mirror of
https://github.com/neovim/neovim.git
synced 2026-01-16 09:57:00 +00:00
d2ca90d87e
Problem:
vim.glob.to_lpeg() errors when patterns contain numeric literals
(like the '1' in '.ps*1') because LPeg interprets numeric strings
as indexed grammar rule references. For example:
vim.glob.to_lpeg('.ps*1')
E5108: Lua: rule '1' undefined in given grammar
Solution:
Prefix all rule names with '_' in the end_seg() function to prevent
literal numbers from being interpreted as LPeg indexed rules. This
ensures pattern components like '1', '2', etc. are treated as
regular rule names rather than special references.
273 lines
11 KiB
Lua
273 lines
11 KiB
Lua
local t = require('test.testutil')
|
|
|
|
local eq = t.eq
|
|
|
|
describe('glob', function()
|
|
local match = function(pattern, str)
|
|
return require('vim.glob').to_lpeg(pattern):match(str) ~= nil
|
|
end
|
|
|
|
describe('glob matching', function()
|
|
it('should match literal strings', function()
|
|
eq(true, match('', ''))
|
|
eq(false, match('', 'a'))
|
|
eq(true, match('a', 'a'))
|
|
eq(true, match('.', '.'))
|
|
eq(true, match('/', '/'))
|
|
eq(true, match('abc', 'abc'))
|
|
eq(false, match('abc', 'abcdef'))
|
|
eq(false, match('abc', 'a'))
|
|
eq(false, match('abc', 'bc'))
|
|
eq(false, match('a', 'b'))
|
|
eq(false, match('.', 'a'))
|
|
eq(true, match('$', '$'))
|
|
eq(true, match('a,b', 'a,b'))
|
|
eq(true, match('/dir', '/dir'))
|
|
eq(true, match('dir/', 'dir/'))
|
|
eq(true, match('dir/subdir', 'dir/subdir'))
|
|
eq(false, match('dir/subdir', 'subdir'))
|
|
eq(false, match('dir/subdir', 'dir/subdir/file'))
|
|
eq(true, match('🤠', '🤠'))
|
|
end)
|
|
|
|
it('should match * wildcards', function()
|
|
eq(true, match('*', ''))
|
|
eq(true, match('*', ' '))
|
|
eq(true, match('*', 'a'))
|
|
eq(false, match('*', '/'))
|
|
eq(false, match('*', '/a'))
|
|
eq(false, match('*', 'a/'))
|
|
eq(true, match('*', 'aaa'))
|
|
eq(true, match('*a', 'aa'))
|
|
eq(true, match('*a', 'abca'))
|
|
eq(true, match('*.ts', '.ts'))
|
|
eq(true, match('*.txt', 'file.txt'))
|
|
eq(false, match('*.txt', 'file.txtxt'))
|
|
eq(false, match('*.txt', 'dir/file.txt'))
|
|
eq(false, match('*.txt', '/dir/file.txt'))
|
|
eq(false, match('*.txt', 'C:/dir/file.txt'))
|
|
eq(false, match('*.dir', 'test.dir/file'))
|
|
eq(true, match('file.*', 'file.txt'))
|
|
eq(false, match('file.*', 'not-file.txt'))
|
|
eq(true, match('*/file.txt', 'dir/file.txt'))
|
|
eq(false, match('*/file.txt', 'dir/subdir/file.txt'))
|
|
eq(false, match('*/file.txt', '/dir/file.txt'))
|
|
eq(true, match('dir/*', 'dir/file.txt'))
|
|
eq(false, match('dir/*', 'dir'))
|
|
eq(false, match('dir/*.txt', 'file.txt'))
|
|
eq(true, match('dir/*.txt', 'dir/file.txt'))
|
|
eq(false, match('dir/*.txt', 'dir/subdir/file.txt'))
|
|
eq(false, match('dir/*/file.txt', 'dir/file.txt'))
|
|
