diff options
Diffstat (limited to 'test')
| -rw-r--r-- | test/functional/api/vim_spec.lua | 22 | ||||
| -rw-r--r-- | test/functional/ui/decorations_spec.lua | 21 | ||||
| -rw-r--r-- | test/functional/ui/messages_spec.lua | 35 | ||||
| -rw-r--r-- | test/functional/ui/multibyte_spec.lua | 122 | ||||
| -rw-r--r-- | test/old/testdir/test_functions.vim | 2 | ||||
| -rw-r--r-- | test/old/testdir/test_normal.vim | 4 | ||||
| -rw-r--r-- | test/unit/mbyte_spec.lua | 119 |
7 files changed, 287 insertions, 38 deletions
diff --git a/test/functional/api/vim_spec.lua b/test/functional/api/vim_spec.lua index 4210b7ecf0..074d3ac0a3 100644 --- a/test/functional/api/vim_spec.lua +++ b/test/functional/api/vim_spec.lua @@ -1435,6 +1435,28 @@ describe('API', function() it('cannot handle NULs', function() eq(0, api.nvim_strwidth('\0abc')) end) + + it('can handle emoji with variant selectors and ZWJ', function() + local selector = 'β€οΈ' + eq(2, fn.strchars(selector)) + eq(1, fn.strcharlen(selector)) + eq(2, api.nvim_strwidth(selector)) + + local no_selector = 'β€' + eq(1, fn.strchars(no_selector)) + eq(1, fn.strcharlen(no_selector)) + eq(1, api.nvim_strwidth(no_selector)) + + local selector_zwj_selector = 'π³οΈββ§οΈ' + eq(5, fn.strchars(selector_zwj_selector)) + eq(1, fn.strcharlen(selector_zwj_selector)) + eq(2, api.nvim_strwidth(selector_zwj_selector)) + + local emoji_zwj_emoji = 'π§βπΎ' + eq(3, fn.strchars(emoji_zwj_emoji)) + eq(1, fn.strcharlen(emoji_zwj_emoji)) + eq(2, api.nvim_strwidth(emoji_zwj_emoji)) + end) end) describe('nvim_get_current_line, nvim_set_current_line', function() diff --git a/test/functional/ui/decorations_spec.lua b/test/functional/ui/decorations_spec.lua index 1709819575..61a5e1d6f7 100644 --- a/test/functional/ui/decorations_spec.lua +++ b/test/functional/ui/decorations_spec.lua @@ -5620,6 +5620,27 @@ l5 ]] }) end) + + it('supports emoji as signs', function() + insert(example_test3) + feed 'gg' + api.nvim_buf_set_extmark(0, ns, 1, 0, {sign_text='π§βπΎ'}) + -- VS16 can change width of character + api.nvim_buf_set_extmark(0, ns, 2, 0, {sign_text='β€οΈ'}) + api.nvim_buf_set_extmark(0, ns, 3, 0, {sign_text='β€'}) + api.nvim_buf_set_extmark(0, ns, 4, 0, {sign_text='β€x'}) + screen:expect([[ + {7: }^l1 | + π§βπΎl2 | + β€οΈl3 | + β€ l4 | + β€xl5 | + {7: } | + {1:~ }|*3 + | + ]]) + eq("Invalid 'sign_text'", pcall_err(api.nvim_buf_set_extmark, 0, ns, 5, 0, {sign_text='β€οΈx'})) + end) end) describe('decorations: virt_text', function() diff --git a/test/functional/ui/messages_spec.lua b/test/functional/ui/messages_spec.lua index 07192800e5..036b5ceefc 100644 --- a/test/functional/ui/messages_spec.lua +++ b/test/functional/ui/messages_spec.lua @@ -1436,6 +1436,41 @@ vimComment xxx match /\s"[^\-:.