +0200
--- src/mbyte.c 2020-08-28 22:14:14.950930035 +0200
***************
*** 132,138 ****
--- 132,140 ----
static int dbcs_ptr2cells_len(char_u *p, int size);
static int dbcs_ptr2char(char_u *p);
static int dbcs_head_off(char_u *base, char_u *p);
+ #ifdef FEAT_EVAL
static int cw_value(int c);
+ #endif
/*
* Lookup table to quickly get the length in bytes of a UTF-8 character from
***************
*** 1388,1395 ****
{0x26ce, 0x26ce},
{0x26d4, 0x26d4},
{0x26ea, 0x26ea},
! {0x26f2, 0x26f3},
! {0x26f5, 0x26f5},
{0x26fa, 0x26fa},
{0x26fd, 0x26fd},
{0x2705, 0x2705},
--- 1390,1396 ----
{0x26ce, 0x26ce},
{0x26d4, 0x26d4},
{0x26ea, 0x26ea},
! {0x26f2, 0x26f5},
{0x26fa, 0x26fa},
{0x26fd, 0x26fd},
{0x2705, 0x2705},
***************
*** 1490,1495 ****
--- 1491,1511 ----
// based on http://unicode.org/emoji/charts/emoji-list.html
static struct interval emoji_wide[] =
{
+ {0x23ed, 0x23ef},
+ {0x23f1, 0x23f2},
+ {0x23f8, 0x23fa},
+ {0x24c2, 0x24c2},
+ {0x261d, 0x261d},
+ {0x26c8, 0x26c8},
+ {0x26cf, 0x26cf},
+ {0x26d1, 0x26d1},
+ {0x26d3, 0x26d3},
+ {0x26e9, 0x26e9},
+ {0x26f0, 0x26f1},
+ {0x26f7, 0x26f9},
+ {0x270c, 0x270d},
+ {0x2934, 0x2935},
+ {0x1f170, 0x1f189},
{0x1f1e6, 0x1f1ff},
{0x1f321, 0x1f321},
{0x1f324, 0x1f32c},
***************
*** 1533,1543 ****
--- 1549,1563 ----
if (c >= 0x100)
{
+ #if defined(FEAT_EVAL) || defined(USE_WCHAR_FUNCTIONS)
int n;
+ #endif
+ #ifdef FEAT_EVAL
n = cw_value(c);
if (n != 0)
return n;
+ #endif
#ifdef USE_WCHAR_FUNCTIONS
/*
***************
*** 2667,2674 ****
{0x3299, 0x3299},
{0x1f004, 0x1f004},
{0x1f0cf, 0x1f0cf},
! {0x1f170, 0x1f171},
! {0x1f17e, 0x1f17f},
{0x1f18e, 0x1f18e},
{0x1f191, 0x1f19a},
{0x1f1e6, 0x1f1ff},
--- 2687,2693 ----
{0x3299, 0x3299},
{0x1f004, 0x1f004},
{0x1f0cf, 0x1f0cf},
! {0x1f170, 0x1f189},
{0x1f18e, 0x1f18e},
{0x1f191, 0x1f19a},
{0x1f1e6, 0x1f1ff},
***************
*** 2835,2840 ****
--- 2854,2863 ----
return 1; // punctuation
}
+ // emoji
+ if (intable(emoji_all, sizeof(emoji_all), c))
+ return 3;
+
// binary search in table
while (top >= bot)
{
***************
*** 2847,2856 ****
return (int)classes[mid].class;
}
- // emoji
- if (intable(emoji_all, sizeof(emoji_all), c))
- return 3;
-
// most other characters are "word" characters
return 2;
}
--- 2870,2875 ----
***************
*** 5352,5357 ****
--- 5371,5378 ----
return retval;
}
+ #if defined(FEAT_EVAL) || defined(PROTO)
+
/*
* Table set by setcellwidths().
