aniani/vim
0
0
Fork 1
mirror of https://github.com/vim/vim.git synced 2025-07-26 11:04:33 -04:00
Code
vim/src/testdir/test_regexp_utf8.vim

209 lines
8.7 KiB
VimL
Raw Normal View History

patch 7.4.1700 Problem: Equivalence classes are not properly tested. Solution: Add tests for multi-byte and latin1. Fix an error. (Owen Leibman)
2016-04-03 14:02:02 +02:00
" Tests for regexp in utf8 encoding
func s:equivalence_test()
let str = "AÀÁÂÃÄÅĀĂĄǍǞǠẢ BḂḆ CÇĆĈĊČ DĎĐḊḎḐ EÈÉÊËĒĔĖĘĚẺẼ FḞ GĜĞĠĢǤǦǴḠ HĤĦḢḦḨ IÌÍÎÏĨĪĬĮİǏỈ JĴ KĶǨḰḴ LĹĻĽĿŁḺ MḾṀ NÑŃŅŇṄṈ OÒÓÔÕÖØŌŎŐƠǑǪǬỎ PṔṖ Q RŔŖŘṘṞ SŚŜŞŠṠ TŢŤŦṪṮ UÙÚÛÜŨŪŬŮŰŲƯǓỦ VṼ WŴẀẂẄẆ XẊẌ YÝŶŸẎỲỶỸ ZŹŻŽƵẐẔ aàáâãäåāăąǎǟǡả bḃḇ cçćĉċč dďđḋḏḑ eèéêëēĕėęěẻẽ fḟ gĝğġģǥǧǵḡ hĥħḣḧḩẖ iìíîïĩīĭįǐỉ jĵǰ kķǩḱḵ lĺļľŀłḻ mḿṁ nñńņňʼnṅṉ oòóôõöøōŏőơǒǫǭỏ pṕṗ q rŕŗřṙṟ sśŝşšṡ tţťŧṫṯẗ uùúûüũūŭůűųưǔủ vṽ wŵẁẃẅẇẘ xẋẍ yýÿŷẏẙỳỷỹ zźżžƶẑẕ"
let groups = split(str)
for group1 in groups
for c in split(group1, '\zs')
" next statement confirms that equivalence class matches every
" character in group
call assert_match('^[[=' . c . '=]]*$', group1)
for group2 in groups
if group2 != group1
" next statement converts that equivalence class doesn't match
" character in any other group
call assert_equal(-1, match(group2, '[[=' . c . '=]]'))
endif
endfor
endfor
endfor
endfunc
func Test_equivalence_re1()
set re=1
call s:equivalence_test()
patch 7.4.2222 Problem: Sourcing a script where a character has 0x80 as a second byte does not work. (Filipe L B Correia) Solution: Turn 0x80 into K_SPECIAL KS_SPECIAL KE_FILLER. (Christian Brabandt, closes #728) Add a test case.
2016-08-16 22:50:55 +02:00
set re=0
patch 7.4.1700 Problem: Equivalence classes are not properly tested. Solution: Add tests for multi-byte and latin1. Fix an error. (Owen Leibman)
2016-04-03 14:02:02 +02:00
endfunc
func Test_equivalence_re2()
set re=2
call s:equivalence_test()
patch 7.4.2222 Problem: Sourcing a script where a character has 0x80 as a second byte does not work. (Filipe L B Correia) Solution: Turn 0x80 into K_SPECIAL KS_SPECIAL KE_FILLER. (Christian Brabandt, closes #728) Add a test case.
2016-08-16 22:50:55 +02:00
set re=0
patch 7.4.1700 Problem: Equivalence classes are not properly tested. Solution: Add tests for multi-byte and latin1. Fix an error. (Owen Leibman)
2016-04-03 14:02:02 +02:00
endfunc
patch 7.4.1783 Problem: The old regexp engine doesn't handle character classes correctly. (Manuel Ortega) Solution: Use regmbc() instead of regc(). Add a test.
2016-04-24 14:40:12 +02:00
func s:classes_test()
patch 7.4.1785 Problem: Regexp test fails on windows. Solution: set 'isprint' to the right value for testing.
2016-04-24 15:11:02 +02:00
set isprint=@,161-255
patch 7.4.1783 Problem: The old regexp engine doesn't handle character classes correctly. (Manuel Ortega) Solution: Use regmbc() instead of regc(). Add a test.