%#=*].*$/ms=s+1,lc=1 excludenl contains=@vim } end) + it('supports nvim_echo messages with emoji', function() + -- stylua: ignore + async_meths.nvim_echo( + { { 'wow, π³οΈββ§οΈπ§βπΎβ€οΈππ΄ββ οΈ\nvariant β€οΈ one\nvariant β€ two' } }, true, {} + ) + + screen:expect([[ + | + {1:~ }| + {3: }| + wow, π³οΈββ§οΈπ§βπΎβ€οΈππ΄ββ οΈ | + variant β€οΈ one | + variant β€ two | + {6:Press ENTER or type command to continue}^ | + ]]) + + feed '<cr>' + screen:expect([[ + ^ | + {1:~ }|*5 + | + ]]) + + feed ':messages<cr>' + screen:expect([[ + | + {1:~ }| + {3: }| + wow, π³οΈββ§οΈπ§βπΎβ€οΈππ΄ββ οΈ | + variant β€οΈ one | + variant β€ two | + {6:Press ENTER or type command to continue}^ | + ]]) + end) + it('prints lines in Ex mode correctly with a burst of carriage returns #19341', function() command('set number') api.nvim_buf_set_lines(0, 0, 0, true, { 'aaa', 'bbb', 'ccc' }) diff --git a/test/functional/ui/multibyte_spec.lua b/test/functional/ui/multibyte_spec.lua index dc25a09d0d..f16f750ea1 100644 --- a/test/functional/ui/multibyte_spec.lua +++ b/test/functional/ui/multibyte_spec.lua @@ -296,6 +296,86 @@ describe('multibyte rendering', function() ]], } end) + + it('supports emoji with variant selectors and ZWJ', function() + command('set ruler') + insert('π³οΈββ§οΈ') + screen:expect([[ + ^π³οΈββ§οΈ | + {1:~ }|*4 + 1,1 All | + ]]) + + feed('a word<esc>') + screen:expect([[ + π³οΈββ§οΈ wor^d | + {1:~ }|*4 + 1,21-7 All | + ]]) + + feed('0') + screen:expect([[ + ^π³οΈββ§οΈ word | + {1:~ }|*4 + 1,1 All | + ]]) + + feed('l') + screen:expect([[ + π³οΈββ§οΈ^ word | + {1:~ }|*4 + 1,17-3 All | + ]]) + + feed('h') + screen:expect([[ + ^π³οΈββ§οΈ word | + {1:~ }|*4 + 1,1 All | + ]]) + + feed('oβ€οΈ variant selected<esc>') + screen:expect([[ + π³οΈββ§οΈ word | + β€οΈ variant selecte^d | + {1:~ }|*3 + 2,23-19 All | + ]]) + + feed('0') + screen:expect([[ + π³οΈββ§οΈ word | + ^β€οΈ variant selected | + {1:~ }|*3 + 2,1 All | + ]]) + + feed('l') + screen:expect([[ + π³οΈββ§οΈ word | + β€οΈ^ variant selected | + {1:~ }|*3 + 2,7-3 All | + ]]) + + feed('h') + screen:expect([[ + π³οΈββ§οΈ word | + ^β€οΈ variant selected | + {1:~ }|*3 + 2,1 All | + ]]) + + -- without selector: single width (note column 18 and not 19) + feed('oβ€ variant selected<esc>') + screen:expect([[ + π³οΈββ§οΈ word | + β€οΈ variant selected | + β€ variant selecte^d | + {1:~ }|*2 + 3,20-18 All | + ]]) + end) end) describe('multibyte rendering: statusline', function() @@ -348,11 +428,12 @@ describe('multibyte rendering: statusline', function() it('non-printable followed by MAX_MCO unicode