address suggestion, add a test

Author: dschuff

emsymbolizer.py

@@ -28,7 +28,6 @@ class Error(BaseException):
 def get_codesec_offset(module):
   for sec in module.sections():
     if sec.type == webassembly.SecType.CODE:
-      print(sec)
       return sec.offset
   raise Error(f'No code section found in {module.filename}')
 
@@ -44,13 +43,12 @@ def symbolize_address_dwarf(module, address):
   vma_adjust = get_codesec_offset(module)
   cmd = [LLVM_SYMBOLIZER, '-e', module.filename, f'--adjust-vma={vma_adjust}',
          str(address)]
-  #print(cmd)
   check_call(cmd)
 
 def main(argv):
   wasm_file = argv[1]
-  print('Warning: the command-line and output format of this file are not'
-        'finalized yet')
+  print('Warning: the command-line and output format of this file are not '
+        'finalized yet', file=sys.stderr)
   module = webassembly.Module(wasm_file)
 
   if not has_debug_line_section(module):

tests/core/test_dwarf.c

@@ -2,14 +2,20 @@
 
 EM_JS(int, out_to_js, (int x), {})
 
-void foo() {
+void __attribute__((noinline)) foo() {
   out_to_js(0); // line 5
   out_to_js(1); // line 6
   out_to_js(2); // line 7
   // A silly possible recursion to avoid binaryen doing any inlining.
   if (out_to_js(3)) foo();
 }
 
+void __attribute__((always_inline)) bar() {
+  out_to_js(3);
+  __builtin_trap();
+}
+
 int main() {
   foo();
+  bar();
 }

tests/test_other.py

@@ -8219,6 +8219,27 @@ def test(infile, source_map_added_dir=''):
     ensure_dir('inner')
     test('inner/a.cpp', 'inner')
 
+  def test_emsymbolizer(self):
+    # Test DWARF output
+    self.run_process([EMCC, test_file('core/test_dwarf.c'),
+                      '-g', '-O1', '-o', 'test_dwarf.js'])
+    # Use hard-coded addresses. This is potentially brittle, but LLVM's
+    # O1 output is pretty minimal so hopefully it won't break too much?
+    # Another option would be to disassemble the binary to look for certain
+    # instructions or code sequences.
+    def get_addr(address):
+      return self.run_process(
+          [PYTHON, path_from_root('emsymbolizer.py'), 'test_dwarf.wasm', address],
+          stdout=PIPE).stdout
+    # Check a location in foo(), not inlined.
+    self.assertIn('test_dwarf.c:6:3', get_addr('0x101'))
+    # Check that both bar (inlined) and main (inlinee) are in the output,
+    # as described by the DWARF.
+    # TODO: consider also checking the function names once the output format
+    # stabilizes more
+    self.assertRegex(get_addr('0x124').replace('\n', ''),
+                     'test_dwarf.c:15:3.*test_dwarf.c:20:3')
+
   def test_separate_dwarf(self):
     self.run_process([EMCC, test_file('hello_world.c'), '-g'])
     self.assertExists('a.out.wasm')

tools/webassembly.py

@@ -125,6 +125,7 @@ class Module:
   """Extremely minimal wasm module reader.  Currently only used
   for parsing the dylink section."""
   def __init__(self, filename):
+    self.buf = None # Set this before FS calls below in case they throw.
     self.filename = filename
     self.size = os.path.getsize(filename)
     self.buf = open(filename, 'rb')
@@ -134,7 +135,7 @@ def __init__(self, filename):
       raise InvalidWasmError(f'{filename} is not a valid wasm file')
 
   def __del__(self):
-    if hasattr(self, 'buf'):
+    if self.buf:
       self.buf.close()
 
   def readAt(self, offset, count):