[Predator] Add ``Project`` class and ``ClassifySuspect`` method to project and component classifier

appengine/findit/crash/findit_for_chromecrash.py

 # Copyright 2016 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 logging
 
 from google.appengine.ext import ndb
 
 from common import appengine_util
 from crash import detect_regression_range
 from crash.changelist_classifier import ChangelistClassifier
 from crash.chromecrash_parser import ChromeCrashParser
-from crash.component_classifier import Component
+from crash.component import Component
 from crash.component_classifier import ComponentClassifier
 from crash.findit import Findit
 from crash.predator import Predator
+from crash.project import Project
 from crash.project_classifier import ProjectClassifier
 from crash.type_enums import CrashClient
 from model.crash.cracas_crash_analysis import CracasCrashAnalysis
 from model.crash.crash_config import CrashConfig
 from model.crash.fracas_crash_analysis import FracasCrashAnalysis
 
 # TODO(katesonia): Remove the default value after adding validity check to
 # config.
 _FRACAS_FEEDBACK_URL_TEMPLATE = 'https://%s/crash/fracas-result-feedback?key=%s'
 
@@ skipping 17 matching lines @@
     else:
       logging.warning(
           'FinditForChromeCrash subclass %s forgot to implement _ClientID',
           cls.__name__)
     raise NotImplementedError()
 
   # TODO(http://crbug.com/659354): remove the dependency on CrashConfig
   # entirely, by passing the relevant data as arguments to this constructor.
   def __init__(self, get_repository):
     super(FinditForChromeCrash, self).__init__(get_repository)
+    project_classifier_config = CrashConfig.Get().project_classifier
     component_classifier_config = CrashConfig.Get().component_classifier
 
     self._stacktrace_parser = ChromeCrashParser()
 
+    projects = [Project(name, path_regexs, function_regexs, host_directories)

[wrengr, 2017/01/30 19:14:19]

Since the order of the tuple/arguments is the same, I think you should be able
to say ``map(Project,
project_classifier_config['project_path_function_hosts'])`` instead

[Sharu Jiang, 2017/01/30 22:23:52]

It turned out that we cannot do that, but we can do something like:
map(Project, *zip(*project_classifier_config['project_path_function_hosts']))

But I don't think this is very clear and readable.

[wrengr, 2017/01/30 22:30:58]

yeah, that's pretty gross. oh well

+                for name, path_regexs, function_regexs, host_directories
+                in project_classifier_config['project_path_function_hosts']]
+    components = [Component(component_name, path_regex, function_regex)
+                  for path_regex, function_regex, component_name
+                  in component_classifier_config['path_function_component']],
     # The top_n is the number of components we should return as
     # components suggestion results.
     # TODO(http://crbug.com/679964) Deprecate the scorer-based changelist
     # classifier and use loglinear model instead.
     self._predator = Predator(
         cl_classifier = ChangelistClassifier(get_repository),
         component_classifier = ComponentClassifier(
-            [Component(component_name, path_regex, function_regex)
-            for path_regex, function_regex, component_name
-            in component_classifier_config['path_function_component']],
-            component_classifier_config['top_n']),
-        project_classifier = ProjectClassifier())
+            components, component_classifier_config['top_n']),
+        project_classifier = ProjectClassifier(
+            projects, project_classifier_config['top_n'],
+            project_classifier_config['non_chromium_project_rank_priority']))
 
   def _InitializeAnalysis(self, model, crash_data):
     super(FinditForChromeCrash, self)._InitializeAnalysis(model, crash_data)
     # TODO(wrengr): see Note#1
     customized_data = crash_data.get('customized_data', {})
     model.channel = customized_data.get('channel', None)
     model.historical_metadata = customized_data.get('historical_metadata', [])
 
   # TODO(wrengr): see Note#1, which would allow us to lift this
   # implementation to the Findit base class.
@@ skipping 89 matching lines @@
 
   def GetAnalysis(self, crash_identifiers):
     # TODO: inline FracasCrashAnalysis.Get stuff here.
     return FracasCrashAnalysis.Get(crash_identifiers)
 
   def ProcessResultForPublishing(self, result, key):
     """Fracas specific processing of result data for publishing."""
     result['feedback_url'] = _FRACAS_FEEDBACK_URL_TEMPLATE % (
         appengine_util.GetDefaultVersionHostname(), key)
     return result