Skip comments in keyword scan

Author: nicosuave

test/sql/measures.test

@@ -59,6 +59,28 @@ from
 2023	EU	225.0
 2023	US	225.0
 
+# FROM inside a line comment should be ignored
+query IIR rowsort
+SEMANTIC SELECT year, region, AGGREGATE(revenue) AT (ALL region) AS year_total
+-- from sales_v
+FROM sales_v;
+----
+2022	EU	150.0
+2022	US	150.0
+2023	EU	225.0
+2023	US	225.0
+
+# FROM inside a block comment should be ignored
+query IIR rowsort
+SEMANTIC SELECT year, region, AGGREGATE(revenue) AT (ALL region) AS year_total
+/* from sales_v */
+FROM sales_v;
+----
+2022	EU	150.0
+2022	US	150.0
+2023	EU	225.0
+2023	US	225.0
+
 # =============================================================================
 # Test: AT modifiers without SEMANTIC prefix
 # =============================================================================

yardstick-rs/src/sql/measures.rs

@@ -697,11 +697,31 @@ fn find_top_level_keyword(sql: &str, keyword: &str, start: usize) -> Option<usiz
     let mut in_double = false;
     let mut in_backtick = false;
     let mut in_bracket = false;
+    let mut in_line_comment = false;
+    let mut in_block_comment = false;
 
     let mut i = start;
     while i < bytes.len() {
         let c = bytes[i] as char;
 
+        if in_line_comment {
+            if c == '\n' || c == '\r' {
+                in_line_comment = false;
+            }
+            i += 1;
+            continue;
+        }
+
+        if in_block_comment {
+            if c == '*' && i + 1 < bytes.len() && bytes[i + 1] as char == '/' {
+                in_block_comment = false;
+                i += 2;
+                continue;
+            }
+            i += 1;
+            continue;
+        }
+
         if in_single {
             if c == '\'' {
                 if i + 1 < bytes.len() && bytes[i + 1] as char == '\'' {
@@ -738,6 +758,18 @@ fn find_top_level_keyword(sql: &str, keyword: &str, start: usize) -> Option<usiz
             continue;
         }
 
+        if c == '-' && i + 1 < bytes.len() && bytes[i + 1] as char == '-' {
+            in_line_comment = true;
+            i += 2;
+            continue;
+        }
+
+        if c == '/' && i + 1 < bytes.len() && bytes[i + 1] as char == '*' {
+            in_block_comment = true;
+            i += 2;
+            continue;
+        }
+
         match c {
             '\'' => {
                 in_single = true;