From e0486db3781dbcdd606e7e088bd3e6df32cb7fba Mon Sep 17 00:00:00 2001
From: eugenesvk <eugenesvk@users.noreply.github.com>
Date: Tue, 21 Jan 2025 13:53:12 +0700
Subject: [PATCH] Add explicit regex-set rules to hex unicode

document {1,3} ranges
---
 draft-marchan-kdl2.md                                    | 9 +++++++--
 .../input/unicode_escaped_too_long_lead0_fail.kdl        | 1 +
 2 files changed, 8 insertions(+), 2 deletions(-)
 create mode 100644 tests/test_cases/input/unicode_escaped_too_long_lead0_fail.kdl

diff --git a/draft-marchan-kdl2.md b/draft-marchan-kdl2.md
index 655e4c3..442cc9e 100644
--- a/draft-marchan-kdl2.md
+++ b/draft-marchan-kdl2.md
@@ -983,8 +983,13 @@ string-character :=
     [^\\"] - disallowed-literal-code-points
 ws-escape := '\\' (unicode-space | newline)+
 hex-digit := [0-9a-fA-F]
-hex-unicode := [\u{0}-\u{10FFFF}] - surrogate  // Unicode Scalar Value₁₆, leading 0s allowed as long as length ≤ 6
-surrogate := [\u{D800}-\u{DFFF}]
+hex-unicode := hex-digit{1, 6} - surrogate - above-max-scalar  // Unicode Scalar Value in hex₁₆, leading 0s allowed within length ≤ 6
+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-quotes :=
diff --git a/tests/test_cases/input/unicode_escaped_too_long_lead0_fail.kdl b/tests/test_cases/input/unicode_escaped_too_long_lead0_fail.kdl
new file mode 100644
index 0000000..7d66a9e
--- /dev/null
+++ b/tests/test_cases/input/unicode_escaped_too_long_lead0_fail.kdl
@@ -0,0 +1 @@
+no "Even with leading 0s Unicode Scalar Value escapes must ≤6: \u{0123456}"