2016-04-24 14:40:12 +02:00
call assert_equal('Motörhead', matchstr('Motörhead', '[[:print:]]\+'))
patch 8.0.0519: character classes are not well tested Problem: Character classes are not well tested. They can differ between platforms. Solution: Add tests. In the documentation make clear which classes depend on what library function. Only use :cntrl: and :graph: for ASCII. (Kazunobu Kuriyama, Dominique Pelle, closes #1560) Update the documentation.
2017-03-29 15:31:20 +02:00
let alnumchars = ''
patch 7.4.1783 Problem: The old regexp engine doesn't handle character classes correctly. (Manuel Ortega) Solution: Use regmbc() instead of regc(). Add a test.
2016-04-24 14:40:12 +02:00
let alphachars = ''
patch 8.0.0519: character classes are not well tested Problem: Character classes are not well tested. They can differ between platforms. Solution: Add tests. In the documentation make clear which classes depend on what library function. Only use :cntrl: and :graph: for ASCII. (Kazunobu Kuriyama, Dominique Pelle, closes #1560) Update the documentation.
2017-03-29 15:31:20 +02:00
let backspacechar = ''
let blankchars = ''
let cntrlchars = ''
let digitchars = ''
let escapechar = ''
let graphchars = ''
patch 7.4.1783 Problem: The old regexp engine doesn't handle character classes correctly. (Manuel Ortega) Solution: Use regmbc() instead of regc(). Add a test.
2016-04-24 14:40:12 +02:00
let lowerchars = ''
let printchars = ''
let punctchars = ''
patch 8.0.0519: character classes are not well tested Problem: Character classes are not well tested. They can differ between platforms. Solution: Add tests. In the documentation make clear which classes depend on what library function. Only use :cntrl: and :graph: for ASCII. (Kazunobu Kuriyama, Dominique Pelle, closes #1560) Update the documentation.
2017-03-29 15:31:20 +02:00
let returnchar = ''
let spacechars = ''
let tabchar = ''
let upperchars = ''
patch 7.4.1783 Problem: The old regexp engine doesn't handle character classes correctly. (Manuel Ortega) Solution: Use regmbc() instead of regc(). Add a test.
2016-04-24 14:40:12 +02:00
let xdigitchars = ''
patch 8.1.0862: no verbose version of character classes Problem: No verbose version of character classes. Solution: Add [:ident:], [:keyword:] and [:fname:]. (Ozaki Kiichi, closes #1373)
2019-01-31 15:34:40 +01:00
let identchars = ''
let identchars1 = ''
let kwordchars = ''
let kwordchars1 = ''
let fnamechars = ''
let fnamechars1 = ''
patch 7.4.1783 Problem: The old regexp engine doesn't handle character classes correctly. (Manuel Ortega) Solution: Use regmbc() instead of regc(). Add a test.
2016-04-24 14:40:12 +02:00
let i = 1
while i <= 255
let c = nr2char(i)
if c =~ '[[:alpha:]]'
let alphachars .= c
endif
if c =~ '[[:alnum:]]'
let alnumchars .= c
endif
patch 8.0.0519: character classes are not well tested Problem: Character classes are not well tested. They can differ between platforms. Solution: Add tests. In the documentation make clear which classes depend on what library function. Only use :cntrl: and :graph: for ASCII. (Kazunobu Kuriyama, Dominique Pelle, closes #1560) Update the documentation.
2017-03-29 15:31:20 +02:00
if c =~ '[[:backspace:]]'
let backspacechar .= c
endif
if c =~ '[[:blank:]]'
let blankchars .= c
endif
if c =~ '[[:cntrl:]]'
let cntrlchars .= c
endif
if c =~ '[[:digit:]]'
let digitchars .= c
endif
if c =~ '[[:escape:]]'
let escapechar .= c
endif
if c =~ '[[:graph:]]'
let graphchars .= c
endif
if c =~ '[[:lower:]]'
let lowerchars .= c
endif
patch 7.4.1783 Problem: The old regexp engine doesn't handle character classes correctly. (Manuel Ortega) Solution: Use regmbc() instead of regc(). Add a test.
2016-04-24 14:40:12 +02:00
if c =~ '[[:print:]]'
let printchars .= c
endif
if c =~ '[[:punct:]]'
let punctchars .= c
endif
patch 8.0.0519: character classes are not well tested Problem: Character classes are not well tested. They can differ between platforms. Solution: Add tests. In the documentation make clear which classes depend on what library function. Only use :cntrl: and :graph: for ASCII. (Kazunobu Kuriyama, Dominique Pelle, closes #1560) Update the documentation.