eq(true, match('dir/*/file.txt', 'dir/subdir/file.txt'))
|
|
eq(false, match('dir/*/file.txt', 'dir/subdir/subdir/file.txt'))
|
|
eq(true, match('a*b*c*d*e*', 'axbxcxdxe'))
|
|
eq(true, match('a*b*c*d*e*', 'axbxcxdxexxx'))
|
|
eq(true, match('a*b?c*x', 'abxbbxdbxebxczzx'))
|
|
eq(false, match('a*b?c*x', 'abxbbxdbxebxczzy'))
|
|
eq(true, match('a*b*[cy]*d*e*', 'axbxcxdxexxx'))
|
|
eq(true, match('a*b*[cy]*d*e*', 'axbxyxdxexxx'))
|
|
eq(true, match('a*b*[cy]*d*e*', 'axbxxxyxdxexxx'))
|
|
eq(true, match('.ps*1', '.ps1'))
|
|
eq(true, match('.ps*1', '.psaa1'))
|
|
eq(false, match('.ps*1', '.ps1a'))
|
|
end)
|
|
|
|
it('should match ? wildcards', function()
|
|
eq(false, match('?', ''))
|
|
eq(true, match('?', 'a'))
|
|
eq(false, match('??', 'a'))
|
|
eq(false, match('?', 'ab'))
|
|
eq(true, match('??', 'ab'))
|
|
eq(true, match('a?c', 'abc'))
|
|
eq(false, match('a?c', 'a/c'))
|
|
eq(false, match('a/', 'a/.b'))
|
|
eq(true, match('?/?', 'a/b'))
|
|
eq(true, match('/??', '/ab'))
|
|
eq(true, match('/?b', '/ab'))
|
|
eq(false, match('foo?bar', 'foo/bar'))
|
|
end)
|
|
|
|
it('should match ** wildcards', function()
|
|
eq(true, match('**', ''))
|
|
eq(true, match('**', 'a'))
|
|
eq(true, match('**', '/'))
|
|
eq(true, match('**', 'a/'))
|
|
eq(true, match('**', '/a'))
|
|
eq(true, match('**', 'C:/a'))
|
|
eq(true, match('**', 'a/a'))
|
|
eq(true, match('**', 'a/a/a'))
|
|
eq(false, match('/**', '')) -- /** matches leading / literally
|
|
eq(true, match('/**', '/'))
|
|
eq(true, match('/**', '/a/b/c'))
|
|
eq(true, match('**/', '')) -- **/ absorbs trailing /
|
|
eq(false, match('**/', '/a/b/c'))
|
|
eq(true, match('**/**', ''))
|
|
eq(true, match('**/**', 'a'))
|
|
eq(false, match('a/**', ''))
|
|
eq(false, match('a/**', 'a'))
|
|
eq(true, match('a/**', 'a/b'))
|
|
eq(true, match('a/**', 'a/b/c'))
|
|
eq(false, match('a/**', 'b/a'))
|
|
eq(false, match('a/**', '/a'))
|
|
eq(false, match('**/a', ''))
|
|
eq(true, match('**/a', 'a'))
|
|
eq(false, match('**/a', 'a/b'))
|
|
eq(true, match('**/a', '/a'))
|
|
eq(true, match('**/a', '/b/a'))
|
|
eq(true, match('**/a', '/c/b/a'))
|
|
eq(true, match('**/a', '/a/a'))
|
|
eq(true, match('**/a', '/abc/a'))
|
|
eq(false, match('a/**/c', 'a'))
|
|
eq(false, match('a/**/c', 'c'))
|
|
eq(true, match('a/**/c', 'a/c'))
|
|
eq(true, match('a/**/c', 'a/b/c'))
|
|
eq(true, match('a/**/c', 'a/b/b/c'))
|
|
eq(false, match('**/a/**', 'a'))
|
|
eq(true, match('**/a/**', 'a/'))
|
|
eq(false, match('**/a/**', '/dir/a'))
|
|
eq(false, match('**/a/**', 'dir/a'))
|
|
eq(true, match('**/a/**', 'dir/a/'))
|
|
eq(true, match('**/a/**', 'a/dir'))
|
|
eq(true, match('**/a/**', 'dir/a/dir'))
|
|
eq(true, match('**/a/**', '/a/dir'))
|
|
eq(true, match('**/a/**', 'C:/a/dir'))
|
|
eq(false, match('**/a/**', 'a.txt'))
|
|
end)
|
|
|
|
it('should match {} groups', function()
