Added update_test_expectations script to remove non-flaky test expectations.

third_party/WebKit/Tools/Scripts/webkitpy/layout_tests/update_test_expectations.py

Index: third_party/WebKit/Tools/Scripts/webkitpy/layout_tests/update_test_expectations.py
diff --git a/third_party/WebKit/Tools/Scripts/webkitpy/layout_tests/update_test_expectations.py b/third_party/WebKit/Tools/Scripts/webkitpy/layout_tests/update_test_expectations.py
new file mode 100644
index 0000000000000000000000000000000000000000..0fb450abee8a9f72fb010cd7a09bd1880e86e76c
--- /dev/null
+++ b/third_party/WebKit/Tools/Scripts/webkitpy/layout_tests/update_test_expectations.py
@@ -0,0 +1,239 @@
+# 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.
+
+"""Updates TestExpectations based on results in builder bots.
+
+Scans the TestExpectations file and uses results from actual builder bots runs
+to remove tests that are marked as flaky but don't fail in the specified way.
+
+E.g. If a test has this expectation:
+    bug(test) fast/test.html [ Failure Pass ]
+
+And all the runs on builders have passed the line will be removed.
+
+Additionally, the runs don't all have to be Passing to remove the line;
+as long as the non-Passing results are of a type not specified in the
+expectation this line will be removed. For example, if this is the
+expectation:
+
+    bug(test) fast/test.html [ Crash Pass ]
+
+But the results on the builders show only Passes and Timeouts, the line
+will be removed since there's no Crash results.
+
+"""
+
+import argparse
+import logging
+
+from webkitpy.layout_tests.models.test_expectations import TestExpectations
+
+_log = logging.getLogger(__name__)
+
+
+def main(host, bot_test_expectations_factory, argv):
+    parser = argparse.ArgumentParser(epilog=__doc__, formatter_class=argparse.RawTextHelpFormatter)
+    parser.parse_args(argv)
+
+    port = host.port_factory.get()
+
+    logging.basicConfig(level=logging.INFO, format="%(message)s")
+
+    expectations_file = port.path_to_generic_test_expectations_file()
+    if not host.filesystem.isfile(expectations_file):
+        _log.warn("Didn't find generic expectations file at: " + expectations_file)
+        return None
+
+    remove_flakes_o_matic = RemoveFlakesOMatic(host,
+                                               port,
+                                               bot_test_expectations_factory)
+
+    test_expectations = remove_flakes_o_matic.get_updated_test_expectations()
+
+    remove_flakes_o_matic.write_test_expectations(test_expectations,
+                                                  expectations_file)
+
+
+class RemoveFlakesOMatic(object):
+    def __init__(self, host, port, bot_test_expectations_factory):
+        self._host = host
+        self._port = port
+        self._expectations_factory = bot_test_expectations_factory
+        self.builder_results_by_path = {}
+
+    def _can_delete_line(self, test_expectation_line):
+        """Returns whether a given line in the expectations can be removed.
+
+        Uses results from builder bots to determine if a given line is stale and
+        can safely be removed from the TestExpectations file. (i.e. remove if
+        the bots show that it's not flaky.) There's also some rules about when
+        not to remove lines (e.g. never remove lines with Rebaseline
+        expectations, don't remove non-flaky expectations, etc.)
+
+        Args:
+            test_expectation_line (TestExpectationLine): A line in the test
+                expectation file to test for possible removal.
+
+        Returns: True if the line can be removed, False otherwise.
+        """
+        expectations = test_expectation_line.expectations
+        if len(expectations) < 2:
+            return False
+
+        if self._has_unstrippable_expectations(expectations):
+            return False
+
+        if not self._has_pass_expectation(expectations):
+            return False
+
+        # The line can be deleted if the only expectation on the line that appears in the actual
+        # results is the PASS expectation.
+        for config in test_expectation_line.matching_configurations:
+            builder_name = self._host.builders.builder_name_for_specifiers(config.version, config.build_type)
+
+            if not builder_name:
+                _log.error('Failed to get builder for config [%s, %s, %s]' % (config.version, config.architecture, config.build_type))
+                # TODO(bokan): Matching configurations often give us bots that don't have a
+                # builder in builders.py's exact_matches. Should we ignore those or be conservative
+                # and assume we need these expectations to make a decision?
+                return False
+
+            if builder_name not in self.builder_results_by_path.keys():
+                _log.error('Failed to find results for builder "%s"' % builder_name)
+                return False
+
+            results_by_path = self.builder_results_by_path[builder_name]
+
+            # No results means the tests were all skipped or all results are passing.