2017-03-29 15:31:20 +02:00
if c =~ '[[:return:]]'
let returnchar .= c
endif
if c =~ '[[:space:]]'
let spacechars .= c
endif
if c =~ '[[:tab:]]'
let tabchar .= c
endif
if c =~ '[[:upper:]]'
let upperchars .= c
endif
patch 7.4.1783 Problem: The old regexp engine doesn't handle character classes correctly. (Manuel Ortega) Solution: Use regmbc() instead of regc(). Add a test.
2016-04-24 14:40:12 +02:00
if c =~ '[[:xdigit:]]'
let xdigitchars .= c
endif
patch 8.1.0862: no verbose version of character classes Problem: No verbose version of character classes. Solution: Add [:ident:], [:keyword:] and [:fname:]. (Ozaki Kiichi, closes #1373)
2019-01-31 15:34:40 +01:00
if c =~ '[[:ident:]]'
let identchars .= c
endif
if c =~ '\i'
let identchars1 .= c
endif
if c =~ '[[:keyword:]]'
let kwordchars .= c
endif
if c =~ '\k'
let kwordchars1 .= c
endif
if c =~ '[[:fname:]]'
let fnamechars .= c
endif
if c =~ '\f'
let fnamechars1 .= c
endif
patch 7.4.1783 Problem: The old regexp engine doesn't handle character classes correctly. (Manuel Ortega) Solution: Use regmbc() instead of regc(). Add a test.
2016-04-24 14:40:12 +02:00
let i += 1
endwhile
call assert_equal('ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz', alphachars)
call assert_equal('0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz', alnumchars)
patch 8.0.0519: character classes are not well tested Problem: Character classes are not well tested. They can differ between platforms. Solution: Add tests. In the documentation make clear which classes depend on what library function. Only use :cntrl: and :graph: for ASCII. (Kazunobu Kuriyama, Dominique Pelle, closes #1560) Update the documentation.
2017-03-29 15:31:20 +02:00
call assert_equal("\b", backspacechar)
call assert_equal("\t ", blankchars)
patch 8.0.0529: line in test commented out Problem: Line in test commented out. Solution: Uncomment the lines for character classes that were failing before 8.0.0519. (Dominique Pelle, closes #1599)
2017-03-30 22:20:29 +02:00
call assert_equal("\x01\x02\x03\x04\x05\x06\x07\b\t\n\x0b\f\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\e\x1c\x1d\x1e\x1f\x7f", cntrlchars)
patch 8.0.0519: character classes are not well tested Problem: Character classes are not well tested. They can differ between platforms. Solution: Add tests. In the documentation make clear which classes depend on what library function. Only use :cntrl: and :graph: for ASCII. (Kazunobu Kuriyama, Dominique Pelle, closes #1560) Update the documentation.
2017-03-29 15:31:20 +02:00
call assert_equal("0123456789", digitchars)
call assert_equal("\<Esc>", escapechar)
patch 8.0.0529: line in test commented out Problem: Line in test commented out. Solution: Uncomment the lines for character classes that were failing before 8.0.0519. (Dominique Pelle, closes #1599)
2017-03-30 22:20:29 +02:00
call assert_equal('!"#$%&''()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~', graphchars)
patch 8.0.0519: character classes are not well tested Problem: Character classes are not well tested. They can differ between platforms. Solution: Add tests. In the documentation make clear which classes depend on what library function. Only use :cntrl: and :graph: for ASCII. (Kazunobu Kuriyama, Dominique Pelle, closes #1560) Update the documentation.
2017-03-29 15:31:20 +02:00
call assert_equal('abcdefghijklmnopqrstuvwxyzµßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ', lowerchars)
patch 7.4.1783 Problem: The old regexp engine doesn't handle character classes correctly. (Manuel Ortega) Solution: Use regmbc() instead of regc(). Add a test.
2016-04-24 14:40:12 +02:00
call assert_equal(' !"#$%&''()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~ ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ', printchars)
call assert_equal('!"#$%&''()*+,-./:;<=>?@[\]^_`{|}~', punctchars)
patch 8.0.0519: character classes are not well tested Problem: Character classes are not well tested. They can differ between platforms. Solution: Add tests. In the documentation make clear which classes depend on what library function. Only use :cntrl: and :graph: for ASCII. (Kazunobu Kuriyama, Dominique Pelle, closes #1560) Update the documentation.
