1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
|
#!/usr/bin/env python
# Copyright 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 argparse
import logging
import os
import subprocess
import sys
from telemetry.core import util
from telemetry.internal.util import command_line
sys.path.insert(1, os.path.abspath(os.path.join(
util.GetCatapultDir(), 'common', 'py_utils')))
from py_utils import cloud_storage
BUCKETS = {bucket: easy_bucket_name for easy_bucket_name, bucket
in cloud_storage.BUCKET_ALIASES.iteritems()}
def _GetPaths(path):
root, ext = os.path.splitext(path)
if ext == '.sha1':
file_path = root
hash_path = path
else:
file_path = path
hash_path = path + '.sha1'
return file_path, hash_path
def _FindFilesInCloudStorage(files):
"""Returns a dict of all files and which buckets they're in."""
# Preprocessing: get the contents of all buckets.
bucket_contents = {}
for bucket in BUCKETS:
try:
bucket_contents[bucket] = cloud_storage.List(bucket)
except (cloud_storage.PermissionError, cloud_storage.CredentialsError):
pass
# Check if each file is in the bucket contents.
file_buckets = {}
for path in files:
file_path, hash_path = _GetPaths(path)
if file_path in file_buckets:
# Ignore duplicates, if both data and sha1 file were in the file list.
continue
if not os.path.exists(hash_path):
# Probably got some non-Cloud Storage files in the file list. Ignore.
continue
file_hash = cloud_storage.ReadHash(hash_path)
file_buckets[file_path] = []
for bucket in BUCKETS:
if bucket in bucket_contents and file_hash in bucket_contents[bucket]:
file_buckets[file_path].append(bucket)
return file_buckets
class Ls(command_line.Command):
"""List which bucket each file is in."""
@classmethod
def AddCommandLineArgs(cls, parser):
parser.add_argument('-r', '--recursive', action='store_true')
parser.add_argument('paths', nargs='+')
@classmethod
def ProcessCommandLineArgs(cls, parser, args):
for path in args.paths:
if not os.path.exists(path):
parser.error('Path not found: %s' % path)
def Run(self, args):
def GetFilesInPaths(paths, recursive):
"""If path is a dir, yields all files in path, otherwise just yields path.
If recursive is true, walks subdirectories recursively."""
for path in paths:
if not os.path.isdir(path):
yield path
continue
if recursive:
for root, _, filenames in os.walk(path):
for filename in filenames:
yield os.path.join(root, filename)
else:
for filename in os.listdir(path):
yield os.path.join(path, filename)
files = _FindFilesInCloudStorage(GetFilesInPaths(args.paths, args.recursive))
if not files:
print 'No files in Cloud Storage.'
return
for file_path, buckets in sorted(files.iteritems()):
if buckets:
buckets = [BUCKETS[bucket] for bucket in buckets]
print '%-11s %s' % (','.join(buckets), file_path)
else:
print '%-11s %s' % ('not found', file_path)
class Mv(command_line.Command):
"""Move files to the given bucket."""
@classmethod
def AddCommandLineArgs(cls, parser):
parser.add_argument('files', nargs='+')
parser.add_argument('bucket', choices=cloud_storage.BUCKET_ALIASES)
@classmethod
def ProcessCommandLineArgs(cls, parser, args):
args.bucket = cloud_storage.BUCKET_ALIASES[args.bucket]
def Run(self, args):
files = _FindFilesInCloudStorage(args.files)
for file_path, buckets in sorted(files.iteritems()):
if not buckets:
raise IOError('%s not found in Cloud Storage.' % file_path)
for file_path, buckets in sorted(files.iteritems()):
if args.bucket in buckets:
buckets.remove(args.bucket)
if not buckets:
logging.info('Skipping %s, no action needed.' % file_path)
continue
# Move to the target bucket.
file_hash = cloud_storage.ReadHash(file_path + '.sha1')
cloud_storage.Move(buckets.pop(), args.bucket, file_hash)
# Delete all additional copies.
for bucket in buckets:
cloud_storage.Delete(bucket, file_hash)
class Rm(command_line.Command):
"""Remove files from Cloud Storage."""
@classmethod
def AddCommandLineArgs(cls, parser):
parser.add_argument('files', nargs='+')
def Run(self, args):
files = _FindFilesInCloudStorage(args.files)
for file_path, buckets in sorted(files.iteritems()):
file_hash = cloud_storage.ReadHash(file_path + '.sha1')
for bucket in buckets:
cloud_storage.Delete(bucket, file_hash)
class Upload(command_line.Command):
"""Upload files to Cloud Storage."""
@classmethod
def AddCommandLineArgs(cls, parser):
parser.add_argument('files', nargs='+')
parser.add_argument('bucket', choices=cloud_storage.BUCKET_ALIASES)
@classmethod
def ProcessCommandLineArgs(cls, parser, args):
args.bucket = cloud_storage.BUCKET_ALIASES[args.bucket]
for path in args.files:
if not os.path.exists(path):
parser.error('File not found: %s' % path)
def Run(self, args):
for file_path in args.files:
file_hash = cloud_storage.CalculateHash(file_path)
# Create or update the hash file.
hash_path = file_path + '.sha1'
with open(hash_path, 'wb') as f:
f.write(file_hash)
f.flush()
# Add the data to Cloud Storage.
cloud_storage.Insert(args.bucket, file_hash, file_path)
# Add the hash file to the branch, for convenience. :)
subprocess.call(['git', 'add', hash_path])
class CloudStorageCommand(command_line.SubcommandCommand):
commands = (Ls, Mv, Rm, Upload)
if __name__ == '__main__':
logging.getLogger().setLevel(logging.INFO)
sys.exit(CloudStorageCommand.main())
|