combination points', function() command('set statusline=Βα·°β―ΜΈββ§β') -- U+9F + U+1DF0 + U+20EF + U+0338 + U+20D0 + U+20E7 + U+20DD + -- TODO: not ideal, better with plain ">" and then space+combining screen:expect([[ - ^ | - {1:~ }| - {3:<9f><1df0><20ef><0338><20d0><20e7><20dd>}| - | + ^ | + {1:~ }| + {3:<9f>α·°β―ΜΈββ§β }| + | ]]) end) @@ -368,9 +449,20 @@ describe('multibyte rendering: statusline', function() } end) - it('unprintable chars in filename with default stl', function() + it('emoji with ZWJ in filename with default stl', function() command('file π§βπ»') - -- TODO: this is wrong but avoids a crash + screen:expect { + grid = [[ + ^ | + {1:~ }| + {3:π§βπ» }| + | + ]], + } + end) + + it('unprintable chars in filename with default stl', function() + command('file π§βπ»') screen:expect { grid = [[ ^ | @@ -381,15 +473,27 @@ describe('multibyte rendering: statusline', function() } end) - it('unprintable chars in filename with custom stl', function() + it('emoji with ZWJ in filename with custom stl', function() command('set statusline=xx%#ErrorMsg#%f%##yy') command('file π§βπ»') - -- TODO: this is also wrong but also avoids a crash screen:expect { grid = [[ ^ | {1:~ }| - {3:xx}{9:π§<200d>π»}{3:yy }| + {3:xx}{9:π§βπ»}{3:yy }| + | + ]], + } + end) + + it('unprintable chars in filename with custom stl', function() + command('set statusline=xx%#ErrorMsg#%f%##yy') + command('file π§βπ»') + screen:expect { + grid = [[ + ^ | + {1:~ }| + {3:xx}{9:π§<200b>π»}{3:yy }| | ]], } diff --git a/test/old/testdir/test_functions.vim b/test/old/testdir/test_functions.vim index 7047a62017..ffe7f3fb39 100644 --- a/test/old/testdir/test_functions.vim +++ b/test/old/testdir/test_functions.vim @@ -3663,7 +3663,7 @@ func Test_string_reverse() call assert_equal('', reverse(v:_null_string)) for [s1, s2] in [['', ''], ['a', 'a'], ['ab', 'ba'], ['abc', 'cba'], \ ['abcd', 'dcba'], ['Β«-Β«-Β»-Β»', 'Β»-Β»-Β«-Β«'], - \ ['π¦', 'π¦'], ['π¦π§', 'π§π¦'], ['π¦π§π¨', 'π¨π§π¦'], + \ ['π¦', 'π¦'], ['π¦π§', 'π¦π§'], ['π¦π§π¨', 'π¨π¦π§'], \ ['π¦Β«π§-π¨Β»π©', 'π©Β»π¨-π§Β«π¦']] call assert_equal(s2, reverse(s1)) endfor diff --git a/test/old/testdir/test_normal.vim b/test/old/testdir/test_normal.vim index 8088b1fc57..3ebc9a69a4 100644 --- a/test/old/testdir/test_normal.vim +++ b/test/old/testdir/test_normal.vim @@ -3897,9 +3897,9 @@ func Test_normal_count_after_operator() bw! endfunc -func Test_normal_gj_on_extra_wide_char() +func Test_normal_gj_on_6_cell_wide_unprintable_char() new | 25vsp - let text='1 foooooooo ar e insβzwe1 foooooooo insβzwei' . + let text='1 foooooooo ar e insβzwe1 foooooooo insβzwei' . \ ' i drei vier fΓΌnf sechs sieben acht un