Mercurial > vim
view src/testdir/test_regexp_utf8.vim @ 10724:ae1c6bf22e5f v8.0.0252
patch 8.0.0252: not properly recognizing word characters between 128 and 255
commit https://github.com/vim/vim/commit/4019cf90b8657d4ab1c39744db63550f44f405a2
Author: Bram Moolenaar <Bram@vim.org>
Date: Sat Jan 28 16:39:34 2017 +0100
patch 8.0.0252: not properly recognizing word characters between 128 and 255
Problem: Characters below 256 that are not one byte are not always
recognized as word characters.
Solution: Make vim_iswordc() and vim_iswordp() work the same way. Add a test
for this. (Ozaki Kiichi)
author | Christian Brabandt <cb@256bit.org> |
---|---|
date | Sat, 28 Jan 2017 16:45:04 +0100 |
parents | bff8a09016a5 |
children | 588de97b40e7 |
line wrap: on
line source
" Tests for regexp in utf8 encoding if !has('multi_byte') finish endif 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 . '=]]*$', group1) for group2 in groups if group2 != group1 " next statement converts that equivalence class doesn't match " character in any other group call assert_equal(-1, match(group2, '[[=' . c . '=]]')) endif endfor endfor endfor endfunc func Test_equivalence_re1() set re=1 call s:equivalence_test() set re=0 endfunc func Test_equivalence_re2() set re=2 call s:equivalence_test() set re=0 endfunc func s:classes_test() set isprint=@,161-255 call assert_equal('Motörhead', matchstr('Motörhead', '[[:print:]]\+')) let alphachars = '' let lowerchars = '' let upperchars = '' let alnumchars = '' let printchars = '' let punctchars = '' let xdigitchars = '' let i = 1 while i <= 255 let c = nr2char(i) if c =~ '[[:alpha:]]' let alphachars .= c endif if c =~ '[[:lower:]]' let lowerchars .= c endif if c =~ '[[:upper:]]' let upperchars .= c endif if c =~ '[[:alnum:]]' let alnumchars .= c endif if c =~ '[[:print:]]' let printchars .= c endif if c =~ '[[:punct:]]' let punctchars .= c endif if c =~ '[[:xdigit:]]' let xdigitchars .= c endif let i += 1 endwhile call assert_equal('ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz', alphachars) call assert_equal('abcdefghijklmnopqrstuvwxyzµßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ', lowerchars) call assert_equal('ABCDEFGHIJKLMNOPQRSTUVWXYZÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞ', upperchars) call assert_equal('0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz', alnumchars) call assert_equal(' !"#$%&''()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~ ¡¢£¤¥¦§¨©ª«¬®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ', printchars) call assert_equal('!"#$%&''()*+,-./:;<=>?@[\]^_`{|}~', punctchars) call assert_equal('0123456789ABCDEFabcdef', xdigitchars) endfunc func Test_classes_re1() set re=1 call s:classes_test() set re=0 endfunc func Test_classes_re2() set re=2 call s:classes_test() set re=0 endfunc