fix(bench): broaden class-modifier regex and document call-type codes in compare-javacg

Author: carlos-alm

scripts/compare-javacg.mjs

@@ -65,14 +65,31 @@ function findJavacgJar() {
 /**
  * Scan .java source files to build SimpleClassName → filename.java map.
  * Used to resolve file fields in the edge key format "name@file".
+ *
+ * Maps the first top-level type per file — inner classes are not indexed.
+ * Handles common modifiers (public, abstract, final, sealed, non-sealed, strictfp)
+ * and type keywords (class, interface, enum, record).
  */
 function buildClassFileMap(fixtureDir) {
   const map = new Map();
-  for (const filename of fs.readdirSync(fixtureDir)) {
-    if (!filename.endsWith('.java')) continue;
+  const javaFiles = fs.readdirSync(fixtureDir).filter((f) => f.endsWith('.java'));
+  for (const filename of javaFiles) {
     const src = fs.readFileSync(path.join(fixtureDir, filename), 'utf8');
-    const m = src.match(/(?:public\s+)?(?:abstract\s+)?(?:class|interface)\s+(\w+)/);
-    if (m) map.set(m[1], filename);
+    // Match any combination of access/modifier keywords before the type keyword
+    const m = src.match(
+      /(?:(?:public|protected|private|abstract|final|sealed|non-sealed|strictfp)\s+)*(?:class|interface|enum|record)\s+(\w+)/,
+    );
+    if (m) {
+      map.set(m[1], filename);
+    } else {
+      console.warn(`[warn] buildClassFileMap: no type declaration found in ${filename} — edges involving this file will be filtered out`);
+    }
+  }
+  // Validate: every .java file should map to exactly one class name
+  if (map.size !== javaFiles.length) {
+    console.warn(
+      `[warn] buildClassFileMap: ${javaFiles.length} .java files but only ${map.size} class names resolved — precision/recall may be skewed`,
+    );
   }
   return map;
 }
@@ -153,7 +170,8 @@ function runJavacg(javacgJar, fixtureDir) {
  */
 function parseJavacgOutput(output, classFileMap) {
   // M: caller (T) callee — the space between caller and (T) may vary
-  const lineRe = /^M:(\S+)\s+\(([CSOIDE])\)(\S+)$/;
+  // T values: C=virtual, S=static, O=special (constructors/super), I=interface, D=dynamic (invokedynamic)
+  const lineRe = /^M:(\S+)\s+\(([CSOID])\)(\S+)$/;
   const edges = new Set();
 
   for (const rawLine of output.split('\n')) {