prefect-managedfiletransfer 0.1.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (54) hide show
  1. prefect_managedfiletransfer-0.1.0/LICENSE +202 -0
  2. prefect_managedfiletransfer-0.1.0/PKG-INFO +193 -0
  3. prefect_managedfiletransfer-0.1.0/README.md +169 -0
  4. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/AssetDownloadResult.py +40 -0
  5. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/FileMatcher.py +41 -0
  6. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/FileToFolderMapping.py +92 -0
  7. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/PathUtil.py +84 -0
  8. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/RCloneCommandBuilder.py +217 -0
  9. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/RCloneConfig.py +10 -0
  10. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/RCloneConfigFileBlock.py +51 -0
  11. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/RCloneConfigSavedInPrefect.py +19 -0
  12. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/RemoteAsset.py +16 -0
  13. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/RemoteConnectionType.py +7 -0
  14. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/ServerWithBasicAuthBlock.py +64 -0
  15. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/ServerWithPublicKeyAuthBlock.py +101 -0
  16. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/SortFilesBy.py +26 -0
  17. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/TransferType.py +6 -0
  18. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/__init__.py +54 -0
  19. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/constants.py +18 -0
  20. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/deploy.py +123 -0
  21. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/download_asset.py +392 -0
  22. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/download_file_task.py +95 -0
  23. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/ensure_space.py +27 -0
  24. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/flows.py +30 -0
  25. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/invoke_rclone.py +207 -0
  26. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/list_remote_assets.py +316 -0
  27. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/list_remote_files_task.py +88 -0
  28. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/main.py +364 -0
  29. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/rclone/osx/rclone +0 -0
  30. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/rclone/rclone +0 -0
  31. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/rclone/rclone.exe +0 -0
  32. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/sftp_utils.py +239 -0
  33. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/tasks.py +25 -0
  34. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/time_util.py +82 -0
  35. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/transfer_files_flow.py +202 -0
  36. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/unpack_files_flow.py +217 -0
  37. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/upload_asset.py +336 -0
  38. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/upload_file_flow.py +240 -0
  39. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer/upload_file_task.py +107 -0
  40. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer.egg-info/PKG-INFO +193 -0
  41. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer.egg-info/SOURCES.txt +52 -0
  42. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer.egg-info/dependency_links.txt +1 -0
  43. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer.egg-info/entry_points.txt +2 -0
  44. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer.egg-info/requires.txt +3 -0
  45. prefect_managedfiletransfer-0.1.0/prefect_managedfiletransfer.egg-info/top_level.txt +1 -0
  46. prefect_managedfiletransfer-0.1.0/pyproject.toml +124 -0
  47. prefect_managedfiletransfer-0.1.0/setup.cfg +4 -0
  48. prefect_managedfiletransfer-0.1.0/tests/test_block_standards.py +20 -0
  49. prefect_managedfiletransfer-0.1.0/tests/test_blocks.py +24 -0
  50. prefect_managedfiletransfer-0.1.0/tests/test_download_asset.py +366 -0
  51. prefect_managedfiletransfer-0.1.0/tests/test_flows.py +6 -0
  52. prefect_managedfiletransfer-0.1.0/tests/test_list_asset.py +302 -0
  53. prefect_managedfiletransfer-0.1.0/tests/test_tasks.py +24 -0
  54. prefect_managedfiletransfer-0.1.0/tests/test_upload_asset.py +610 -0
@@ -0,0 +1,202 @@
1
+
2
+ Apache License
3
+ Version 2.0, January 2004
4
+ http://www.apache.org/licenses/
5
+
6
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+ 1. Definitions.
9
+
10
+ "License" shall mean the terms and conditions for use, reproduction,
11
+ and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+ "Licensor" shall mean the copyright owner or entity authorized by
14
+ the copyright owner that is granting the License.
15
+
16
+ "Legal Entity" shall mean the union of the acting entity and all
17
+ other entities that control, are controlled by, or are under common
18
+ control with that entity. For the purposes of this definition,
19
+ "control" means (i) the power, direct or indirect, to cause the
20
+ direction or management of such entity, whether by contract or
21
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+ outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+ "You" (or "Your") shall mean an individual or Legal Entity
25
+ exercising permissions granted by this License.
