Patch 8.2.3068
Problem: Unicode tables are slightly outdated.
Solution: Update the tables for Unicode release 13. (Christian Brabandt
closes #8430)
Files: runtime/tools/unicode.vim, src/mbyte.c
*** ../vim-8.2.3067/runtime/tools/unicode.vim 2018-07-14 19:27:57.000000000
+0200
--- runtime/tools/unicode.vim 2021-06-27 21:26:27.129681656 +0200
***************
*** 7,13 ****
" Usage: Vim -S <this-file>
"
" Author: Bram Moolenaar
! " Last Update: 2010 Jan 12
" Parse lines of UnicodeData.txt. Creates a list of lists in s:dataprops.
func! ParseDataToProps()
--- 7,13 ----
" Usage: Vim -S <this-file>
"
" Author: Bram Moolenaar
! " Last Update: 2020 Aug 24
" Parse lines of UnicodeData.txt. Creates a list of lists in s:dataprops.
func! ParseDataToProps()
***************
*** 195,200 ****
--- 195,207 ----
let end = -1
let ranges = []
let dataidx = 0
+ " Account for indentation differences between ambiguous and doublewidth
+ " table in mbyte.c
+ if a:pattern == 'A'
+ let spc = ' '
+ else
+ let spc = "\t"
+ endif
for p in s:widthprops
if p[1][0] =~ a:pattern
if p[0] =~ '\.\.'
***************
*** 229,235 ****
else
if start >= 0
" produce previous range
! call add(ranges, printf("\t{0x%04x, 0x%04x},", start, end))
if a:pattern == 'A'
call add(s:ambitable, [start, end])
else
--- 236,242 ----
else
if start >= 0
" produce previous range
! call add(ranges, printf("%s{0x%04x, 0x%04x},", spc, start, end))
if a:pattern == 'A'
call add(s:ambitable, [start, end])
else
***************
*** 243,249 ****
endif
endfor
if start >= 0
! call add(ranges, printf("\t{0x%04x, 0x%04x},", start, end))
if a:pattern == 'A'
call add(s:ambitable, [start, end])
else
--- 250,256 ----
endif
endfor
if start >= 0
! call add(ranges, printf("%s{0x%04x, 0x%04x},", spc, start, end))
if a:pattern == 'A'
call add(s:ambitable, [start, end])
else
***************
*** 254,346 ****
" New buffer to put the result in.
new
exe "file " . a:tableName
! call setline(1, " static struct interval " . a:tableName . "[] =")
! call setline(2, " {")
call append('$', ranges)
call setline('$', getline('$')[:-2]) " remove last comma
! call setline(line('$') + 1, " };")
wincmd p
endfunc
! " Build the amoji width table in a new buffer.
! func! BuildEmojiTable(pattern, tableName)
! let alltokens = []
! let widthtokens = []
! let lines = map(filter(filter(getline(1, '$'), 'v:val=~"^[1-9]"'),
'v:val=~a:pattern'), 'matchstr(v:val,"^\\S\\+")')
! for n in range(len(lines))
! let line = lines[n]
! let token = split(line, '\.\.')
! let first = ('0x' . token[0]) + 0
! if len(token) == 1
let last = first
else
! let last = ('0x' . token[1]) + 0
endif
! let token = [first, last]
! if len(alltokens) > 0 && (token[0] - 1 == alltokens[-1][1])
! let alltokens[-1][1] = token[1]
else
! call add(alltokens, token)
endif
! " Characters below 1F000 may be considered single width traditionally,
! " making them double width causes problems.