|
|
eq(true, match('{,}', ''))
|
|
eq(true, match('{a,}', ''))
|
|
eq(true, match('{a,}', 'a'))
|
|
eq(true, match('{a,b}', 'a'))
|
|
eq(true, match('{a,b}', 'b'))
|
|
eq(false, match('{a,b}', 'ab'))
|
|
eq(true, match('{ab,cd}', 'ab'))
|
|
eq(false, match('{ab,cd}', 'a'))
|
|
eq(true, match('{ab,cd}', 'cd'))
|
|
eq(true, match('{a,b,c}', 'c'))
|
|
eq(true, match('{a,{b,c}}', 'c'))
|
|
eq(true, match('a{,/}*.txt', 'a.txt'))
|
|
eq(true, match('a{,/}*.txt', 'ab.txt'))
|
|
eq(true, match('a{,/}*.txt', 'a/b.txt'))
|
|
eq(true, match('a{,/}*.txt', 'a/ab.txt'))
|
|
eq(true, match('a/{a{a,b},b}', 'a/aa'))
|
|
eq(true, match('a/{a{a,b},b}', 'a/ab'))
|
|
eq(false, match('a/{a{a,b},b}', 'a/ac'))
|
|
eq(true, match('a/{a{a,b},b}', 'a/b'))
|
|
eq(false, match('a/{a{a,b},b}', 'a/c'))
|
|
eq(true, match('foo{bar,b*z}', 'foobar'))
|
|
eq(true, match('foo{bar,b*z}', 'foobuzz'))
|
|
eq(true, match('foo{bar,b*z}', 'foobarz'))
|
|
eq(true, match('{a,b}/c/{d,e}/**/*est.ts', 'a/c/d/one/two/three.test.ts'))
|
|
eq(true, match('{a,{d,e}b}/c', 'a/c'))
|
|
eq(true, match('{**/a,**/b}', 'b'))
|
|
end)
|
|
|
|
it('should match [] groups', function()
|
|
eq(true, match('[]', '[]')) -- empty [] is a literal
|
|
eq(false, match('[a-z]', ''))
|
|
eq(true, match('[a-z]', 'a'))
|
|
eq(false, match('[a-z]', 'ab'))
|
|
eq(true, match('[a-z]', 'z'))
|
|
eq(true, match('[a-z]', 'j'))
|
|
eq(false, match('[a-f]', 'j'))
|
|
eq(false, match('[a-z]', '`')) -- 'a' - 1
|
|
eq(false, match('[a-z]', '{')) -- 'z' + 1
|
|
eq(false, match('[a-z]', 'A'))
|
|
eq(false, match('[a-z]', '5'))
|
|
eq(true, match('[A-Z]', 'A'))
|
|
eq(true, match('[A-Z]', 'Z'))
|
|
eq(true, match('[A-Z]', 'J'))
|
|
eq(false, match('[A-Z]', '@')) -- 'A' - 1
|
|
eq(false, match('[A-Z]', '[')) -- 'Z' + 1
|
|
eq(false, match('[A-Z]', 'a'))
|
|
eq(false, match('[A-Z]', '5'))
|
|
eq(true, match('[a-zA-Z0-9]', 'z'))
|
|
eq(true, match('[a-zA-Z0-9]', 'Z'))
|
|
eq(true, match('[a-zA-Z0-9]', '9'))
|
|
eq(false, match('[a-zA-Z0-9]', '&'))
|
|
eq(true, match('[?]', '?'))
|
|
eq(false, match('[?]', 'a'))
|
|
eq(true, match('[*]', '*'))
|
|
eq(false, match('[*]', 'a'))
|
|
eq(true, match('[\\!]', '!'))
|
|
eq(true, match('a\\*b', 'a*b'))
|
|
eq(false, match('a\\*b', 'axb'))
|
|
end)
|
|
|
|
it('should match [!...] groups', function()
|
|
eq(true, match('[!]', '[!]')) -- [!] is a literal
|
|
eq(false, match('[!a-z]', ''))
|
|
eq(false, match('[!a-z]', 'a'))
|
|
eq(false, match('[!a-z]', 'z'))
|
|
eq(false, match('[!a-z]', 'j'))
|
|
eq(true, match('[!a-f]', 'j'))
|
|
eq(false, match('[!a-f]', 'jj'))
|
|
eq(true, match('[!a-z]', '`')) -- 'a' - 1
|
|
eq(true, match('[!a-z]', '{')) -- 'z' + 1
|
|
eq(false, match('[!a-zA-Z0-9]', 'a'))
|
|
eq(false, match('[!a-zA-Z0-9]', 'A'))
|
|
eq(false, match('[!a-zA-Z0-9]', '0'))
|
|
eq(true, match('[!a-zA-Z0-9]', '!'))