26
+
27
+ "Source" form shall mean the preferred form for making modifications,
28
+ including but not limited to software source code, documentation
29
+ source, and configuration files.
30
+
31
+ "Object" form shall mean any form resulting from mechanical
32
+ transformation or translation of a Source form, including but
33
+ not limited to compiled object code, generated documentation,
34
+ and conversions to other media types.
35
+
36
+ "Work" shall mean the work of authorship, whether in Source or
37
+ Object form, made available under the License, as indicated by a
38
+ copyright notice that is included in or attached to the work
39
+ (an example is provided in the Appendix below).
40
+
41
+ "Derivative Works" shall mean any work, whether in Source or Object
42
+ form, that is based on (or derived from) the Work and for which the
43
+ editorial revisions, annotations, elaborations, or other modifications
44
+ represent, as a whole, an original work of authorship. For the purposes
45
+ of this License, Derivative Works shall not include works that remain
46
+ separable from, or merely link (or bind by name) to the interfaces of,
47
+ the Work and Derivative Works thereof.
48
+
49
+ "Contribution" shall mean any work of authorship, including
50
+ the original version of the Work and any modifications or additions
51
+ to that Work or Derivative Works thereof, that is intentionally
52
+ submitted to Licensor for inclusion in the Work by the copyright owner
53
+ or by an individual or Legal Entity authorized to submit on behalf of
54
+ the copyright owner. For the purposes of this definition, "submitted"
55
+ means any form of electronic, verbal, or written communication sent
56
+ to the Licensor or its representatives, including but not limited to
57
+ communication on electronic mailing lists, source code control systems,
58
+ and issue tracking systems that are managed by, or on behalf of, the
59
+ Licensor for the purpose of discussing and improving the Work, but
60
+ excluding communication that is conspicuously marked or otherwise
61
+ designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+ "Contributor" shall mean Licensor and any individual or Legal Entity
64
+ on behalf of whom a Contribution has been received by Licensor and
65
+ subsequently incorporated within the Work.
66
+
67
+ 2. Grant of Copyright License. Subject to the terms and conditions of
68
+ this License, each Contributor hereby grants to You a perpetual,
69
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+ copyright license to reproduce, prepare Derivative Works of,
71
+ publicly display, publicly perform, sublicense, and distribute the
72
+ Work and such Derivative Works in Source or Object form.
73
+
74
+ 3. Grant of Patent License. Subject to the terms and conditions of
75
+ this License, each Contributor hereby grants to You a perpetual,
76
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+ (except as stated in this section) patent license to make, have made,
78
+ use, offer to sell, sell, import, and otherwise transfer the Work,
79
+ where such license applies only to those patent claims licensable
80
+ by such Contributor that are necessarily infringed by their
81
+ Contribution(s) alone or by combination of their Contribution(s)
82
+ with the Work to which such Contribution(s) was submitted. If You
83
+ institute patent litigation against any entity (including a
84
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+ or a Contribution incorporated within the Work constitutes direct
86
+ or contributory patent infringement, then any patent licenses
87
+ granted to You under this License for that Work shall terminate
88
+ as of the date such litigation is filed.
89
+
90
+ 4. Redistribution. You may reproduce and distribute copies of the
91
+ Work or Derivative Works thereof in any medium, with or without
92
+ modifications, and in Source or Object form, provided that You
93
+ meet the following conditions:
94
+
95
+ (a) You must give any other recipients of the Work or
96
+ Derivative Works a copy of this License; and
97
+
98
+ (b) You must cause any modified files to carry prominent notices
99
+ stating that You changed the files; and
100
+
101
+ (c) You must retain, in the Source form of any Derivative Works
102
+ that You distribute, all copyright, patent, trademark, and
103
+ attribution notices from the Source form of the Work,
104
+ excluding those notices that do not pertain to any part of
105
+ the Derivative Works; and
106
+
107
+ (d) If the Work includes a "NOTICE" text file as part of its
108
+ distribution, then any Derivative Works that You distribute must
109
+ include a readable copy of the attribution notices contained
110
+ within such NOTICE file, excluding those notices that do not
111
+ pertain to any part of the Derivative Works, in at least one
112
+ of the following places: within a NOTICE text file distributed
113
+ as part of the Derivative Works; within the Source form or
114
+ documentation, if provided along with the Derivative Works; or,
115
+ within a display generated by the Derivative Works, if and
116
+ wherever such third-party notices normally appear. The contents
117
+ of the NOTICE file are for informational purposes only and
118
+ do not modify the License. You may add Your own attribution
119
+ notices within Derivative Works that You distribute, alongside
120
+ or as an addendum to the NOTICE text from the Work, provided
121
+ that such additional attribution notices cannot be construed
122
+ as modifying the License.