! if first < 0x1f000
! continue
! endif
- " exclude characters that are in the "ambiguous" or "doublewidth" table
- for ambi in s:ambitable
- if first >= ambi[0] && first <= ambi[1]
- let first = ambi[1] + 1
- endif
- if last >= ambi[0] && last <= ambi[1]
- let last = ambi[0] - 1
- endif
- endfor
- for double in s:doubletable
- if first >= double[0] && first <= double[1]
- let first = double[1] + 1
- endif
- if last >= double[0] && last <= double[1]
- let last = double[0] - 1
- endif
- endfor
! if first <= last
! let token = [first, last]
! if len(widthtokens) > 0 && (token[0] - 1 == widthtokens[-1][1])
! let widthtokens[-1][1] = token[1]
! else
! call add(widthtokens, token)
! endif
! endif
! endfor
! let allranges = map(alltokens, 'printf("\t{0x%04x, 0x%04x},", v:val[0],
v:val[1])')
! let widthranges = map(widthtokens, 'printf("\t{0x%04x, 0x%04x},", v:val[0],
v:val[1])')
" New buffer to put the result in.
new
! exe "file " . a:tableName . '_all'
! call setline(1, " static struct interval " . a:tableName . "_all[] =")
! call setline(2, " {")
call append('$', allranges)
call setline('$', getline('$')[:-2]) " remove last comma
! call setline(line('$') + 1, " };")
wincmd p
" New buffer to put the result in.
new
! exe "file " . a:tableName . '_width'
! call setline(1, " static struct interval " . a:tableName . "_width[] =")
call setline(2, " {")
! call append('$', widthranges)
call setline('$', getline('$')[:-2]) " remove last comma
call setline(line('$') + 1, " };")
wincmd p
endfunc
" Try to avoid hitting E36
set equalalways
--- 261,425 ----
" New buffer to put the result in.
new
exe "file " . a:tableName
! if a:pattern == 'A'
! call setline(1, "static struct interval " . a:tableName . "[] =")
! call setline(2, "{")
! else
! call setline(1, " static struct interval " . a:tableName . "[] =")
! call setline(2, " {")
! endif
call append('$', ranges)
call setline('$', getline('$')[:-2]) " remove last comma
! if a:pattern == 'A'
! call setline(line('$') + 1, "};")
! else
! call setline(line('$') + 1, " };")
! endif
wincmd p
endfunc
!
! " Get characters from a list of lines in form "12ab .." or "12ab..56cd ..."
! " and put them in dictionary "chardict"
! func AddLinesToCharDict(lines, chardict)
! for line in a:lines
! let tokens = split(line, '\.\.')
! let first = str2nr(tokens[0], 16)
! if len(tokens) == 1
let last = first
else
! let last = str2nr(tokens[1], 16)
endif
+ for nr in range(first, last)
+ let a:chardict[nr] = 1
+ endfor
+ endfor
+ endfunc
! func Test_AddLinesToCharDict()
! let dict = {}
! call AddLinesToCharDict([
! \ '1234 blah blah',
! \ '1235 blah blah',
! \ '12a0..12a2 blah blah',
! \ '12a1 blah blah',
! \ ], dict)
! call assert_equal({0x1234: 1, 0x1235: 1,
! \ 0x12a0: 1, 0x12a1: 1, 0x12a2: 1,
! \ }, dict)
! if v:errors != []
! echoerr 'AddLinesToCharDict' v:errors
! return 1
! endif
! return 0
! endfunc
!
!
! func CharDictToPairList(chardict)
! let result = []
! let keys = keys(a:chardict)->map('str2nr(v:val)')->sort('N')
! let low = keys[0]
! let high = keys[0]
! for key in keys
! if key > high + 1
! call add(result, [low, high])
! let low = key
! let high = key
else
! let high = key
endif
+ endfor
+ call add(result, [low, high])
+ return result
+ endfunc
! func Test_CharDictToPairList()
! let dict = {0x1020: 1, 0x1021: 1, 0x1022: 1,
! \ 0x1024: 1,
! \ 0x2022: 1,
! \ 0x2024: 1, 0x2025: 1}
! call assert_equal([
! \ [0x1020, 0x1022],
! \ [0x1024, 0x1024],
! \ [0x2022, 0x2022],
! \ [0x2024, 0x2025],
! \ ], CharDictToPairList(dict))
! if v:errors != []
! echoerr 'CharDictToPairList' v:errors
! return 1
! endif
! return 0
! endfunc
! " Build the amoji width table in a new buffer.
! func BuildEmojiTable()
! " First make the table for all emojis.
! let pattern = '; Emoji\s\+#\s'
! let lines = map(filter(filter(getline(1, '$'), 'v:val=~"^[1-9]"'),
'v:val=~pattern'), 'matchstr(v:val,"^\\S\\+")')
!