|
|
end)
|
|
|
|
it('should handle long patterns', function()
|
|
-- lpeg has a recursion limit of 200 by default, make sure the grammar does trigger it on
|
|
-- strings longer than that
|
|
local fill_200 = ('a'):rep(200)
|
|
eq(200, fill_200:len())
|
|
local long_lit = fill_200 .. 'a'
|
|
eq(false, match(long_lit, 'b'))
|
|
eq(true, match(long_lit, long_lit))
|
|
local long_pat = fill_200 .. 'a/**/*.c'
|
|
eq(true, match(long_pat, fill_200 .. 'a/b/c/d.c'))
|
|
end)
|
|
|
|
-- New test for unicode patterns from assets
|
|
it('should match unicode patterns', function()
|
|
eq(true, match('😎/¢£.{ts,tsx,js,jsx}', '😎/¢£.ts'))
|
|
eq(true, match('😎/¢£.{ts,tsx,js,jsx}', '😎/¢£.tsx'))
|
|
eq(true, match('😎/¢£.{ts,tsx,js,jsx}', '😎/¢£.js'))
|
|
eq(true, match('😎/¢£.{ts,tsx,js,jsx}', '😎/¢£.jsx'))
|
|
eq(false, match('😎/¢£.{ts,tsx,js,jsx}', '😎/¢£.jsxxxxxxxx'))
|
|
eq(true, match('*é*', 'café noir'))
|
|
eq(true, match('caf*noir', 'café noir'))
|
|
eq(true, match('caf*noir', 'cafeenoir'))
|
|
eq(true, match('F[ë£a]', 'Fë'))
|
|
eq(true, match('F[ë£a]', 'F£'))
|
|
eq(true, match('F[ë£a]', 'Fa'))
|
|
end)
|
|
|
|
it('should match complex patterns', function()
|
|
eq(false, match('**/*.{c,h}', ''))
|
|
eq(false, match('**/*.{c,h}', 'c'))
|
|
eq(false, match('**/*.{c,h}', 'file.m'))
|
|
eq(true, match('**/*.{c,h}', 'file.c'))
|
|
eq(true, match('**/*.{c,h}', 'file.h'))
|
|
eq(true, match('**/*.{c,h}', '/file.c'))
|
|
eq(true, match('**/*.{c,h}', 'dir/subdir/file.c'))
|
|
eq(true, match('**/*.{c,h}', 'dir/subdir/file.h'))
|
|
eq(true, match('**/*.{c,h}', '/dir/subdir/file.c'))
|
|
eq(true, match('**/*.{c,h}', 'C:/dir/subdir/file.c'))
|
|
eq(true, match('/dir/**/*.{c,h}', '/dir/file.c'))
|
|
eq(false, match('/dir/**/*.{c,h}', 'dir/file.c'))
|
|
eq(true, match('/dir/**/*.{c,h}', '/dir/subdir/subdir/file.c'))
|
|
|
|
eq(true, match('{[0-9],[a-z]}', '0'))
|
|
eq(true, match('{[0-9],[a-z]}', 'a'))
|
|
eq(false, match('{[0-9],[a-z]}', 'A'))
|
|
|
|
-- glob is from willRename filter in typescript-language-server
|
|
-- https://github.com/typescript-language-server/typescript-language-server/blob/b224b878652438bcdd639137a6b1d1a6630129e4/src/lsp-server.ts#L266
|
|
eq(true, match('**/*.{ts,js,jsx,tsx,mjs,mts,cjs,cts}', 'test.js'))
|
|
eq(true, match('**/*.{ts,js,jsx,tsx,mjs,mts,cjs,cts}', 'test.ts'))
|
|
eq(true, match('**/*.{ts,js,jsx,tsx,mjs,mts,cjs,cts}', 'test.mts'))
|
|
eq(true, match('**/*.{ts,js,jsx,tsx,mjs,mts,cjs,cts}', 'test.mjs'))
|
|
eq(true, match('**/*.{ts,js,jsx,tsx,mjs,mts,cjs,cts}', 'test.cjs'))
|
|
eq(true, match('**/*.{ts,js,jsx,tsx,mjs,mts,cjs,cts}', 'test.cts'))
|
|
eq(true, match('**/*.{ts,js,jsx,tsx,mjs,mts,cjs,cts}', 'test.jsx'))
|
|
eq(true, match('**/*.{ts,js,jsx,tsx,mjs,mts,cjs,cts}', 'test.tsx'))
|
|
end)
|
|
end)
|
|
end)
|