+            if test_expectation_line.path not in results_by_path.keys():
+                continue
+
+            results_for_single_test = results_by_path[test_expectation_line.path]
+
+            if self._expectations_that_were_met(test_expectation_line, results_for_single_test) != set(['PASS']):
+                return False
+
+        return True
+
+    def _has_pass_expectation(self, expectations):
+        return 'PASS' in expectations
+
+    def _expectations_that_were_met(self, test_expectation_line, results_for_single_test):
+        """Returns the set of expectations that appear in the given results.
+
+        e.g. If the test expectations is:
+            bug(test) fast/test.html [Crash Failure Pass]
+
+        And the results are ['TEXT', 'PASS', 'PASS', 'TIMEOUT']
+
+        This method would return [Pass Failure]
+
+        Args:
+            test_expectation_line: A TestExpectationLine object
+            results_for_single_test: A list of result strings.
+                e.g. ['IMAGE', 'IMAGE', 'PASS']
+
+        Returns:
+            A set containing expectations that occured in the results.
+        """
+        # TODO(bokan): Does this not exist in a more central place?
+        def replace_failing_with_fail(expectation):
+            if expectation in ('TEXT', 'IMAGE', 'IMAGE+TEXT', 'AUDIO'):
+                return 'FAIL'
+            else:
+                return expectation
+
+        actual_results = {replace_failing_with_fail(r) for r in results_for_single_test}
+
+        return set(test_expectation_line.expectations) & actual_results
+
+    def _has_unstrippable_expectations(self, expectations):
+        """ Returns whether any of the given expectations are considered unstrippable.
+
+        Unstrippable expectations are those which should stop a line from being
+        removed regardless of builder bot results.
+
+        Args:
+            expectations: A list of string expectations.
+                E.g. ['PASS', 'FAIL' 'CRASH']
+
+        Returns:
+            True if at least one of the expectations is unstrippable. False
+            otherwise.
+        """
+        unstrippable_expectations = ('REBASELINE', 'NEEDSREBASELINE',
+                                     'NEEDSMANUALREBASELINE', 'SLOW',
+                                     'SKIP')
+        return any(s in expectations for s in unstrippable_expectations)
+
+    def get_updated_test_expectations(self):
+        """Filters out passing lines from TestExpectations file.
+
+        Reads the current TestExpectatoins file and, using results from the
+        build bots, removes lines that are passing. That is, removes lines that
+        were not needed to keep the bots green.
+
+        Returns: A TestExpectations object with the passing lines filtered out.
+        """
+        test_expectations = TestExpectations(self._port, include_overrides=False).expectations()
+
+        self.builder_results_by_path = {}
+        for builder_name in self._host.builders.all_builder_names():
+            expectations_for_builder = (
+                self._expectations_factory.expectations_for_builder(builder_name)
+            )
+
+            if not expectations_for_builder:
+                # This is not fatal since we may not need to check these
+                # results. If we do need these results we'll log an error later
+                # when trying to check against them.
+                _log.warn('Downloaded results are missing results for builder "%s"' % builder_name)
+                continue
+
+            self.builder_results_by_path[builder_name] = (
+                expectations_for_builder.all_results_by_path()
+            )
+
+        expectations_to_remove = []
+
+        for expectation in test_expectations:
+            if self._can_delete_line(expectation):
+                expectations_to_remove.append(expectation)
+
+        for expectation in expectations_to_remove:
+            index = test_expectations.index(expectation)
+            test_expectations.remove(expectation)
+
+            # Remove associated comments and whitespace if we've removed the last expectation under
+            # a comment block. Only remove a comment block if it's not separated from the test
+            # expectation line by whitespace.
+            if index == len(test_expectations) or test_expectations[index].is_whitespace() or test_expectations[index].is_comment():
+                removed_whitespace = False
+                while index and test_expectations[index - 1].is_whitespace():
+                    index = index - 1
+                    test_expectations.pop(index)
+                    removed_whitespace = True
+
+                if not removed_whitespace:
+                    while index and test_expectations[index - 1].is_comment():
+                        index = index - 1
+                        test_expectations.pop(index)
+
+                    while index and test_expectations[index - 1].is_whitespace():
+                        index = index - 1
+                        test_expectations.pop(index)
+
+        return test_expectations
+
+    def write_test_expectations(self, test_expectations, test_expectations_file):
+        """Writes the given TestExpectations object to the filesystem.
+
+        Args:
+            test_expectatoins: The TestExpectations object to write.
+            test_expectations_file: The full file path of the Blink
+                TestExpectations file. This file will be overwritten.
+        """
+        self._host.filesystem.write_text_file(
+            test_expectations_file,
+            TestExpectations.list_to_string(test_expectations, reconstitute_only_these=[]))