! " Make a dictionary with an entry for each character.
! let chardict = {}
! call AddLinesToCharDict(lines, chardict)
! let pairlist = CharDictToPairList(chardict)
! let allranges = map(pairlist, 'printf(" {0x%04x, 0x%04x},", v:val[0],
v:val[1])')
" New buffer to put the result in.
new
! exe 'file emoji_all'
! call setline(1, "static struct interval emoji_all[] =")
! call setline(2, "{")
call append('$', allranges)
call setline('$', getline('$')[:-2]) " remove last comma
! call setline(line('$') + 1, "};")
wincmd p
+ " Make the table for wide emojis.
+ let pattern = '; Emoji_\(Presentation\|Modifier_Base\)\s\+#\s'
+ let lines = map(filter(filter(getline(1, '$'), 'v:val=~"^[1-9]"'),
'v:val=~pattern'), 'matchstr(v:val,"^\\S\\+")')
+
+ " Make a dictionary with an entry for each character.
+ let chardict = {}
+ call AddLinesToCharDict(lines, chardict)
+
+ " exclude characters that are in the "ambiguous" or "doublewidth" table
+ for ambi in s:ambitable
+ for nr in range(ambi[0], ambi[1])
+ if has_key(chardict, nr)
+ call remove(chardict, nr)
+ endif
+ endfor
+ endfor
+
+ for wide in s:doubletable
+ for nr in range(wide[0], wide[1])
+ if has_key(chardict, nr)
+ call remove(chardict, nr)
+ endif
+ endfor
+ endfor
+
+ let pairlist = CharDictToPairList(chardict)
+ let wide_ranges = map(pairlist, 'printf("\t{0x%04x, 0x%04x},", v:val[0],
v:val[1])')
+
" New buffer to put the result in.
new
! exe 'file emoji_wide'
! call setline(1, " static struct interval emoji_wide[] =")
call setline(2, " {")
! call append('$', wide_ranges)
call setline('$', getline('$')[:-2]) " remove last comma
call setline(line('$') + 1, " };")
wincmd p
endfunc
+ " First test a few things
+ let v:errors = []
+ if Test_AddLinesToCharDict() || Test_CharDictToPairList()
+ finish
+ endif
+
+
" Try to avoid hitting E36
set equalalways
***************
*** 383,391 ****
call BuildWidthTable('A', 'ambiguous')
" Edit the emoji text file. Requires the netrw plugin.
! edit https://www.unicode.org/Public/emoji/11.0/emoji-data.txt
! "edit http://www.unicode.org/Public/emoji/latest/emoji-data.txt
" Build the emoji table. Ver. 1.0 - 6.0
! " Must come after the "ambiguous" table
! call BuildEmojiTable('; Emoji\s\+#\s\+\d\+\.\d', 'emoji')
--- 462,469 ----
call BuildWidthTable('A', 'ambiguous')
" Edit the emoji text file. Requires the netrw plugin.
