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 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453
|
" Script to extract tables from Unicode .txt files, to be used in src/mbyte.c.
" The format of the UnicodeData.txt file is explained here:
" http://www.unicode.org/Public/5.1.0/ucd/UCD.html
" For the other files see the header.
"
" Might need to update the URL to the emoji-data.txt
" 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()
let s:dataprops = []
let lnum = 1
while lnum <= line('$')
let l = split(getline(lnum), '\s*;\s*', 1)
if len(l) != 15
echoerr 'Found ' . len(l) . ' items in line ' . lnum . ', expected 15'
return
endif
call add(s:dataprops, l)
let lnum += 1
endwhile
endfunc
" Parse lines of CaseFolding.txt. Creates a list of lists in s:foldprops.
func! ParseFoldProps()
let s:foldprops = []
let lnum = 1
while lnum <= line('$')
let line = getline(lnum)
if line !~ '^#' && line !~ '^\s*$'
let l = split(line, '\s*;\s*', 1)
if len(l) != 4
echoerr 'Found ' . len(l) . ' items in line ' . lnum . ', expected 4'
return
endif
call add(s:foldprops, l)
endif
let lnum += 1
endwhile
endfunc
" Parse lines of EastAsianWidth.txt. Creates a list of lists in s:widthprops.
func! ParseWidthProps()
let s:widthprops = []
let lnum = 1
while lnum <= line('$')
let line = getline(lnum)
if line !~ '^#' && line !~ '^\s*$'
let l = split(line, '\s*;\s*', 1)
if len(l) != 2
echoerr 'Found ' . len(l) . ' items in line ' . lnum . ', expected 2'
return
endif
call add(s:widthprops, l)
endif
let lnum += 1
endwhile
endfunc
" Build the toLower or toUpper table in a new buffer.
" Uses s:dataprops.
func! BuildCaseTable(name, index)
let start = -1
let end = -1
let step = 0
let add = -1
let ranges = []
for p in s:dataprops
if p[a:index] != ''
let n = ('0x' . p[0]) + 0
let nl = ('0x' . p[a:index]) + 0
if start >= 0 && add == nl - n && (step == 0 || n - end == step)
" continue with same range.
let step = n - end
let end = n
else
if start >= 0
" produce previous range
call Range(ranges, start, end, step, add)
endif
let start = n
let end = n
let step = 0
let add = nl - n
endif
endif
endfor
if start >= 0
call Range(ranges, start, end, step, add)
endif
" New buffer to put the result in.
new
exe "file to" . a:name
call setline(1, "static convertStruct to" . a:name . "[] =")
call setline(2, "{")
call append('$', ranges)
call setline('$', getline('$')[:-2]) " remove last comma
call setline(line('$') + 1, "};")
wincmd p
endfunc
" Build the foldCase table in a new buffer.
" Uses s:foldprops.
func! BuildFoldTable()
let start = -1
let end = -1
let step = 0
let add = -1
let ranges = []
for p in s:foldprops
if p[1] == 'C' || p[1] == 'S'
let n = ('0x' . p[0]) + 0
let nl = ('0x' . p[2]) + 0
if start >= 0 && add == nl - n && (step == 0 || n - end == step)
" continue with same range.
let step = n - end
let end = n
else
if start >= 0
" produce previous range
call Range(ranges, start, end, step, add)
endif
let start = n
let end = n
let step = 0
let add = nl - n
endif
endif
endfor
if start >= 0
call Range(ranges, start, end, step, add)
endif
" New buffer to put the result in.
new
file foldCase
call setline(1, "static convertStruct foldCase[] =")
call setline(2, "{")
call append('$', ranges)
call setline('$', getline('$')[:-2]) " remove last comma
call setline(line('$') + 1, "};")
wincmd p
endfunc
func! Range(ranges, start, end, step, add)
let s = printf("\t{0x%x,0x%x,%d,%d},", a:start, a:end, a:step == 0 ? -1 : a:step, a:add)
call add(a:ranges, s)
endfunc
" Build the combining table.
" Uses s:dataprops.
func! BuildCombiningTable()
let start = -1
let end = -1
let ranges = []
for p in s:dataprops
if p[2] == 'Mn' || p[2] == 'Mc' || p[2] == 'Me'
let n = ('0x' . p[0]) + 0
if start >= 0 && end + 1 == n
" continue with same range.
let end = n
else
if start >= 0
" produce previous range
call add(ranges, printf("\t{0x%04x, 0x%04x},", start, end))
endif
let start = n
let end = n
endif
endif
endfor
if start >= 0
call add(ranges, printf("\t{0x%04x, 0x%04x},", start, end))
endif
" New buffer to put the result in.
new
file combining
call setline(1, " static struct interval combining[] =")
call setline(2, " {")
call append('$', ranges)
call setline('$', getline('$')[:-2]) " remove last comma
call setline(line('$') + 1, " };")
wincmd p
endfunc
" Build the double width or ambiguous width table in a new buffer.
