berkus
/
kdl
mirror of https://github.com/kdl-org/kdl.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add explicit regex-set rules to hex unicode 

document {1,3} ranges
This commit is contained in:
eugenesvk 2025-01-21 13:53:12 +07:00
parent a84dc3b44f
commit e0486db378
2 changed files with 8 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
draft-marchan-kdl2.md
View File

@ -983,8 +983,13 @@ string-character :=
[^\\"] - disallowed-literal-code-points [^\\"] - disallowed-literal-code-points
ws-escape := '\\' (unicode-space | newline)+ ws-escape := '\\' (unicode-space | newline)+
hex-digit := [0-9a-fA-F] hex-digit := [0-9a-fA-F]
hex-unicode := [\u{0}-\u{10FFFF}] - surrogate // Unicode Scalar Value₁₆, leading 0s allowed as long as length ≤ 6 hex-unicode := hex-digit{1, 6} - surrogate - above-max-scalar // Unicode Scalar Value in hex₁₆, leading 0s allowed within length ≤ 6
surrogate := [\u{D800}-\u{DFFF}] surrogate := [0]{0,2}[dD][8-9a-fA-F]hex-digit{2}
// U+D800-DFFF: D 8 00
// D F FF
above-max-scalar = [2-9a-fA-F]hex-digit{5} | [1][1-9a-fA-F]hex-digit{4}
// >U+10FFFF: >1 _____ 1 >0 ____
raw-string := '#' raw-string-quotes '#' | '#' raw-string '#' raw-string := '#' raw-string-quotes '#' | '#' raw-string '#'
raw-string-quotes := raw-string-quotes :=

1
tests/test_cases/input/unicode_escaped_too_long_lead0_fail.kdl Normal file
View File

@ -0,0 +1 @@
no "Even with leading 0s Unicode Scalar Value escapes must ≤6: \u{0123456}"