! edit https://unicode.org/Public/emoji/12.1/emoji-data.txt
" Build the emoji table. Ver. 1.0 - 6.0
! " Must come after the "ambiguous" and "doublewidth" tables
! call BuildEmojiTable()
*** ../vim-8.2.3067/src/mbyte.c 2021-06-13 20:27:32.889357660 +0200
--- src/mbyte.c 2021-06-27 21:26:27.129681656 +0200
***************
*** 1389,1395 ****
{0x26ce, 0x26ce},
{0x26d4, 0x26d4},
{0x26ea, 0x26ea},
! {0x26f2, 0x26f5},
{0x26fa, 0x26fa},
{0x26fd, 0x26fd},
{0x2705, 0x2705},
--- 1389,1396 ----
{0x26ce, 0x26ce},
{0x26d4, 0x26d4},
{0x26ea, 0x26ea},
! {0x26f2, 0x26f3},
! {0x26f5, 0x26f5},
{0x26fa, 0x26fa},
{0x26fd, 0x26fd},
{0x2705, 0x2705},
***************
*** 1414,1421 ****
{0x3099, 0x30ff},
{0x3105, 0x312f},
{0x3131, 0x318e},
! {0x3190, 0x31ba},
! {0x31c0, 0x31e3},
{0x31f0, 0x321e},
{0x3220, 0x3247},
{0x3250, 0x4dbf},
--- 1415,1421 ----
{0x3099, 0x30ff},
{0x3105, 0x312f},
{0x3131, 0x318e},
! {0x3190, 0x31e3},
{0x31f0, 0x321e},
{0x3220, 0x3247},
{0x3250, 0x4dbf},
***************
*** 1431,1438 ****
{0xff01, 0xff60},
{0xffe0, 0xffe6},
{0x16fe0, 0x16fe3},
{0x17000, 0x187f7},
! {0x18800, 0x18af2},
{0x1b000, 0x1b11e},
{0x1b150, 0x1b152},
{0x1b164, 0x1b167},
--- 1431,1440 ----
{0xff01, 0xff60},
{0xffe0, 0xffe6},
{0x16fe0, 0x16fe3},
+ {0x16ff0, 0x16ff1},
{0x17000, 0x187f7},
! {0x18800, 0x18cd5},
! {0x18d00, 0x18d08},
{0x1b000, 0x1b11e},
{0x1b150, 0x1b152},
{0x1b164, 0x1b167},
***************
*** 1467,1486 ****
{0x1f680, 0x1f6c5},
{0x1f6cc, 0x1f6cc},
{0x1f6d0, 0x1f6d2},
! {0x1f6d5, 0x1f6d5},
{0x1f6eb, 0x1f6ec},
! {0x1f6f4, 0x1f6fa},
{0x1f7e0, 0x1f7eb},
! {0x1f90d, 0x1f971},
! {0x1f973, 0x1f976},
! {0x1f97a, 0x1f9a2},
! {0x1f9a5, 0x1f9aa},
! {0x1f9ae, 0x1f9ca},
{0x1f9cd, 0x1f9ff},
! {0x1fa70, 0x1fa73},
{0x1fa78, 0x1fa7a},
! {0x1fa80, 0x1fa82},
! {0x1fa90, 0x1fa95},
{0x20000, 0x2fffd},
{0x30000, 0x3fffd}
};
--- 1469,1490 ----
{0x1f680, 0x1f6c5},
{0x1f6cc, 0x1f6cc},
{0x1f6d0, 0x1f6d2},
! {0x1f6d5, 0x1f6d7},
{0x1f6eb, 0x1f6ec},
! {0x1f6f4, 0x1f6fc},
{0x1f7e0, 0x1f7eb},
! {0x1f90c, 0x1f93a},
! {0x1f93c, 0x1f945},
! {0x1f947, 0x1f978},
! {0x1f97a, 0x1f9cb},
{0x1f9cd, 0x1f9ff},
! {0x1fa70, 0x1fa74},
{0x1fa78, 0x1fa7a},
! {0x1fa80, 0x1fa86},
! {0x1fa90, 0x1faa8},
! {0x1fab0, 0x1fab6},
! {0x1fac0, 0x1fac2},
! {0x1fad0, 0x1fad6},
{0x20000, 0x2fffd},
{0x30000, 0x3fffd}
};
***************
*** 2350,2356 ****
{0x0b3e, 0x0b44},
{0x0b47, 0x0b48},
{0x0b4b, 0x0b4d},
! {0x0b56, 0x0b57},