123
+
124
+ You may add Your own copyright statement to Your modifications and
125
+ may provide additional or different license terms and conditions
126
+ for use, reproduction, or distribution of Your modifications, or
127
+ for any such Derivative Works as a whole, provided Your use,
128
+ reproduction, and distribution of the Work otherwise complies with
129
+ the conditions stated in this License.
130
+
131
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
132
+ any Contribution intentionally submitted for inclusion in the Work
133
+ by You to the Licensor shall be under the terms and conditions of
134
+ this License, without any additional terms or conditions.
135
+ Notwithstanding the above, nothing herein shall supersede or modify
136
+ the terms of any separate license agreement you may have executed
137
+ with Licensor regarding such Contributions.
138
+
139
+ 6. Trademarks. This License does not grant permission to use the trade
140
+ names, trademarks, service marks, or product names of the Licensor,
141
+ except as required for reasonable and customary use in describing the
142
+ origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+ 7. Disclaimer of Warranty. Unless required by applicable law or
145
+ agreed to in writing, Licensor provides the Work (and each
146
+ Contributor provides its Contributions) on an "AS IS" BASIS,
147
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+ implied, including, without limitation, any warranties or conditions
149
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+ PARTICULAR PURPOSE. You are solely responsible for determining the
151
+ appropriateness of using or redistributing the Work and assume any
152
+ risks associated with Your exercise of permissions under this License.
153
+
154
+ 8. Limitation of Liability. In no event and under no legal theory,
155
+ whether in tort (including negligence), contract, or otherwise,
156
+ unless required by applicable law (such as deliberate and grossly
157
+ negligent acts) or agreed to in writing, shall any Contributor be
158
+ liable to You for damages, including any direct, indirect, special,
159
+ incidental, or consequential damages of any character arising as a
160
+ result of this License or out of the use or inability to use the
161
+ Work (including but not limited to damages for loss of goodwill,
162
+ work stoppage, computer failure or malfunction, or any and all
163
+ other commercial damages or losses), even if such Contributor
164
+ has been advised of the possibility of such damages.
165
+
166
+ 9. Accepting Warranty or Additional Liability. While redistributing
167
+ the Work or Derivative Works thereof, You may choose to offer,
168
+ and charge a fee for, acceptance of support, warranty, indemnity,
169
+ or other liability obligations and/or rights consistent with this
170
+ License. However, in accepting such obligations, You may act only
171
+ on Your own behalf and on Your sole responsibility, not on behalf
172
+ of any other Contributor, and only if You agree to indemnify,
173
+ defend, and hold each Contributor harmless for any liability
174
+ incurred by, or claims asserted against, such Contributor by reason
175
+ of your accepting any such warranty or additional liability.
176
+
177
+ END OF TERMS AND CONDITIONS
178
+
179
+ APPENDIX: How to apply the Apache License to your work.
180
+
181
+ To apply the Apache License to your work, attach the following
182
+ boilerplate notice, with the fields enclosed by brackets "[]"
183
+ replaced with your own identifying information. (Don't include
184
+ the brackets!) The text should be enclosed in the appropriate
185
+ comment syntax for the file format. We also recommend that a
186
+ file or class name and description of purpose be included on the
187
+ same "printed page" as the copyright notice for easier
188
+ identification within third-party archives.
189
+
190
+ Copyright 2021 Prefect Technologies, Inc.
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.
