Update symbolize_trace to work on macOS.

tracing/bin/symbolize_trace

Index: tracing/bin/symbolize_trace
diff --git a/tracing/bin/symbolize_trace b/tracing/bin/symbolize_trace
index ecfbb673bf0c46bbbcb4dce0f414a68388f237fe..105b9e943ee34a7fa5dc08c7d3856941331bad33 100755
--- a/tracing/bin/symbolize_trace
+++ b/tracing/bin/symbolize_trace
@@ -55,7 +55,8 @@ def FindInSystemPath(binary_name):
 def IsSymbolizableFile(file_path):
   result = subprocess.check_output(['file', '-0', file_path])
   type_string = result[result.find('\0') + 1:]
-  return bool(re.match(r'\: (ELF|Mach-O) (32|64)-bit\b', type_string))
+  return bool(re.match(r'.*(ELF|Mach-O) (32|64)-bit\b.*',
+              type_string, re.DOTALL))
 
 
 class ProcessMemoryMaps(object):
@@ -271,7 +272,7 @@ def ResolveSymbolizableFiles(processes):
   return symfile_by_path.values()
 
 
-def SymbolizeFiles(symfiles, addr2line_path):
+def SymbolizeFiles(symfiles, symbolizer_path):
   """Symbolizes each file in the given list of SymbolizableFiles
      and updates stack frames with symbolization results."""
   print 'Symbolizing...'
@@ -301,37 +302,54 @@ def SymbolizeFiles(symfiles, addr2line_path):
           frame.name = unsymbolized_name
       continue
 
-    def _SymbolizerCallback(sym_info, frames):
-      # Unwind inline chain to the top.
-      while sym_info.inlined_by:
-        sym_info = sym_info.inlined_by
-
-      symbolized_name = sym_info.name if sym_info.name else unsymbolized_name
-      for frame in frames:
-        frame.name = symbolized_name
-
-    symbolizer = elf_symbolizer.ELFSymbolizer(symfile.symbolizable_path,
-                                              addr2line_path,
-                                              _SymbolizerCallback,
-                                              inlines=True)
-
     _SubPrintf('Symbolizing {} PCs from {}...',
                len(symfile.frames_by_address),
                symfile.path)
 
-    for address, frames in symfile.frames_by_address.iteritems():
-      # SymbolizeAsync() asserts that the type of address is int. We operate
-      # on longs (since they are raw pointers possibly from 64-bit processes).
-      # It's OK to cast here because we're passing relative PC, which should
-      # always fit into int.
-      symbolizer.SymbolizeAsync(int(address), frames)
-
-    symbolizer.Join()
+    if sys.platform == 'darwin':

[DmitrySkiba, 2017/01/10 21:28:09]

We have this check in two places - first when we decide what symbolizer_path
should be, the other is here. If looks like symbolizer_path should instead be
'symblizer' object with a single method.

[erikchen, 2017/02/04 02:34:56]

Introducing a class to avoid an extra conditional seems dubious to me, but
whatever. Done.

+      SymbolizeMac(symfile, symbolizer_path)
+    else:
+      SymbolizeLinuxAndAndroid(sym_file, symbolizer_path)
     symbolized = True
 
   return symbolized
 
 
+def SymbolizeLinuxAndAndroid(sym_file, symbolizer_path):
+  def _SymbolizerCallback(sym_info, frames):
+    # Unwind inline chain to the top.
+    while sym_info.inlined_by:
+      sym_info = sym_info.inlined_by
+
+    symbolized_name = sym_info.name if sym_info.name else unsymbolized_name
+    for frame in frames:
+      frame.name = symbolized_name
+
+  symbolizer = elf_symbolizer.ELFSymbolizer(symfile.symbolizable_path,
+                                            symbolizer_path,
+                                            _SymbolizerCallback,
+                                            inlines=True)
+
+  for address, frames in symfile.frames_by_address.iteritems():
+    # SymbolizeAsync() asserts that the type of address is int. We operate
+    # on longs (since they are raw pointers possibly from 64-bit processes).
+    # It's OK to cast here because we're passing relative PC, which should
+    # always fit into int.
+    symbolizer.SymbolizeAsync(int(address), frames)
+
+  symbolizer.Join()
+
+
+def SymbolizeMac(symfile, symbolizer_path):
+  cmd = [symbolizer_path, '-arch', 'x86_64', '-l',
+         '0x0', '-o' , symfile.symbolizable_path]
+  cmd.extend([hex(int(x)) for x in symfile.frames_by_address.keys()])

[DmitrySkiba, 2017/01/10 21:28:09]

What is the max command line length on macOS? This can easily append thousands
of addresses.

[erikchen, 2017/02/04 02:34:56]

By default, the max length is 260k characters. I've added logic to not exceed
that limit.

+  output_array = subprocess.check_output(cmd).split('\n')
+  for i in range(len(symfile.frames_by_address.keys())):
+    for frame in symfile.frames_by_address.values()[i]:
+      frame.name = output_array[i]
+
+
 def HaveFilesFromAndroid(symfiles):
   return any(ANDROID_PATH_MATCHER.match(f.path) for f in symfiles)
 
@@ -372,9 +390,13 @@ def main():
     else:
       return open(trace_file_path, mode + 't')
 
-  addr2line_path = FindInSystemPath('addr2line')
-  if addr2line_path is None:
-    sys.exit("Can't symbolize - no addr2line in PATH.")
+  if sys.platform == 'darwin':
+    symbolizer = 'atos'
+  else:
+    symbolizer = 'addr2line'
+  symbolizer_path = FindInSystemPath(symbolizer)
+  if symbolizer_path is None:
+    sys.exit("Can't symbolize - no %s in PATH." % symbolizer)
 
   print 'Reading trace file...'
   with _OpenTraceFile('r') as trace_file:
@@ -392,7 +414,7 @@ def main():
                    'symbolize it.')
     RemapAndroidFiles(symfiles, os.path.abspath(options.output_directory))
 
-  if SymbolizeFiles(symfiles, addr2line_path):
+  if SymbolizeFiles(symfiles, symbolizer_path):
     if options.backup:
       backup_file_path = trace_file_path + BACKUP_FILE_TAG
       print 'Backing up trace file to {}...'.format(backup_file_path)