{0x0b62, 0x0b63},
{0x0b82, 0x0b82},
{0x0bbe, 0x0bc2},
--- 2354,2360 ----
{0x0b3e, 0x0b44},
{0x0b47, 0x0b48},
{0x0b4b, 0x0b4d},
! {0x0b55, 0x0b57},
{0x0b62, 0x0b63},
{0x0b82, 0x0b82},
{0x0bbe, 0x0bc2},
***************
*** 2377,2383 ****
{0x0d4a, 0x0d4d},
{0x0d57, 0x0d57},
{0x0d62, 0x0d63},
! {0x0d82, 0x0d83},
{0x0dca, 0x0dca},
{0x0dcf, 0x0dd4},
{0x0dd6, 0x0dd6},
--- 2381,2387 ----
{0x0d4a, 0x0d4d},
{0x0d57, 0x0d57},
{0x0d62, 0x0d63},
! {0x0d81, 0x0d83},
{0x0dca, 0x0dca},
{0x0dcf, 0x0dd4},
{0x0dd6, 0x0dd6},
***************
*** 2424,2430 ****
{0x1a55, 0x1a5e},
{0x1a60, 0x1a7c},
{0x1a7f, 0x1a7f},
! {0x1ab0, 0x1abe},
{0x1b00, 0x1b04},
{0x1b34, 0x1b44},
{0x1b6b, 0x1b73},
--- 2428,2434 ----
{0x1a55, 0x1a5e},
{0x1a60, 0x1a7c},
{0x1a7f, 0x1a7f},
! {0x1ab0, 0x1ac0},
{0x1b00, 0x1b04},
{0x1b34, 0x1b44},
{0x1b6b, 0x1b73},
***************
*** 2453,2458 ****
--- 2457,2463 ----
{0xa806, 0xa806},
{0xa80b, 0xa80b},
{0xa823, 0xa827},
+ {0xa82c, 0xa82c},
{0xa880, 0xa881},
{0xa8b4, 0xa8c5},
{0xa8e0, 0xa8f1},
***************
*** 2488,2493 ****
--- 2493,2499 ----
{0x10a3f, 0x10a3f},
{0x10ae5, 0x10ae6},
{0x10d24, 0x10d27},
+ {0x10eab, 0x10eac},
{0x10f46, 0x10f50},
{0x11000, 0x11002},
{0x11038, 0x11046},
***************
*** 2500,2505 ****
--- 2506,2512 ----
{0x11180, 0x11182},
{0x111b3, 0x111c0},
{0x111c9, 0x111cc},
+ {0x111ce, 0x111cf},
{0x1122c, 0x11237},
{0x1123e, 0x1123e},
{0x112df, 0x112ea},
***************
*** 2522,2527 ****
--- 2529,2539 ----
{0x116ab, 0x116b7},
{0x1171d, 0x1172b},
{0x1182c, 0x1183a},
+ {0x11930, 0x11935},
+ {0x11937, 0x11938},
+ {0x1193b, 0x1193e},
+ {0x11940, 0x11940},
+ {0x11942, 0x11943},
{0x119d1, 0x119d7},
{0x119da, 0x119e0},
{0x119e4, 0x119e4},
***************
*** 2549,2554 ****
--- 2561,2568 ----
{0x16f4f, 0x16f4f},
{0x16f51, 0x16f87},
{0x16f8f, 0x16f92},
+ {0x16fe4, 0x16fe4},
+ {0x16ff0, 0x16ff1},
{0x1bc9d, 0x1bc9e},
{0x1d165, 0x1d169},
{0x1d16d, 0x1d172},
***************
*** 2650,2655 ****
--- 2664,2670 ----
{0x2699, 0x2699},
{0x269b, 0x269c},
{0x26a0, 0x26a1},
+ {0x26a7, 0x26a7},
{0x26aa, 0x26ab},
{0x26b0, 0x26b1},
{0x26bd, 0x26be},
***************
*** 2695,2701 ****
{0x3299, 0x3299},
{0x1f004, 0x1f004},
{0x1f0cf, 0x1f0cf},
! {0x1f170, 0x1f189},
{0x1f18e, 0x1f18e},
{0x1f191, 0x1f19a},
{0x1f1e6, 0x1f1ff},
--- 2710,2717 ----
{0x3299, 0x3299},
{0x1f004, 0x1f004},
{0x1f0cf, 0x1f0cf},
! {0x1f170, 0x1f171},
! {0x1f17e, 0x1f17f},
{0x1f18e, 0x1f18e},
