From 18101b8ddcbf555530302aefa4fd3053d834cc9a Mon Sep 17 00:00:00 2001
From: Mihaela Mihaljevic <mihaelamj@me.com>
Date: Wed, 24 Jun 2026 18:11:58 +0200
Subject: [PATCH] feat(parsing): accept full YAML 1.2 anchor and alias names

An anchor or alias name is ns-anchor-char+ (any printable character that
is not whitespace, a line break, the BOM, or a flow indicator), so Unicode
and punctuation names are valid. libyaml restricts the name to
alphanumerics and rejects them.

Canonical event conformance: 271 -> 275 of 308 (2SXE, 8XYN, W5VH, Y2GN).
379 tests pass.
---
 Sources/Parsing/LibYAML.Scanner.Anchor.swift | 26 +++++++++++++-------
 Tests/CanonicalEventConformanceTests.swift   |  8 +++---
 2 files changed, 21 insertions(+), 13 deletions(-)

diff --git a/Sources/Parsing/LibYAML.Scanner.Anchor.swift b/Sources/Parsing/LibYAML.Scanner.Anchor.swift
index d8d2efa..1df8ba0 100644
--- a/Sources/Parsing/LibYAML.Scanner.Anchor.swift
+++ b/Sources/Parsing/LibYAML.Scanner.Anchor.swift
@@ -1,20 +1,21 @@
 extension PureYAML.Parsing.LibYAML.Scanner {
     private typealias Classify = PureYAML.Parsing.LibYAML.CharacterClass
 
-    /// Port of `yaml_parser_scan_anchor`. Scans an anchor (`&name`) or alias
-    /// (`*name`): the name is a run of `IS_ALPHA` characters and must be non-empty
-    /// and followed by a blank, the end of input, or one of the indicators that may
-    /// terminate it.
+    /// Port of `yaml_parser_scan_anchor`, widened to YAML 1.2: an anchor (`&name`)
+    /// or alias (`*name`) name is `ns-anchor-char+`, i.e. any printable character
+    /// that is not whitespace, a line break, or a flow indicator (`,[]{}`). libyaml
+    /// restricts the name to alphanumerics, which rejects Unicode and punctuation
+    /// anchor names that YAML 1.2 allows.
     mutating func scanAnchor(isAnchor: Bool) throws -> PureYAML.Parsing.LibYAML.Token {
         let startMark = reader.mark
         reader.skip()
         var name = ""
-        while let character = reader.peek(), Classify.isAlpha(character) {
+        while let character = reader.peek(), isAnchorCharacter(character) {
             name.unicodeScalars.append(character)
             reader.skip()
         }
         let endMark = reader.mark
-        guard !name.isEmpty, Classify.isBlankZ(reader.peek()) || isAnchorTerminator(reader.peek()) else {
+        guard !name.isEmpty else {
             throw PureYAML.Parsing.LibYAML.ScannerError(
                 context: isAnchor ? "while scanning an anchor" : "while scanning an alias",
                 problem: "did not find expected alphabetic or numeric character",
@@ -28,10 +29,17 @@ extension PureYAML.Parsing.LibYAML.Scanner {
         )
     }
 
-    private func isAnchorTerminator(_ scalar: Unicode.Scalar?) -> Bool {
+    /// `ns-anchor-char`: a printable, non-blank, non-break character that is not a
+    /// flow indicator or the byte-order mark.
+    private func isAnchorCharacter(_ scalar: Unicode.Scalar) -> Bool {
+        guard Classify.isPrintable(scalar), !Classify.isBlankZ(scalar), scalar != "\u{FEFF}" else {
+            return false
+        }
         switch scalar {
-        case "?", ":", ",", "]", "}", "%", "@", "`": true
-        default: false
+        case ",", "[", "]", "{", "}":
+            return false
+        default:
+            return true
         }
     }
 }
diff --git a/Tests/CanonicalEventConformanceTests.swift b/Tests/CanonicalEventConformanceTests.swift
index f919823..af1b12c 100644
--- a/Tests/CanonicalEventConformanceTests.swift
+++ b/Tests/CanonicalEventConformanceTests.swift
@@ -21,14 +21,14 @@ struct CanonicalEventConformanceTests {
         // itself handles.
         //
         // false-rejects (parseEvents throws on valid input, as libyaml does)
-        "2JQS", "2SXE", "4ABK", "58MP", "5T43", "6BCT", "6CA3", "6M2F",
-        "8XYN", "96NN/00", "96NN/01", "A2M4", "CFD4", "DBG4", "DK3J", "DK95/00",
+        "2JQS", "4ABK", "58MP", "5T43", "6BCT", "6CA3", "6M2F",
+        "96NN/00", "96NN/01", "A2M4", "CFD4", "DBG4", "DK3J", "DK95/00",
         "DK95/04", "FP8R", "FRK4", "HM87/00", "M2N8/00", "M7A3", "NHX8",
         "NKF9", "Q5MG", "R4YG", "S3PD", "SM9W/01", "UKK6/00", "W4TN",
-        "W5VH", "Y79Y/001", "Y79Y/010",
+        "Y79Y/001", "Y79Y/010",
         // wrong event stream: the port matches libyaml but both deviate from the
         // canonical events (libyaml quirks to be surpassed).
-        "652Z", "HM87/01", "JEF9/02", "Y2GN",
+        "652Z", "HM87/01", "JEF9/02",
     ]
 
     @Test("Every valid case emits canonical events, except the recorded gaps")