[Findit] Plain objects to represent and parse stack trace.

tools/findit/stacktrace.py

Index: tools/findit/stacktrace.py
diff --git a/tools/findit/stacktrace.py b/tools/findit/stacktrace.py
new file mode 100644
index 0000000000000000000000000000000000000000..490750037166144e1e910c0502c0e852244bac73
--- /dev/null
+++ b/tools/findit/stacktrace.py
@@ -0,0 +1,169 @@
+# 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 os
+import re
+import crash_utils
+
+
+class Stacktrace(object):
+  """Represents Stacktrace object.
+
+  Contains release build stacktrace and debug build stacktrace.
+  """
+
+  def __init__(self, stacktrace, chrome_build):
+    self.stack_list = []
+    self.ParseStacktrace(stacktrace, chrome_build)
+
+  def ParseStacktrace(self, stacktrace, chrome_build):
+    """Parses stacktrace and normalizes it.
+
+    If there are multiple callstacks within the stacktrace,
+    it will parse each of them separately, and store them in the stack_list
+    variable.
+
+    Args:
+      stacktrace: a string containing stacktrace
+      chrome_build: a string containing the job type of the crash
+    """
+    # If the passed in string is empty, the object does not represent anything.
+    if not stacktrace:
+      self.stack_list = None
+      return
+
+    stack_frame_index_pattern = re.compile(r'#(\d+)')
+
+    # Reset the stack list, and assume we start from main thread.
+    self.stack_list = []
+    stack_priority = 0
+    seen_main_thread = False

[stgao, 2014/07/31 19:48:58]

reach_new_callstack?

+    current_stack = CallStack(stack_priority)
+
+    for line in stacktrace:
+      # match the line to see if it is a valid stack frame

[stgao, 2014/07/31 19:48:58]

nit: comment style

+      stack_frame_index_match = stack_frame_index_pattern.match(line)
+
+      # If this line does not represent the crashing information, continue.
+      if not stack_frame_index_match:
+        continue
+
+      # Get the stack frame index from the match
+      stack_frame_index = int(stack_frame_index_match.group(1))
+
+      # If it is 0, we need to check if this is from freed or prev-alloc, or
+      # is from main thead.
+      if stack_frame_index == 0:
+
+        # If this callstack is from main thread, update the boolean.
+        if not seen_main_thread:
+          seen_main_thread = True
+
+        # If this is from freed or prev-alloc, add the callstack we have
+        # to the list of callstacks, and increment the stack priority.
+        else:
+          self.stack_list.append(current_stack)
+          stack_priority += 1
+          current_stack = CallStack(stack_priority)
+
+      # Parse function name, file path and line number from the line.
+      parsed_stack_frame_line = self.ExtractFromStackFrame(
+          line, chrome_build)
+
+      # If the line is malformed, ignore this line. Else, get the info.
+      if not parsed_stack_frame_line:
+        continue
+      (function, file_path, crashed_line_number) = parsed_stack_frame_line
+
+      # Normalize the file path so that it can be compared to repository path.
+      file_name = os.path.basename(file_path)
+      (component, file_path) = crash_utils.NormalizePathLinux(file_path)
+
+      # Currently supports only blink and chromium.
+      if component == 'blink' or component == 'chromium':
+        current_stack.Add(
+            StackFrame(stack_frame_index, component, file_name,
+                           function, file_path, crashed_line_number))
+
+    self.stack_list.append(current_stack)
+
+  def ExtractFromStackFrame(self, line, chrome_build):

[stgao, 2014/07/31 19:48:58]

Used within class only. Add underscore before function name.

+    """Extracts information from a line in stacktrace.
+
+    Args:
+      line: a stacktrace string to extract data from
+      chrome_build: a string containing the job type
+               of this crash (e.g. linux_asan_chrome_mp)
+
+    Returns:
+      A triple containing the name of the function, the path of the file and
+      the line of crash
+    """
+    line_parts = line.split()
+    try:
+      # tsan has different stack frame style from other builds.
+      if chrome_build.startswith('linux_tsan'):
+        file_path_and_line = line_parts[-2]
+        function = ' '.join(line_parts[1:-2])
+
+      else:
+        file_path_and_line = line_parts[-1]
+        function = ' '.join(line_parts[3:-1])
+
+      # Get file path and line info from the line.
+      file_path_and_line = file_path_and_line.split(':')
+      file_path = file_path_and_line[0]
+      crashed_line_number = int(file_path_and_line[1])
+      return (function, file_path, crashed_line_number)
+
+    # Return None if the line is malformed.
+    except IndexError:
+      return None
+    except ValueError:
+      return None
+
+  def __getitem__(self, index):
+    return self.stack_list[index]
+
+  def GetStackFromMainThread(self):
+    return self.stack_list[0]
+
+
+class CallStack(object):
+  """Represents a call stack within a stacktrace.
+
+  It is a list of StackFrame object, and the stack represented by
+  this object is from main thread, freed thread or previously-allocated thread.
+  """
+
+  def __init__(self, stack_priority):
+    self.frame_list = []
+    self.priority = stack_priority
+
+  def Add(self, stacktrace_line):
+    self.frame_list.append(stacktrace_line)
+
+  def GetFirstN(self, n):
+    return self.frame_list[:n]
+
+
+class StackFrame(object):
+  """Represents a line in stacktrace.
+
+  Attributes:
+    index: index in the stacktrace
+    component: a component this line represents, such as blink, chrome, etc.
+    file_name: name of the file that crashed
+    function: function that caused the crash
+    file_path: path of the crashed file
+    crashed_line_number: line of the file that caused the crash
+  """
+
+  def __init__(self, stack_frame_index, component, file_name,
+               function, file_path, crashed_line_number):
+    self.index = stack_frame_index
+    self.component = component
+    self.file_name = file_name
+    self.function = function
+    self.file_path = file_path
+    self.crashed_line_number = crashed_line_number