2017-03-29 15:31:20 +02:00
call assert_equal('ABCDEFGHIJKLMNOPQRSTUVWXYZÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞ', upperchars)
call assert_equal("\r", returnchar)
call assert_equal("\t\n\x0b\f\r ", spacechars)
call assert_equal("\t", tabchar)
patch 7.4.1783 Problem: The old regexp engine doesn't handle character classes correctly. (Manuel Ortega) Solution: Use regmbc() instead of regc(). Add a test.
2016-04-24 14:40:12 +02:00
call assert_equal('0123456789ABCDEFabcdef', xdigitchars)
patch 8.1.0862: no verbose version of character classes Problem: No verbose version of character classes. Solution: Add [:ident:], [:keyword:] and [:fname:]. (Ozaki Kiichi, closes #1373)
2019-01-31 15:34:40 +01:00
if has('win32')
let identchars_ok = '0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz€‚ƒ„…†‡ˆ‰Š‹ŒŽ‘’“”•–—˜™š›œžŸ ¡¢£¤¥¦§µÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ'
let kwordchars_ok = '0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyzµÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ'
elseif has('ebcdic')
let identchars_ok = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz€ŒŽœž¬®µº¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ'
let kwordchars_ok = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz€ŒŽœž¬®µº¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ'
else
let identchars_ok = '0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyzµÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ'
let kwordchars_ok = '0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyzµÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ'
endif
if has('win32')
let fnamechars_ok = '!#$%+,-./0123456789:=@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]_abcdefghijklmnopqrstuvwxyz{}~ ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ'
elseif has('amiga')
let fnamechars_ok = '$+,-./0123456789:ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz~ ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ'
elseif has('vms')
let fnamechars_ok = '#$%+,-./0123456789:;<>ABCDEFGHIJKLMNOPQRSTUVWXYZ[]_abcdefghijklmnopqrstuvwxyz~ ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ'
elseif has('ebcdic')
let fnamechars_ok = '#$%+,-./=ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz~ ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ'
else
let fnamechars_ok = '#$%+,-./0123456789=ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz~ ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ'
endif
call assert_equal(identchars_ok, identchars)
call assert_equal(kwordchars_ok, kwordchars)
call assert_equal(fnamechars_ok, fnamechars)
call assert_equal(identchars1, identchars)
call assert_equal(kwordchars1, kwordchars)
call assert_equal(fnamechars1, fnamechars)
patch 7.4.1783 Problem: The old regexp engine doesn't handle character classes correctly. (Manuel Ortega) Solution: Use regmbc() instead of regc(). Add a test.
2016-04-24 14:40:12 +02:00
endfunc
func Test_classes_re1()
set re=1
call s:classes_test()
patch 7.4.2222 Problem: Sourcing a script where a character has 0x80 as a second byte does not work. (Filipe L B Correia) Solution: Turn 0x80 into K_SPECIAL KS_SPECIAL KE_FILLER. (Christian Brabandt, closes #728) Add a test case.
2016-08-16 22:50:55 +02:00
set re=0
patch 7.4.1783 Problem: The old regexp engine doesn't handle character classes correctly. (Manuel Ortega) Solution: Use regmbc() instead of regc(). Add a test.
2016-04-24 14:40:12 +02:00
endfunc
func Test_classes_re2()
set re=2
call s:classes_test()
patch 7.4.2222 Problem: Sourcing a script where a character has 0x80 as a second byte does not work. (Filipe L B Correia) Solution: Turn 0x80 into K_SPECIAL KS_SPECIAL KE_FILLER. (Christian Brabandt, closes #728) Add a test case.
2016-08-16 22:50:55 +02:00
set re=0
endfunc
patch 8.0.0623: error for invalid regexp is not very informative Problem: The message "Invalid range" is used for multiple errors. Solution: Add two more specific error messages. (Itchyny, Ken Hamada)
2017-06-05 16:54:08 +02:00
func Test_reversed_range()
for re in range(0, 2)
exe 'set re=' . re
call assert_fails('call match("abc def", "[c-a]")', 'E944:')
endfor
set re=0
endfunc
func Test_large_class()
set re=1
call assert_fails('call match("abc def", "[\u3000-\u4000]")', 'E945:')
set re=2
call assert_equal(0, 'abc def' =~# '[\u3000-\u4000]')
call assert_equal(1, "\u3042" =~# '[\u3000-\u4000]')
set re=0
endfunc
Copy Permalink