*/
***************
*** 5525,5527 ****
--- 5546,5562 ----
cw_table = table;
cw_table_size = l->lv_len;
}
+
+ void
+ f_charclass(typval_T *argvars, typval_T *rettv UNUSED)
+ {
+ if (argvars[0].v_type != VAR_STRING
+ || argvars[0].vval.v_string == NULL
+ || *argvars[0].vval.v_string == NUL)
+ {
+ emsg(_(e_stringreq));
+ return;
+ }
+ rettv->vval.v_number = mb_get_class(argvars[0].vval.v_string);
+ }
+ #endif
*** ../vim-8.2.1535/src/proto/mbyte.pro 2020-08-28 21:04:20.502881357 +0200
--- src/proto/mbyte.pro 2020-08-28 21:23:20.604288455 +0200
***************
*** 85,88 ****
--- 85,89 ----
char_u *string_convert(vimconv_T *vcp, char_u *ptr, int *lenp);
char_u *string_convert_ext(vimconv_T *vcp, char_u *ptr, int *lenp, int
*unconvlenp);
void f_setcellwidths(typval_T *argvars, typval_T *rettv);
+ void f_charclass(typval_T *argvars, typval_T *rettv);
/* vim: set ft=c : */
*** ../vim-8.2.1535/src/testdir/emoji_list.vim 2020-08-28 22:16:31.414375282
+0200
--- src/testdir/emoji_list.vim 2020-08-28 21:39:21.151554959 +0200
***************
*** 0 ****
--- 1,22 ----
+ " Script to fill the window with emoji characters, one per line.
+
+ if &modified
+ new
+ else
+ enew
+ endif
+
+ " Use a compiled Vim9 function for speed
+ def DoIt()
+ let lnum = 1
+ for c in range(0x100, 0x1ffff)
+ let cs = nr2char(c)
+ if charclass(cs) == 3
+ setline(lnum, '|' .. cs .. '| ' .. strwidth(cs))
+ lnum += 1
+ endif
+ endfor
+ enddef
+
+ call DoIt()
+ set nomodified
*** ../vim-8.2.1535/src/testdir/test_functions.vim 2020-08-23
17:33:43.773458055 +0200
--- src/testdir/test_functions.vim 2020-08-28 22:22:47.260947940 +0200
***************
*** 2077,2082 ****
--- 2077,2089 ----
set encoding=utf-8
endfunc
+ func Test_charclass()
+ call assert_equal(0, charclass(' '))
+ call assert_equal(1, charclass('.'))
+ call assert_equal(2, charclass('x'))
+ call assert_equal(3, charclass("\u203c"))
+ endfunc
+
func Test_eventhandler()
call assert_equal(0, eventhandler())
endfunc
*** ../vim-8.2.1535/src/version.c 2020-08-28 21:04:20.502881357 +0200
--- src/version.c 2020-08-28 21:20:42.189114372 +0200
***************
*** 756,757 ****
--- 756,759 ----
{ /* Add new patch number below this line */
+ /**/
+ 1536,
/**/
--
DINGO: You must spank her well and after you have spanked her you
may deal with her as you like and then ... spank me.
AMAZING: And spank me!
STUNNER: And me.
LOVELY: And me.
"Monty Python and the Holy Grail" PYTHON (MONTY) PICTURES LTD
/// Bram Moolenaar -- [email protected] -- http://www.Moolenaar.net \\\
/// sponsor Vim, vote for features -- http://www.Vim.org/sponsor/ \\\
\\\ an exciting new programming language -- http://www.Zimbu.org ///
\\\ help me help AIDS victims -- http://ICCF-Holland.org ///
--
--
You received this message from the "vim_dev" maillist.
Do not top-post! Type your reply below the text you are replying to.
For more information, visit http://www.vim.org/maillist.php
---
You received this message because you are subscribed to the Google Groups
"vim_dev" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To view this discussion on the web visit
https://groups.google.com/d/msgid/vim_dev/202008282025.07SKPR912343912%40masaka.moolenaar.net.
