[Findit] findit algorithms and a cluster-fuzz implementation.

tools/findit/findit_for_clusterfuzz.py

Index: tools/findit/findit_for_clusterfuzz.py
diff --git a/tools/findit/findit_for_clusterfuzz.py b/tools/findit/findit_for_clusterfuzz.py
new file mode 100644
index 0000000000000000000000000000000000000000..033d1b55c9c2c10e4874b588ace160531354f60e
--- /dev/null
+++ b/tools/findit/findit_for_clusterfuzz.py
@@ -0,0 +1,140 @@
+# Copyright (c) 2014 The Chromium Authors. All rights reserved.
+# Use of this source code is governed by a BSD-style license that can be
+# found in the LICENSE file.
+
+import chromium_deps
+import crash_utils
+import findit_for_crash as findit
+import stacktrace
+
+
+def SplitStacktrace(stacktrace_string):
+  """Preprocesses stacktrace string into two parts, release and debug.
+
+  Args:
+    stacktrace_string: A string representation of stacktrace,
+                       in clusterfuzz format.
+
+  Returns:
+    A tuple of list of strings, release build stacktrace and
+    debug build stacktrace.
+  """
+  # Make sure we only parse release/debug build stacktrace, and ignore
+  # unsymbolised stacktrace.
+  in_release_or_debug_stacktrace = False
+  release_build_stacktrace_lines = None
+  debug_build_stacktrace_lines = None
+  current_stacktrace_lines = []
+
+  # Iterate through all lines in stacktrace.
+  for line in stacktrace_string.splitlines():
+    line = line.strip()
+
+    # If the line starts with +, it signifies the start of new stacktrace.
+    if line.startswith('+'):
+      if 'Release Build Stacktrace' in line:
+        in_release_or_debug_stacktrace = True
+        current_stacktrace_lines = []
+        release_build_stacktrace_lines = current_stacktrace_lines
+
+      elif 'Debug Build Stacktrace' in line:
+        in_release_or_debug_stacktrace = True
+        current_stacktrace_lines = []
+        debug_build_stacktrace_lines = current_stacktrace_lines
+
+      # If the stacktrace is neither release/debug build stacktrace, ignore
+      # all lines after it until we encounter release/debug build stacktrace.
+      else:
+        in_release_or_debug_stacktrace = False
+
+    # This case, it must be that the line is an actual stack frame, so add to
+    # the current stacktrace.
+    elif in_release_or_debug_stacktrace:
+      current_stacktrace_lines.append(line)
+
+  return (release_build_stacktrace_lines, debug_build_stacktrace_lines)
+
+
+def GetResultsFromString(stacktrace_string,

[stgao, 2014/08/14 18:25:42]

Rename to "FindCulpritCL"?

[jeun, 2014/08/14 20:54:12]

Done.

+                         build_type,
+                         chrome_regression=None,
+                         component_regression=None,
+                         chrome_crash_revision=None,
+                         component_crash_revision=None,
+                         crashing_component=None):
+  """Returns string representation of the result, a list of suspected CLs.

[stgao, 2014/08/14 18:25:42]

After the result.py is committed, maybe refer to result.Result instead of saying
suspected CLs.

[jeun, 2014/08/14 20:54:12]

Done.

+
+  Args:
+    stacktrace_string: A string representing stacktrace.
+    build_type: The type of the job.
+    chrome_regression: A string, chrome regression from clusterfuzz, in format
+                       '123456:123457'
+    component_regression: A string, component regression in the same format.
+    chrome_crash_revision: A crash revision of chrome, in string.
+    component_crash_revision: A crash revision of the component,
+                              if component build.
+    crashing_component: Yet to be decided.
+
+  Returns:
+    A list of result objects.

[stgao, 2014/08/14 18:25:42]

We agreed the returned result would be as below, right?

(message, result_list)
message: Message as summary of the result.
result_list: a list of result.Result, could be an empty list.

[jeun, 2014/08/14 20:54:12]

Done.

+  """
+  build_type = build_type.lower()
+  if 'android' in build_type or 'windows' in build_type:
+    return 'This build type is currently not supported.'
+
+  crash_revision_dict = {}
+  regression_dict = {}
+
+  # TODO(jeun): Come up with a good way to connect crashing component name to
+  # its path.
+  if component_regression or component_crash_revision:
+    return 'This feature is not supported.'
+
+  # If chrome regression is available, parse DEPS file.
+  chrome_regression = crash_utils.SplitRange(chrome_regression)
+  if chrome_regression:
+    chrome_regression_start = chrome_regression[0]
+    chrome_regression_end = chrome_regression[1]
+
+    # If the regression is not reliable, do not parse regression information.
+    if chrome_regression_start != '0':
+      regression_dict = chromium_deps.GetChromiumComponentRange(
+          chrome_regression_start, chrome_regression_end)
+
+  # Parse crash revision.
+  if chrome_crash_revision:
+    crash_revision_dict = chromium_deps.GetChromiumComponents(
+        chrome_crash_revision)
+
+  # Parsed DEPS is used to normalize the stacktrace. Since parsed regression
+  # and parsed crash state essentially contain same information, use either.
+  if regression_dict:
+    parsed_deps = regression_dict
+  elif crash_revision_dict:
+    parsed_deps = crash_revision_dict
+  else:
+    return 'No regression and crash revision information available.'
+
+  # Split stacktrace into release build/debug build and parse them.
+  (release_build_stacktrace, debug_build_stacktrace) = SplitStacktrace(
+      stacktrace_string)
+  parsed_release_build_stacktrace = stacktrace.Stacktrace(
+      release_build_stacktrace, build_type, parsed_deps)
+  parsed_debug_build_stacktrace = stacktrace.Stacktrace(
+      debug_build_stacktrace, build_type, parsed_deps)
+  release_stacktrace_exists = parsed_release_build_stacktrace.stack_list

[stgao, 2014/08/14 18:25:42]

*_exists is not necessary, could be merged into the if/elif clause.

[jeun, 2014/08/14 20:54:12]

Done.

+  debug_stacktrace_exists = parsed_debug_build_stacktrace.stack_list
+
+  # Get a highest priority callstack from stacktrace, with release build
+  # stacktrace in higher priority than debug build stacktace.
+  if release_stacktrace_exists:
+    main_stack = parsed_release_build_stacktrace.GetCrashStack()
+  elif debug_stacktrace_exists:
+    main_stack = parsed_debug_build_stacktrace.GetCrashStack()
+  else:
+    return 'ERROR: Stacktrace is malformed.'
+
+  stacktrace_list = [parsed_release_build_stacktrace,
+                     parsed_debug_build_stacktrace]
+  return findit.FindItForCrash(stacktrace_list, main_stack, build_type,
+                               regression_dict, crash_revision_dict)