1# -*- coding: utf-8 -*-
2# Copyright 2012 Google Inc. All Rights Reserved.
3#
4# Licensed under the Apache License, Version 2.0 (the "License");
5# you may not use this file except in compliance with the License.
6# You may obtain a copy of the License at
7#
8#     http://www.apache.org/licenses/LICENSE-2.0
9#
10# Unless required by applicable law or agreed to in writing, software
11# distributed under the License is distributed on an "AS IS" BASIS,
12# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13# See the License for the specific language governing permissions and
14# limitations under the License.
15"""Additional help about subdirectory handling in gsutil."""
16
17from __future__ import absolute_import
18
19from gslib.help_provider import HelpProvider
20
21_DETAILED_HELP_TEXT = ("""
22<B>OVERVIEW</B>
23  This section provides details about how subdirectories work in gsutil.
24  Most users probably don't need to know these details, and can simply use
25  the commands (like cp -r) that work with subdirectories. We provide this
26  additional documentation to help users understand how gsutil handles
27  subdirectories differently than most GUI / web-based tools (e.g., why
28  those other tools create "dir_$folder$" objects), and also to explain cost and
29  performance implications of the gsutil approach, for those interested in such
30  details.
31
32  gsutil provides the illusion of a hierarchical file tree atop the "flat"
33  name space supported by the Google Cloud Storage service. To the service,
34  the object gs://your-bucket/abc/def/ghi.txt is just an object that happens to
35  have "/" characters in its name. There are no "abc" or "abc/def" directories;
36  just a single object with the given name. This diagram:
37  https://cloud.google.com/storage/images/gsutil-subdirectories-thumb.png
38  illustrates how gsutil provides a hierarchical view of objects in a bucket.
39
40  gsutil achieves the hierarchical file tree illusion by applying a variety of
41  rules, to try to make naming work the way users would expect. For example, in
42  order to determine whether to treat a destination URL as an object name or the
43  root of a directory under which objects should be copied gsutil uses these
44  rules:
45
46  1. If the destination object ends with a "/" gsutil treats it as a directory.
47     For example, if you run the command:
48
49       gsutil cp your-file gs://your-bucket/abc/
50
51     gsutil will create the object gs://your-bucket/abc/your-file.
52
53  2. If the destination object is XYZ and an object exists called XYZ_$folder$
54     gsutil treats XYZ as a directory. For example, if you run the command:
55
56       gsutil cp your-file gs://your-bucket/abc
57
58     and there exists an object called abc_$folder$, gsutil will create the
59     object gs://your-bucket/abc/your-file.
60
61  3. If you attempt to copy multiple source files to a destination URL, gsutil
62     treats the destination URL as a directory. For example, if you run
63     the command:
64
65       gsutil cp -r your-dir gs://your-bucket/abc
66
67     gsutil will create objects like gs://your-bucket/abc/your-dir/file1, etc.
68     (assuming file1 is a file under the source directory your-dir).
69
70  4. If none of the above rules applies, gsutil performs a bucket listing to
71     determine if the target of the operation is a prefix match to the
72     specified string. For example, if you run the command:
73
74       gsutil cp your-file gs://your-bucket/abc
75
76     gsutil will make a bucket listing request for the named bucket, using
77     delimiter="/" and prefix="abc". It will then examine the bucket listing
78     results and determine whether there are objects in the bucket whose path
79     starts with gs://your-bucket/abc/, to determine whether to treat the target
80     as an object name or a directory name. In turn this impacts the name of the
81     object you create: If the above check indicates there is an "abc" directory
82     you will end up with the object gs://your-bucket/abc/your-file; otherwise
83     you will end up with the object gs://your-bucket/abc. (See
84     "HOW NAMES ARE CONSTRUCTED" under "gsutil help cp" for more details.)
85
86  This rule-based approach stands in contrast to the way many tools work, which
87  create objects to mark the existence of folders (such as "dir_$folder$").
88  gsutil understands several conventions used by such tools but does not
89  require such marker objects to implement naming behavior consistent with
90  UNIX commands.
91
92  A downside of the gsutil approach is it requires an extra bucket listing
93  before performing the needed cp or mv command. However those listings are
94  relatively inexpensive, because they use delimiter and prefix parameters to
95  limit result data. Moreover, gsutil makes only one bucket listing request
96  per cp/mv command, and thus amortizes the bucket listing cost across all
97  transferred objects (e.g., when performing a recursive copy of a directory
98  to the cloud).
99""")
100
101
102class CommandOptions(HelpProvider):
103  """Additional help about subdirectory handling in gsutil."""
104
105  # Help specification. See help_provider.py for documentation.
106  help_spec = HelpProvider.HelpSpec(
107      help_name='subdirs',
108      help_name_aliases=[
109          'dirs', 'directory', 'directories', 'folder', 'folders', 'hierarchy',
110          'subdir', 'subdirectory', 'subdirectories'],
111      help_type='additional_help',
112      help_one_line_summary='How Subdirectories Work',
113      help_text=_DETAILED_HELP_TEXT,
114      subcommand_help_text={},
115  )
116