From 9de233eca8a5af1c08f7a9030cbd1efccacf09e6 Mon Sep 17 00:00:00 2001
From: Vladimir Makaev <vmakaev@gmail.com>
Date: Thu, 19 Feb 2026 19:24:46 +0000
Subject: [PATCH] fix: accept unterminated block comments at EOF in scanner

The scanner previously rejected unterminated /* comments at EOF,
causing tree-sitter to parse the comment delimiters as operators
(multiplicative_expression, spread_expression). This matches JetBrains
PSI behavior which recognizes unclosed /* as a BLOCK_COMMENT token.

Fixes 4 cross-validation fixtures (BlockCommentAtBeginningOfFile 1-4),
improving match rate from 97/124 (78.2%) to 101/126 (80.2%).
---
 src/scanner.c                                    | 10 ++++++++++
 .../jetbrains/BlockCommentAtBeginningOfFile1.txt | 12 ++++++++++++
 .../jetbrains/BlockCommentAtBeginningOfFile2.txt | 13 +++++++++++++
 .../jetbrains/BlockCommentAtBeginningOfFile3.txt | 14 ++++++++++++++
 .../jetbrains/BlockCommentAtBeginningOfFile4.txt | 16 ++++++++++++++++
 tools/cross-validation/excluded.txt              |  8 +-------
 6 files changed, 66 insertions(+), 7 deletions(-)
 create mode 100644 test/corpus/jetbrains/BlockCommentAtBeginningOfFile1.txt
 create mode 100644 test/corpus/jetbrains/BlockCommentAtBeginningOfFile2.txt
 create mode 100644 test/corpus/jetbrains/BlockCommentAtBeginningOfFile3.txt
 create mode 100644 test/corpus/jetbrains/BlockCommentAtBeginningOfFile4.txt

diff --git a/src/scanner.c b/src/scanner.c
index caed63a2..03243643 100644
--- a/src/scanner.c
+++ b/src/scanner.c
@@ -224,6 +224,16 @@ static bool scan_multiline_comment(TSLexer *lexer) {
         }
         break;
       case '\0':
+        // Accept unterminated block comments at EOF rather than rejecting them.
+        // This matches JetBrains PSI behavior which recognizes unclosed /* as a
+        // BLOCK_COMMENT token (plus an error element). Without this, the scanner
+        // returns false and tree-sitter tries to parse the comment delimiters
+        // as operators/expressions.
+        if (lexer->eof(lexer)) {
+          lexer->result_symbol = MULTILINE_COMMENT;
+          lexer->mark_end(lexer);
+          return true;
+        }
         return false;
       default:
         advance(lexer);
diff --git a/test/corpus/jetbrains/BlockCommentAtBeginningOfFile1.txt b/test/corpus/jetbrains/BlockCommentAtBeginningOfFile1.txt
new file mode 100644
index 00000000..01b300f9
--- /dev/null
+++ b/test/corpus/jetbrains/BlockCommentAtBeginningOfFile1.txt
@@ -0,0 +1,12 @@
+==================
+BlockCommentAtBeginningOfFile1
+==================
+
+// COMPILATION_ERRORS
+
+/*
+---
+
+(source_file
+  (line_comment)
+  (multiline_comment))
diff --git a/test/corpus/jetbrains/BlockCommentAtBeginningOfFile2.txt b/test/corpus/jetbrains/BlockCommentAtBeginningOfFile2.txt
new file mode 100644
index 00000000..3e8c6a15
--- /dev/null
+++ b/test/corpus/jetbrains/BlockCommentAtBeginningOfFile2.txt
@@ -0,0 +1,13 @@
+==================
+BlockCommentAtBeginningOfFile2
+==================
+
+// COMPILATION_ERRORS
+
+/*
+/*
+---
+
+(source_file
+  (line_comment)
+  (multiline_comment))
diff --git a/test/corpus/jetbrains/BlockCommentAtBeginningOfFile3.txt b/test/corpus/jetbrains/BlockCommentAtBeginningOfFile3.txt
new file mode 100644
index 00000000..5f58f03b
--- /dev/null
+++ b/test/corpus/jetbrains/BlockCommentAtBeginningOfFile3.txt
@@ -0,0 +1,14 @@
+==================
+BlockCommentAtBeginningOfFile3
+==================
+
+// COMPILATION_ERRORS
+
+/*
+
+fooo
+---
+
+(source_file
+  (line_comment)
+  (multiline_comment))
diff --git a/test/corpus/jetbrains/BlockCommentAtBeginningOfFile4.txt b/test/corpus/jetbrains/BlockCommentAtBeginningOfFile4.txt
new file mode 100644
index 00000000..5bea7b59
--- /dev/null
+++ b/test/corpus/jetbrains/BlockCommentAtBeginningOfFile4.txt
@@ -0,0 +1,16 @@
+==================
+BlockCommentAtBeginningOfFile4
+==================
+
+// COMPILATION_ERRORS
+
+/*
+
+/*foo*/
+
+asdfas
+---
+
+(source_file
+  (line_comment)
+  (multiline_comment))
diff --git a/tools/cross-validation/excluded.txt b/tools/cross-validation/excluded.txt
index aa7d8b0a..6980b3af 100644
--- a/tools/cross-validation/excluded.txt
+++ b/tools/cross-validation/excluded.txt
@@ -20,13 +20,9 @@
 #   3. Run: npm test (to verify the new corpus test passes)
 
 # =============================================================================
-# MISMATCH: Grammar produces wrong AST structure (26 files)
+# MISMATCH: Grammar produces wrong AST structure (24 files)
 # =============================================================================
 
-# --- unterminated_block_comment (tree-sitter limitation) ---
-BlockCommentAtBeginningOfFile3
-BlockCommentAtBeginningOfFile4
-
 # --- duplicate_accessor (error recovery difference) ---
 DuplicateAccessor
 
@@ -88,8 +84,6 @@ AbsentInnerType
 AnnotatedIntersections
 AssertNotNull
 BackslashInString
-BlockCommentAtBeginningOfFile1
-BlockCommentAtBeginningOfFile2
 CallsInWhen
 CollectionLiterals
 CommentsBinding