From 4bd86120d41e3b01433004bf761beccb7f3a0167 Mon Sep 17 00:00:00 2001 From: Jon Huhn Date: Mon, 10 Jun 2024 06:23:03 -0500 Subject: [PATCH] fix(glob): handle overlapping `{}` condition elements #29236 This change fixes an issue where glob patterns like `{a,ab}` would not match `ab` because the first option `a` matches, then the end of the string is expected but `b` is found, and LPeg does not backtrack to try the next option `ab` which would match. The fix here is to also append the rest of the pattern to the generated LPeg pattern for each option. This changes a glob `{a,ab}` from being parsed as ("a" or "ab") "end of string" to ("a" "end of string" or "ab" "end of string") Here, matching against `ab` would try the first option, fail to match, then proceed to the next option, and match. The sacrifice this change makes is dropping support for nested `{}` conditions, which VSCode doesn't seem to support or test AFAICT. Fixes #28931 Co-authored-by: Sergey Slipchenko --- runtime/lua/vim/glob.lua | 11 ++++++----- test/functional/lua/glob_spec.lua | 13 ++++++++++++- 2 files changed, 18 insertions(+), 6 deletions(-) diff --git a/runtime/lua/vim/glob.lua b/runtime/lua/vim/glob.lua index ad4a915a94..6de2bc3e94 100644 --- a/runtime/lua/vim/glob.lua +++ b/runtime/lua/vim/glob.lua @@ -29,8 +29,10 @@ function M.to_lpeg(pattern) return patt end - local function add(acc, a) - return acc + a + local function condlist(conds, after) + return vim.iter(conds):fold(P(false), function(acc, cond) + return acc + cond * after + end) end local function mul(acc, m) @@ -63,15 +65,14 @@ function M.to_lpeg(pattern) * C(P('!') ^ -1) * Ct(Ct(C(P(1)) * P('-') * C(P(1) - P(']'))) ^ 1 * P(']')) / class, - CondList = P('{') * Cf(V('Cond') * (P(',') * V('Cond')) ^ 0, add) * P('}'), + CondList = P('{') * Ct(V('Cond') * (P(',') * V('Cond')) ^ 0) * P('}') * V('Pattern') / condlist, -- TODO: '*' inside a {} condition is interpreted literally but should probably have the same -- wildcard semantics it usually has. -- Fixing this is non-trivial because '*' should match non-greedily up to "the rest of the -- pattern" which in all other cases is the entire succeeding part of the pattern, but at the end of a {} -- condition means "everything after the {}" where several other options separated by ',' may -- exist in between that should not be matched by '*'. - Cond = Cf((V('Ques') + V('Class') + V('CondList') + (V('Literal') - S(',}'))) ^ 1, mul) - + Cc(P(0)), + Cond = Cf((V('Ques') + V('Class') + V('Literal') - S(',}')) ^ 1, mul) + Cc(P(0)), Literal = P(1) / P, End = P(-1) * Cc(P(-1)), }) diff --git a/test/functional/lua/glob_spec.lua b/test/functional/lua/glob_spec.lua index 56cd4c9bb5..b3e1b79ee7 100644 --- a/test/functional/lua/glob_spec.lua +++ b/test/functional/lua/glob_spec.lua @@ -161,7 +161,7 @@ describe('glob', function() 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(false, match('{a,{b,c}}', 'c')) -- {} cannot nest end) it('should match [] groups', function() @@ -223,6 +223,17 @@ describe('glob', function() 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)