" Uses s:widthprops and s:dataprops.
func! BuildWidthTable(pattern, tableName)
let start = -1
let end = -1
let ranges = []
let dataidx = 0
for p in s:widthprops
if p[1][0] =~ a:pattern
if p[0] =~ '\.\.'
" It is a range. we don't check for composing char then.
let rng = split(p[0], '\.\.')
if len(rng) != 2
echoerr "Cannot parse range: '" . p[0] . "' in width table"
endif
let n = ('0x' . rng[0]) + 0
let n_last = ('0x' . rng[1]) + 0
else
let n = ('0x' . p[0]) + 0
let n_last = n
endif
" Find this char in the data table.
while 1
let dn = ('0x' . s:dataprops[dataidx][0]) + 0
if dn >= n
break
endif
let dataidx += 1
endwhile
if dn != n && n_last == n
echoerr "Cannot find character " . n . " in data table"
endif
" Only use the char when it's not a composing char.
" But use all chars from a range.
let dp = s:dataprops[dataidx]
if n_last > n || (dp[2] != 'Mn' && dp[2] != 'Mc' && dp[2] != 'Me')
if start >= 0 && end + 1 == n
" continue with same range.
else
if start >= 0
" produce previous range
call add(ranges, printf("\t{0x%04x, 0x%04x},", start, end))
if a:pattern == 'A'
call add(s:ambitable, [start, end])
else
call add(s:doubletable, [start, end])
endif
endif
let start = n
endif
let end = n_last
endif
endif
endfor
if start >= 0
call add(ranges, printf("\t{0x%04x, 0x%04x},", start, end))
if a:pattern == 'A'
call add(s:ambitable, [start, end])
else
call add(s:doubletable, [start, end])
endif
endif
" New buffer to put the result in.
new
exe "file " . a:tableName
call setline(1, " static struct interval " . a:tableName . "[] =")
call setline(2, " {")
call append('$', ranges)
call setline('$', getline('$')[:-2]) " remove last comma
call setline(line('$') + 1, " };")
wincmd p
endfunc
" Get characters from a list of lines in form "12ab .." or "12ab..56cd ..."
" and put them in dictionary "chardict"
func AddLinesToCharDict(lines, chardict)
for line in a:lines
let tokens = split(line, '\.\.')
let first = str2nr(tokens[0], 16)
if len(tokens) == 1
let last = first
else
let last = str2nr(tokens[1], 16)
endif
for nr in range(first, last)
let a:chardict[nr] = 1
endfor
endfor
endfunc
func Test_AddLinesToCharDict()
let dict = {}
call AddLinesToCharDict([
\ '1234 blah blah',
\ '1235 blah blah',
\ '12a0..12a2 blah blah',
\ '12a1 blah blah',
\ ], dict)
call assert_equal({0x1234: 1, 0x1235: 1,
\ 0x12a0: 1, 0x12a1: 1, 0x12a2: 1,
\ }, dict)
if v:errors != []
echoerr 'AddLinesToCharDict' v:errors
return 1
endif
return 0
endfunc
func CharDictToPairList(chardict)
let result = []
let keys = keys(a:chardict)->map('str2nr(v:val)')->sort('N')
let low = keys[0]
let high = keys[0]
for key in keys
if key > high + 1
call add(result, [low, high])
let low = key
let high = key
else
let high = key
endif
endfor
call add(result, [low, high])
return result
endfunc
func Test_CharDictToPairList()
let dict = {0x1020: 1, 0x1021: 1, 0x1022: 1,
\ 0x1024: 1,
\ 0x2022: 1,
\ 0x2024: 1, 0x2025: 1}
call assert_equal([
\ [0x1020, 0x1022],
\ [0x1024, 0x1024],
\ [0x2022, 0x2022],
\ [0x2024, 0x2025],
\ ], CharDictToPairList(dict))
if v:errors != []
echoerr 'CharDictToPairList' v:errors
return 1
endif
return 0
endfunc
" Build the amoji width table in a new buffer.
func BuildEmojiTable()
" First make the table for all emojis.
let pattern = '; Emoji\s\+#\s'
let lines = map(filter(filter(getline(1, '$'), '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
" Edit the Unicode text file. Requires the netrw plugin.
edit http://unicode.org/Public/UNIDATA/UnicodeData.txt
" Parse each line, create a list of lists.
call ParseDataToProps()
" Build the toLower table.
call BuildCaseTable("Lower", 13)
" Build the toUpper table.
call BuildCaseTable("Upper", 12)
" Build the ranges of composing chars.
call BuildCombiningTable()
" Edit the case folding text file. Requires the netrw plugin.
edit http://www.unicode.org/Public/UNIDATA/CaseFolding.txt
" Parse each line, create a list of lists.
call ParseFoldProps()
" Build the foldCase table.
call BuildFoldTable()
" Edit the width text file. Requires the netrw plugin.
edit http://www.unicode.org/Public/UNIDATA/EastAsianWidth.txt
" Parse each line, create a list of lists.
call ParseWidthProps()
" Build the double width table.
let s:doubletable = []
call BuildWidthTable('[WF]', 'doublewidth')
" Build the ambiguous width table.
let s:ambitable = []
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()
|