{0x1f191, 0x1f19a},
{0x1f1e6, 0x1f1ff},
***************
*** 2735,2755 ****
{0x1f5fa, 0x1f64f},
{0x1f680, 0x1f6c5},
{0x1f6cb, 0x1f6d2},
{0x1f6e0, 0x1f6e5},
{0x1f6e9, 0x1f6e9},
{0x1f6eb, 0x1f6ec},
{0x1f6f0, 0x1f6f0},
! {0x1f6f3, 0x1f6f9},
! {0x1f910, 0x1f93a},
! {0x1f93c, 0x1f93e},
! {0x1f940, 0x1f945},
! {0x1f947, 0x1f970},
! {0x1f973, 0x1f976},
! {0x1f97a, 0x1f97a},
! {0x1f97c, 0x1f9a2},
! {0x1f9b0, 0x1f9b9},
! {0x1f9c0, 0x1f9c2},
! {0x1f9d0, 0x1f9ff}
};
/*
--- 2751,2775 ----
{0x1f5fa, 0x1f64f},
{0x1f680, 0x1f6c5},
{0x1f6cb, 0x1f6d2},
+ {0x1f6d5, 0x1f6d7},
{0x1f6e0, 0x1f6e5},
{0x1f6e9, 0x1f6e9},
{0x1f6eb, 0x1f6ec},
{0x1f6f0, 0x1f6f0},
! {0x1f6f3, 0x1f6fc},
! {0x1f7e0, 0x1f7eb},
! {0x1f90c, 0x1f93a},
! {0x1f93c, 0x1f945},
! {0x1f947, 0x1f978},
! {0x1f97a, 0x1f9cb},
! {0x1f9cd, 0x1f9ff},
! {0x1fa70, 0x1fa74},
! {0x1fa78, 0x1fa7a},
! {0x1fa80, 0x1fa86},
! {0x1fa90, 0x1faa8},
! {0x1fab0, 0x1fab6},
! {0x1fac0, 0x1fac2},
! {0x1fad0, 0x1fad6}
};
/*
***************
*** 3097,3102 ****
--- 3117,3124 ----
{0xa7c4,0xa7c4,-1,-48},
{0xa7c5,0xa7c5,-1,-42307},
{0xa7c6,0xa7c6,-1,-35384},
+ {0xa7c7,0xa7c9,2,1},
+ {0xa7f5,0xa7f5,-1,1},
{0xab70,0xabbf,1,-38864},
{0xff21,0xff3a,1,32},
{0x10400,0x10427,1,40},
***************
*** 3321,3326 ****
--- 3343,3350 ----
{0xa7c4,0xa7c4,-1,-48},
{0xa7c5,0xa7c5,-1,-42307},
{0xa7c6,0xa7c6,-1,-35384},
+ {0xa7c7,0xa7c9,2,1},
+ {0xa7f5,0xa7f5,-1,1},
{0xff21,0xff3a,1,32},
{0x10400,0x10427,1,40},
{0x104b0,0x104d3,1,40},
***************
*** 3509,3515 ****
{0xa794,0xa794,-1,48},
{0xa797,0xa7a9,2,-1},
{0xa7b5,0xa7bf,2,-1},
! {0xa7c3,0xa7c3,-1,-1},
{0xab53,0xab53,-1,-928},
{0xab70,0xabbf,1,-38864},
{0xff41,0xff5a,1,-32},
--- 3533,3540 ----
{0xa794,0xa794,-1,48},
{0xa797,0xa7a9,2,-1},
{0xa7b5,0xa7bf,2,-1},
! {0xa7c3,0xa7c8,5,-1},
! {0xa7ca,0xa7f6,44,-1},
{0xab53,0xab53,-1,-928},
{0xab70,0xabbf,1,-38864},
{0xff41,0xff5a,1,-32},
*** ../vim-8.2.3067/src/version.c 2021-06-27 19:02:48.985931140 +0200
--- src/version.c 2021-06-27 21:27:44.421556106 +0200
***************
*** 757,758 ****
--- 757,760 ----
{ /* Add new patch number below this line */
+ /**/
+ 3068,
/**/
--
Don't read everything you believe.
/// Bram Moolenaar -- [email protected] -- http://www.Moolenaar.net \\\
/// \\\
\\\ sponsor Vim, vote for features -- http://www.Vim.org/sponsor/ ///
\\\ 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/202106271931.15RJVETe704559%40masaka.moolenaar.net.