zehn elf zwΓΆfl' . \ ' dreizehn v ierzehn fΓΌnfzehn' put =text diff --git a/test/unit/mbyte_spec.lua b/test/unit/mbyte_spec.lua index 8fcc67d20b..787a8862ae 100644 --- a/test/unit/mbyte_spec.lua +++ b/test/unit/mbyte_spec.lua @@ -3,8 +3,15 @@ local itp = t.gen_itp(it) local ffi = t.ffi local eq = t.eq +local to_cstr = t.to_cstr +local ok = t.ok -local lib = t.cimport('./src/nvim/mbyte.h', './src/nvim/charset.h', './src/nvim/grid.h') +local lib = t.cimport( + './src/nvim/mbyte.h', + './src/nvim/charset.h', + './src/nvim/grid.h', + './src/nvim/option_vars.h' +) describe('mbyte', function() -- Convert from bytes to string @@ -45,12 +52,21 @@ describe('mbyte', function() end) end - describe('utfc_ptr2schar_len', function() + describe('utfc_ptr2schar', function() local function test_seq(seq) local firstc = ffi.new('int[1]') local buf = ffi.new('char[32]') - lib.schar_get(buf, lib.utfc_ptr2schar_len(to_string(seq), #seq, firstc)) - return { ffi.string(buf), firstc[0] } + lib.schar_get(buf, lib.utfc_ptr2schar(to_string(seq), firstc)) + local str = ffi.string(buf) + if 1 > 2 then -- for debugging + local tabel = {} + for i = 1, #str do + table.insert(tabel, string.format('0x%02x', string.byte(str, i))) + end + print('{ ' .. table.concat(tabel, ', ') .. ' }') + io.stdout:flush() + end + return { str, firstc[0] } end local function byte(val) @@ -88,7 +104,9 @@ describe('mbyte', function() eq(byte(0x7f), test_seq { 0x7f, 0xc2, 0x80 }) -- Combining character is U+0300 - eq({ '\x7f\xcc\x80', 0x7f }, test_seq { 0x7f, 0xcc, 0x80 }) + eq({ '\x29\xcc\x80', 0x29 }, test_seq { 0x29, 0xcc, 0x80 }) + -- invalid start byte for combining + eq({ '\x7f', 0x7f }, test_seq { 0x7f, 0xcc, 0x80 }) -- No UTF-8 sequence eq({ '', 0xc2 }, test_seq { 0xc2, 0x7f, 0xcc }) @@ -102,18 +120,21 @@ describe('mbyte', function() itp('4-byte sequences', function() -- No following combining character eq(byte(0x7f), test_seq { 0x7f, 0x7f, 0xcc, 0x80 }) + eq(byte(0x29), test_seq { 0x29, 0x29, 0xcc, 0x80 }) -- No second UTF-8 character eq(byte(0x7f), test_seq { 0x7f, 0xc2, 0xcc, 0x80 }) -- Combining character U+0300 - eq({ '\x7f\xcc\x80', 0x7f }, test_seq { 0x7f, 0xcc, 0x80, 0xcc }) + eq({ '\x29\xcc\x80', 0x29 }, test_seq { 0x29, 0xcc, 0x80, 0xcc }) -- No UTF-8 sequence eq({ '', 0xc2 }, test_seq { 0xc2, 0x7f, 0xcc, 0x80 }) -- No following UTF-8 character eq({ '\xc2\x80', 0x80 }, test_seq { 0xc2, 0x80, 0xcc, 0xcc }) -- Combining character U+0301 - eq({ '\xc2\x80\xcc\x81', 0x80 }, test_seq { 0xc2, 0x80, 0xcc, 0x81 }) + eq({ '\xc2\xbc\xcc\x81', 0xbc }, test_seq { 0xc2, 0xbc, 0xcc, 0x81 }) + -- U+0080 : not a valid start char + eq({ '\xc2\x80', 0x80 }, test_seq { 0xc2, 0x80, 0xcc, 0x81 }) -- One UTF-8 character eq({ '\xf4\x80\x80\x80', 0x100000 }, test_seq { 0xf4, 0x80, 0x80, 0x80 }) @@ -126,36 +147,36 @@ describe('mbyte', function() eq(byte(0x7f), test_seq { 0x7f, 0xc2, 0xcc, 0x80, 0x80 }) -- Combining character U+0300 - eq({ '\x7f\xcc\x80', 0x7f }, test_seq { 0x7f, 0xcc, 0x80, 0xcc, 0x00 }) + eq({ '\x29\xcc\x80', 0x29 }, test_seq { 0x29, 0xcc, 0x80, 0xcc, 0x00 }) -- Combining characters U+0300 and U+0301 - eq({ '\x7f\xcc\x80\xcc\x81', 0x7f }, test_seq { 0x7f, 0xcc, 0x80, 0xcc, 0x81 }) + eq({ '\x29\xcc\x80\xcc\x81', 0x29 }, test_seq { 0x29, 0xcc, 0x80, 0xcc, 0x81 }) -- Combining characters U+0300, U+0301, U+0302 eq( - { '\x7f\xcc\x80\xcc\x81\xcc\x82', 0x7f }, - test_seq { 0x7f, 0xcc, 0x80, 0xcc, 0x81, 0xcc, 0x82 } + { '\x29\xcc\x80\xcc\x81\xcc\x82', 0x29 }, + test_seq { 0x29, 0xcc, 0x80, 0xcc, 0x81, 0xcc, 0x82 } ) -- Combining characters U+0300, U+0301, U+0302, U+0303 eq( - { '\x7f\xcc\x80\xcc\x81\xcc\x82\xcc\x83', 0x7f }, - test_seq { 0x7f, 0xcc, 0x80, 0xcc, 0x81, 0xcc, 0x82, 0xcc, 0x83 } + { '\x29\xcc\x80\xcc\x81\xcc\x82\xcc\x83', 0x29 }, + test_seq { 0x29, 0xcc, 0x80, 0xcc, 0x81, 0xcc, 0x82, 0xcc, 0x83 } ) -- Combining characters U+0300, U+0301, U+0302, U+0303, U+0304 eq( - { '\x7f\xcc\x80\xcc\x81\xcc\x82\xcc\x83\xcc\x84', 0x7f }, - test_seq { 0x7f, 0xcc, 0x80, 0xcc, 0x81, 0xcc, 0x82, 0xcc, 0x83, 0xcc, 0x84 } + { '\x29\xcc\x80\xcc\x81\xcc\x82\xcc\x83\xcc\x84', 0x29 }, + test_seq { 0x29, 0xcc, 0x80, 0xcc, 0x81, 0xcc, 0x82, 0xcc, 0x83, 0xcc, 0x84 } ) -- Combining characters U+0300, U+0301, U+0302, U+0303, U+0304, U+0305 eq( - { '\x7f\xcc\x80\xcc\x81\xcc\x82\xcc\x83\xcc\x84\xcc\x85', 0x7f }, - test_seq { 0x7f, 0xcc, 0x80, 0xcc, 0x81, 0xcc, 0x82, 0xcc, 0x83, 0xcc, 0x84, 0xcc, 0x85 } + { '\x29\xcc\x80\xcc\x81\xcc\x82\xcc\x83\xcc\x84\xcc\x85', 0x29 }, + test_seq { 0x29, 0xcc, 0x80, 0xcc, 0x81, 0xcc, 0x82, 0xcc, 0x83, 0xcc, 0x84, 0xcc, 0x85 } ) -- Combining characters U+0300, U+0301, U+0302, U+0303, U+0304, U+0305, U+0306 eq( - { '\x7f\xcc\x80\xcc\x81\xcc\x82\xcc\x83\xcc\x84\xcc\x85\xcc\x86', 0x7f }, + { '\x29\xcc\x80\xcc\x81\xcc\x82\xcc\x83\xcc\x84\xcc\x85\xcc\x86', 0x29 }, test_seq { - 0x7f, + 0x29, 0xcc, 0x80, 0xcc, @@ -175,18 +196,18 @@ describe('mbyte', function() -- Only three following combining characters U+0300, U+0301, U+0302 eq( - { '\x7f\xcc\x80\xcc\x81\xcc\x82', 0x7f }, - test_seq { 0x7f, 0xcc, 0x80, 0xcc, 0x81, 0xcc, 0x82, 0xc2, 0x80, 0xcc, 0x84, 0xcc, 0x85 } + { '\x29\xcc\x80\xcc\x81\xcc\x82', 0x29 }, + test_seq { 0x29, 0xcc, 0x80, 0xcc, 0x81, 0xcc, 0x82, 0xc2, 0x80, 0xcc, 0x84, 0xcc, 0x85 } ) -- No UTF-8 sequence eq({ '', 0xc2 }, test_seq { 0xc2, 0x7f, 