Show detailed difference on unexpected difference.

tools/determinism/compare_build_artifacts.py

Index: tools/determinism/compare_build_artifacts.py
diff --git a/tools/determinism/compare_build_artifacts.py b/tools/determinism/compare_build_artifacts.py
index 57bb236e8541f0335cd3c06733820837e0998e78..87e55731906ff6f910d5c32e3dfbdc06243b6731 100755
--- a/tools/determinism/compare_build_artifacts.py
+++ b/tools/determinism/compare_build_artifacts.py
@@ -9,6 +9,8 @@ import difflib
 import json
 import optparse
 import os
+import re
+import subprocess
 import struct
 import sys
 import time
@@ -495,6 +497,46 @@ def compare_files(first_filepath, second_filepath):
   return diff_binary(first_filepath, second_filepath, file_len)
 
 
+def get_deps(build_dir, target):
+  """Returns list of object files needed to build target."""
+  NODE_PATTERN = re.compile(r'label="([a-zA-Z0-9_\\/.-]+)"')
+  CHECK_EXTS = ('.o', '.obj')
+  try:
+    out = subprocess.check_output(['ninja', '-C', build_dir,

[M-A Ruel, 2016/08/24 18:47:27]

There's a problem as the directory was renamed, so calling ninja after the
directory was renamed will likely not result in the expected outcome, as the
ninja files may have absolute paths. So it is important to rename the directory
:/ before calling ninja.

[Yoshisato Yanagisawa, 2016/08/25 08:47:29]

I have never seen absolute object file path names but I am not confident.  Let
me rename to possibly original directory, and warn and skip if absolute object
file path is used.

[M-A Ruel, 2016/08/25 15:46:26]

zforman@ worked on making this work on linux but this is likely not the case on
OSX and Windows, probably worth double checking on at least one of the other
platform eventually.

[Yoshisato Yanagisawa, 2016/08/29 05:44:49]

I checked the code seems to work on Win.

+                                   '-t', 'graph', target])
+  except subprocess.CalledProcessError as e:
+    print >> sys.stderr, 'error to get graph for %s: %s' % (target, e)
+    return []
+  files = []
+  for line in out.splitlines():
+    matched = NODE_PATTERN.search(line)
+    if matched:
+      path = matched.group(1)
+      if not os.path.splitext(path)[1] in CHECK_EXTS:
+        continue
+      files.append(path)
+  return files
+
+
+def compare_deps(first_dir, second_dir, targets):
+  """Print difference of dependent files."""
+  for target in targets:
+    print 'Checking %s difference:' % target
+    first_deps = get_deps(first_dir, target)
+    second_deps = get_deps(second_dir, target)
+    deps = set(first_deps).union(set(second_deps))

[M-A Ruel, 2016/08/24 18:47:27]

the difference should be empty ?

[Yoshisato Yanagisawa, 2016/08/25 08:47:29]

I am not confident.  However, I will simplify the code expecting no difference
between first_deps and second_deps.

[M-A Ruel, 2016/08/25 15:46:26]

I guess my question was more to print out the differences to be able to monitor
when this happens.

[Yoshisato Yanagisawa, 2016/08/29 05:44:49]

I think current code still help us to find this kind of difference, not clearly
mentions which one is larger, though.
Let me update the code when we actually see this case.

+    for d in deps:
+      first_file = os.path.join(first_dir, d)
+      second_file = os.path.join(second_dir, d)
+      if not os.path.exists(first_file):
+        print '%s: not found' % first_file
+        continue
+      if not os.path.exists(second_file):
+        print '%s: not found' % second_file
+        continue
+      compare_files(first_file, second_file)
+
+
 def compare_build_artifacts(first_dir, second_dir, target_platform,
                             recursive=False):
   """Compares the artifacts from two distinct builds."""
@@ -561,6 +603,11 @@ def compare_build_artifacts(first_dir, second_dir, target_platform,
     for u in unexpected_equals:
       print('  %s' % u)
 
+  if unexpected_diffs:
+    diffs_to_investigate = set(unexpected_diffs).difference(
+        set(missing_files))
+    compare_deps(first_dir, second_dir, diffs_to_investigate)
+
   return int(bool(unexpected_diffs))
 
 
@@ -575,7 +622,7 @@ def main():
   target = {
       'darwin': 'mac', 'linux2': 'linux', 'win32': 'win'
   }.get(sys.platform, sys.platform)
-  parser.add_option('-t', '--target-platform', help='The target platform.'
+  parser.add_option('-t', '--target-platform', help='The target platform.',
                     default=target, choices=('android', 'mac', 'linux', 'win'))
   options, _ = parser.parse_args()