Script for exporting WPT

third_party/WebKit/Tools/Scripts/webkitpy/w3c/local_wpt.py

Index: third_party/WebKit/Tools/Scripts/webkitpy/w3c/local_wpt.py
diff --git a/third_party/WebKit/Tools/Scripts/webkitpy/w3c/local_wpt.py b/third_party/WebKit/Tools/Scripts/webkitpy/w3c/local_wpt.py
new file mode 100644
index 0000000000000000000000000000000000000000..829d269d50d5e821a974e559c842f9ef39c36d4d
--- /dev/null
+++ b/third_party/WebKit/Tools/Scripts/webkitpy/w3c/local_wpt.py
@@ -0,0 +1,88 @@
+# 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
+
+
+WPT_REPO_URL = 'https://chromium.googlesource.com/external/w3c/web-platform-tests.git'
+WPT_TMP_DIR = '/tmp/wpt'
+CR_WPT_DIR = 'third_party/WebKit/LayoutTests/imported/wpt/'
+_log = logging.getLogger(__name__)
+
+
+class LocalWPT(object):
+
+    def __init__(self, host, path=WPT_TMP_DIR, no_fetch=False, gh=False):

[qyearsley, 2016/11/04 17:40:32]

A docstring or different argument names might make it clearer what should be
passed in for `path` and `gh`. For gh, would it make sense to call it
use_github?

+        self.host = host
+        self.path = path
+
+        if no_fetch:
+            _log.info('Skipping remote WPT fetch')
+        else:
+            if self.host.filesystem.exists(self.path):
+                _log.info('WPT checkout exists at %s, fetching latest', self.path)
+                self.run(['git', 'checkout', 'master'])
+                self.run(['git', 'fetch', '--all'])
+                self.run(['git', 'merge', '--ff-only', 'origin/master'])
+            else:
+                _log.info('Cloning %s into %s', WPT_REPO_URL, self.path)
+                self.host.executive.run_command(['git', 'clone', WPT_REPO_URL, self.path])
+
+            if gh and 'github' not in self.run(['git', 'remote']):
+                raise Exception('Need to set up remote "github"')

[qyearsley, 2016/11/04 17:40:32]

Possible minor restructuring: if you add a return after `_log.info('Skipping
remote WPT fetch')` then you can get rid of the else branch and un-indent.

+
+    def run(self, command, **kwargs):
+        """Runs a command in the local WPT directory."""
+        return self.host.executive.run_command(command, cwd=self.path, **kwargs)
+
+    def run_to_list(self, command, **kwargs):
+        return self.run(command, **kwargs).splitlines()

[qyearsley, 2016/11/04 17:40:32]

Would it be simpler just to add a .splitlines() in all-branches and remove this
method?

+
+    def most_recent_cr_commit(self):
+        """Goes back in WPT commit history and gets the most recent commit
+        that contains 'Cr-Commit-Position:'
+        """
+        sha = self.run(['git', 'rev-list', 'HEAD', '-n', '1', '--grep=Cr-Commit-Position'])
+        if not sha:
+            return None, None
+
+        sha = sha.strip()
+        position = self.run(['git', 'footers', '--position', sha])
+        position = position.strip()
+        assert position
+        return sha, position
+
+    def clean(self):
+        self.run(['git', 'reset', '--hard', 'HEAD'])
+        self.run(['git', 'clean', '-fdx'])
+        self.run(['git', 'checkout', 'master'])
+
+    def all_branches(self):
+        return self.run_to_list(['git', 'branch', '-a'])
+
+    def create_branch_with_patch(self, branch_name, message, patch):
+        self.clean()
+        all_branches = self.all_branches()
+        remote_branch_name = 'remotes/github/%s' % branch_name
+
+        if branch_name in all_branches:
+            _log.info('Local branch %s already exists, deleting', branch_name)
+            self.run(['git', 'branch', '-D', branch_name])
+
+        if remote_branch_name in all_branches:
+            _log.info('Remote branch %s already exists, deleting', branch_name)
+            # TODO(jeffcarp): Investigate what happens when remote branch exists
+            self.run(['git', 'push', 'github', ':{}'.format(branch_name)])
+
+        _log.info('Creating local branch %s', branch_name)
+        self.run(['git', 'checkout', '-b', branch_name])
+
+        # Remove Chromium WPT directory prefix
+        patch = patch.replace(CR_WPT_DIR, '')
+
+        # TODO(jeffcarp): Use git am -p<n> where n is len(CR_WPT_DIR.split(/'))
+        # or something not off-by-one.
+        self.run(['git', 'apply', '-'], input=patch)
+        self.run(['git', 'commit', '-am', message])
+        self.run(['git', 'push', 'github', branch_name])