grammar: allow digit-leading segment names

Segment ids such as `2~1` and `1~12` appear in real samples (most
visibly /Free Culture/'s `2~1 1. More Formalities`). The previous
segment_name regex required a leading [a-zA-Z_!]; relax to also
accept digits at the first position. The internal-hyphen and
no-trailing-hyphen constraints (the latter to avoid colliding with
the suppress marker) are unchanged.

(assisted by Claude-Code)

3 files changed, 6 insertions, 3 deletions

diff --git a/grammar.js b/grammar.js
index 34582fa..a49da94 100644
--- a/grammar.js
+++ b/grammar.js
@@ -124,8 +124,10 @@ module.exports = grammar({
     ),
 
     segment_marker: $ => token(prec(20, choice('1~', '2~', '3~'))),
-    // Allow internal hyphens but not trailing hyphen (which is the suppress marker)
-    segment_name: $ => /[a-zA-Z_!][a-zA-Z0-9_]*(-[a-zA-Z0-9_]+)*/,
+    // Allow internal hyphens but not trailing hyphen (which is the suppress
+    // marker). Names may begin with a digit to support numeric section ids
+    // such as `2~1 ...` seen in real-world markup (e.g. Free Culture).
+    segment_name: $ => /[a-zA-Z0-9_!][a-zA-Z0-9_]*(-[a-zA-Z0-9_]+)*/,
 
     // =================================================================
     // Code blocks (raw content - no inline parsing)
diff --git a/src/grammar.json b/src/grammar.json
index e8ce79a..3974246 100644
--- a/src/grammar.json
+++ b/src/grammar.json
@@ -425,7 +425,7 @@
     },
     "segment_name": {
       "type": "PATTERN",
-      "value": "[a-zA-Z_!][a-zA-Z0-9_]*(-[a-zA-Z0-9_]+)*"
+      "value": "[a-zA-Z0-9_!][a-zA-Z0-9_]*(-[a-zA-Z0-9_]+)*"
     },
     "code_block_curly": {
       "type": "PREC",
diff --git a/src/parser.c b/src/parser.c
index e194b48..12d39c9 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -2093,6 +2093,7 @@ static bool ts_lex(TSLexer *lexer, TSStateId state) {
       if (lookahead == '-') ADVANCE(214);
       if (lookahead == '}') ADVANCE(499);
       if (lookahead == '!' ||
+          ('0' <= lookahead && lookahead <= '9') ||
           ('A' <= lookahead && lookahead <= 'Z') ||
           lookahead == '_' ||
           ('a' <= lookahead && lookahead <= 'z')) ADVANCE(217);