0xcc, 0x80, 0x80 }) -- No following UTF-8 character - eq({ '\xc2\x80', 0x80 }, test_seq { 0xc2, 0x80, 0xcc, 0xcc, 0x80 }) + eq({ '\xc2\xbc', 0xbc }, test_seq { 0xc2, 0xbc, 0xcc, 0xcc, 0x80 }) -- Combining character U+0301 - eq({ '\xc2\x80\xcc\x81', 0x80 }, test_seq { 0xc2, 0x80, 0xcc, 0x81, 0x7f }) + eq({ '\xc2\xbc\xcc\x81', 0xbc }, test_seq { 0xc2, 0xbc, 0xcc, 0x81, 0x7f }) -- Combining character U+0301 - eq({ '\xc2\x80\xcc\x81', 0x80 }, test_seq { 0xc2, 0x80, 0xcc, 0x81, 0xcc }) + eq({ '\xc2\xbc\xcc\x81', 0xbc }, test_seq { 0xc2, 0xbc, 0xcc, 0x81, 0xcc }) -- One UTF-8 character eq({ '\xf4\x80\x80\x80', 0x100000 }, test_seq { 0xf4, 0x80, 0x80, 0x80, 0x7f }) @@ -205,8 +226,6 @@ describe('mbyte', function() end) describe('utf_cp_bounds_len', function() - local to_cstr = t.to_cstr - local tests = { { name = 'for valid string', @@ -273,4 +292,52 @@ describe('mbyte', function() eq(expected_offsets, { b = b_offsets, e = e_offsets }) end) end) + + itp('utf_head_off', function() + local function check(str, expected_glyphs) + local len = #str + local cstr = to_cstr(str) + local breaks = { 0 } -- SOT + local pos = 0 + local mb_glyphs = {} + while pos < len do + local clen = lib.utfc_ptr2len(cstr + pos) + ok(clen > 0) -- otherwise we get stuck + if clen > 1 then + table.insert(mb_glyphs, string.sub(str, pos + 1, pos + clen)) + end + pos = pos + clen + table.insert(breaks, pos) + end + eq(breaks[#breaks], len) -- include EOT as break + -- we could also send in breaks, but this is more human readable + eq(mb_glyphs, expected_glyphs) + + for i = 1, #breaks - 1 do + local start, next = breaks[i], breaks[i + 1] + + for p = start, next - 1 do + eq(p - start, lib.utf_head_off(cstr, cstr + p)) + end + end + eq(0, lib.utf_head_off(cstr, cstr + len)) -- NUL byte is safe + end + -- stylua doesn't like ZWJ chars.. + -- stylua: ignore start + check('hej och hΓ₯ π§βπΎ!', { 'Γ₯', 'π§βπΎ' }) + -- emoji only (various kinds of combinations, use g8 to see them) + check("π³οΈββ§οΈπ§βπΎβ€οΈππ΄ββ οΈ", {"π³οΈββ§οΈ", "π§βπΎ", "β€οΈ", "π", "π΄ββ οΈ"}) + check('π³οΈββ§οΈxyπ§βπΎ\rβ€οΈπΓ₯π΄ββ οΈΒ', { 'π³οΈββ§οΈ', 'π§βπΎ', 'β€οΈ', 'π', 'Γ₯', 'π΄ββ οΈ', 'Β' }) + + check('π¦π
±οΈ π¦π½ π¦π¨π¦ π²π½πΉπ±',{'π¦', 'π
±οΈ', 'π¦π½', 'π¦π¨', 'π¦', 'π²π½', 'πΉπ±'}) + check('π΄σ §σ ’σ ³σ £σ ΄σ Ώπ΄σ §σ ’σ ·σ ¬σ ³σ Ώ', {'π΄σ §σ ’σ ³σ £σ ΄σ Ώ', 'π΄σ §σ ’σ ·σ ¬σ ³σ Ώ'}) + + lib.p_arshape = true -- default + check('Ψ³ΩΨ§Ω
', { 'Ψ³', 'ΩΨ§', 'Ω
' }) + lib.p_arshape = false + check('Ψ³ΩΨ§Ω
', { 'Ψ³', 'Ω', 'Ψ§', 'Ω
' }) + + check('LΜΜΜΜΜΜoΜΜΜΜΜΜrΜΜΜΜΜΜeΜΜΜ
ΜΜΜmΜ
ΜΜΜΜΜ', {'LΜΜΜΜΜΜ', 'oΜΜΜΜΜΜ', 'rΜΜΜΜΜΜ', 'eΜΜΜ
ΜΜΜ', 'mΜ
ΜΜΜΜΜ'}) + -- stylua: ignore end + end) end) |