Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix language_js regex constant detection #1581

Merged
merged 4 commits into from
Nov 29, 2023
Merged

Fix language_js regex constant detection #1581

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ce72cd0
Fix `language_js` regex constant detection
Guldoman Aug 13, 2023
fb0c3dc
Simplify regex constant detection in `language_js`
Guldoman Nov 8, 2023
c68e26f
Add more possessive quantifiers in `language_js` regex constant detec…
Guldoman Nov 8, 2023
fb3ecca
Allow `.` after regex constant in `language_js`
Guldoman Nov 29, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
74 changes: 62 additions & 12 deletions data/plugins/language_js.lua
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,24 +1,74 @@
-- mod-version:3
local syntax = require "core.syntax"

-- Regex pattern explanation:
-- This will match / and will look ahead for something that looks like a regex.
--
-- (?!/) Don't match empty regexes.
--
-- (?>...) this is using an atomic group to minimize backtracking, as that'd
-- cause "Catastrophic Backtracking" in some cases.
--
-- [^\\[\/]++ will match anything that's isn't an escape, a start of character
-- class or an end of pattern, without backtracking (the second +).
--
-- \\. will match anything that's escaped.
--
-- \[(?:[^\\\]++]|\\.)*+\] will match character classes.
--
-- /[gmiyuvsd]*\s*[\n,;\)\]\}\.]) will match the end of pattern delimiter, optionally
-- followed by pattern options, and anything that can
-- be after a pattern.
--
-- Demo with some unit tests (click on the Unit Tests entry): https://regex101.com/r/R0w8Qw/1
-- Note that it has a couple of changes to make it work on that platform.
local regex_pattern = {
[=[/(?=(?!/)(?:(?>[^\\[\/]++|\\.|\[(?:[^\\\]]++|\\.)*+\])*+)++/[gmiyuvsd]*\s*[\n,;\)\]\}\.])()]=],
"/()[gmiyuvsd]*", "\\"
}

-- For the moment let's not actually differentiate the insides of the regex,
-- as this will need new token types...
local inner_regex_syntax = {
patterns = {
{ pattern = "%(()%?[:!=><]", type = { "string", "string" } },
{ pattern = "[.?+*%(%)|]", type = "string" },
{ pattern = "{%d*,?%d*}", type = "string" },
{ regex = { [=[\[()\^?]=], [=[(?:\]|(?=\n))()]=], "\\" },
type = { "string", "string" },
syntax = { -- Inside character class
patterns = {
{ pattern = "\\\\", type = "string" },
{ pattern = "\\%]", type = "string" },
{ pattern = "[^%]\n]", type = "string" }
},
symbols = {}
}
},
{ regex = "\\/", type = "string" },
{ regex = "[^/\n]", type = "string" },
},
symbols = {}
}

syntax.add {
name = "JavaScript",
files = { "%.js$", "%.json$", "%.cson$", "%.mjs$", "%.cjs$" },
comment = "//",
block_comment = { "/*", "*/" },
patterns = {
{ pattern = "//.*", type = "comment" },
{ pattern = { "/%*", "%*/" }, type = "comment" },
{ pattern = { '/[^= ]', '/', '\\' },type = "string" },
{ pattern = { '"', '"', '\\' }, type = "string" },
{ pattern = { "'", "'", '\\' }, type = "string" },
{ pattern = { "`", "`", '\\' }, type = "string" },
{ pattern = "0x[%da-fA-F_]+n?", type = "number" },
{ pattern = "-?%d+[%d%.eE_n]*", type = "number" },
{ pattern = "-?%.?%d+", type = "number" },
{ pattern = "[%+%-=/%*%^%%<>!~|&]", type = "operator" },
{ pattern = "[%a_][%w_]*%f[(]", type = "function" },
{ pattern = "[%a_][%w_]*", type = "symbol" },
{ pattern = "//.*", type = "comment" },
{ pattern = { "/%*", "%*/" }, type = "comment" },
{ regex = regex_pattern, syntax = inner_regex_syntax, type = {"string", "string"} },
{ pattern = { '"', '"', '\\' }, type = "string" },
{ pattern = { "'", "'", '\\' }, type = "string" },
{ pattern = { "`", "`", '\\' }, type = "string" },
{ pattern = "0x[%da-fA-F_]+n?()%s*()/?", type = {"number", "normal", "operator"} },
{ pattern = "-?%d+[%d%.eE_n]*()%s*()/?", type = {"number", "normal", "operator"} },
{ pattern = "-?%.?%d+()%s*()/?", type = {"number", "normal", "operator"} },
{ pattern = "[%+%-=/%*%^%%<>!~|&]", type = "operator" },
{ pattern = "[%a_][%w_]*%f[(]", type = "function" },
{ pattern = "[%a_][%w_]*()%s*()/?", type = {"symbol", "normal", "operator"} },
},
symbols = {
["async"] = "keyword",
Expand Down
Loading