@@ -0,0 +1,193 @@
1
+ Metadata-Version: 2.4
2
+ Name: prefect-managedfiletransfer
3
+ Version: 0.1.0
4
+ Summary: Upload and download files easily between Local/SFTP/Cloud storage using rclone
5
+ Author-email: Alastair Crabtree <a.crabtree@imperial.ac.uk>
6
+ License-Expression: Apache-2.0
7
+ Project-URL: Homepage, https://github.com/ImperialCollegeLondon/prefect-managedfiletransfer
8
+ Keywords: prefect,file,copy,move,transfer,SFTP,rclone
9
+ Classifier: Intended Audience :: Developers
10
+ Classifier: Intended Audience :: System Administrators
11
+ Classifier: Natural Language :: English
12
+ Classifier: Programming Language :: Python :: 3 :: Only
13
+ Classifier: Programming Language :: Python :: 3.10
14
+ Classifier: Programming Language :: Python :: 3.11
15
+ Classifier: Programming Language :: Python :: 3.12
16
+ Classifier: Topic :: Software Development :: Libraries
17
+ Requires-Python: >=3.10
18
+ Description-Content-Type: text/markdown
19
+ License-File: LICENSE
20
+ Requires-Dist: prefect>=3.1.7
21
+ Requires-Dist: pydantic>=2.11.0a2
22
+ Requires-Dist: paramiko>=4.0.0
23
+ Dynamic: license-file
24
+
25
+ # Prefect Managed File Transfer
26
+
27
+ <p align="center">
28
+ <!--- Insert a cover image here -->
29
+ <!--- <br> -->
30
+ <a href="https://pypi.python.org/pypi/prefect-managedfiletransfer/" alt="PyPI version">
31
+ <img alt="PyPI" src="https://img.shields.io/pypi/v/prefect-managedfiletransfer?color=0052FF&labelColor=090422"></a>
32
+ <a href="https://github.com/ImperialCollegeLondon/prefect-managedfiletransfer/" alt="Stars">
33
+ <img src="https://img.shields.io/github/stars/ImperialCollegeLondon/prefect-managedfiletransfer?color=0052FF&labelColor=090422" /></a>
34
+ <a href="https://pypistats.org/packages/prefect-managedfiletransfer/" alt="Downloads">
35
+ <img src="https://img.shields.io/pypi/dm/prefect-managedfiletransfer?color=0052FF&labelColor=090422" /></a>
36
+ <a href="https://github.com/ImperialCollegeLondon/prefect-managedfiletransfer/pulse" alt="Activity">
37
+ <img src="https://img.shields.io/github/commit-activity/m/ImperialCollegeLondon/prefect-managedfiletransfer?color=0052FF&labelColor=090422" /></a>
38
+ <br>
39
+ </p>
40
+
41
+ Turn a prefect.io server into a managed file transfer solution. UI and Programatic creation of cron style jobs (aka Flows!) to upload and download files easily between servers. Support local, SFTP remotes plus any Cloud storage supported by rclone - so thats aws, azure, google, sharepoint, and [many more](https://rclone.org/overview/) out of the box.
42
+
43
+ Using prefect for managed file transfer means retries, logging, multi node and [high availability](https://docs.prefect.io/v3/advanced/self-hosted) come as standard - turning prefect into a reliable enterprise ready file transfer solution.
44
+
45
+ This package is not the fastest solution to move files around, but it prioritises reliability and ease of use, making it an excellent choice for replacing both quick cron job copy scripts and enterprise managed file transfer applicances.
46
+
47
+ Key features
48
+
49
+ - Copy and move files between almost any storage system easily.
50
+ - Reliable file moving with checksumming, file size checking etc.
51
+ - Smart and safe moving - settings to allow/block overwriting and to only copy files if they are new or changed.
52
+ - Unzip/Untar compressed folders after downloading them.
53
+ - Repath files as you move them.
54
+ - Complex filtering and ordering of files - by path, age, size etc. Pattern matching with regular expressions.
55
+ - Leverage Prefect.IO built in scheduling and orchestration capabilities:
56
+ - Transfer files on complex cron schedules
57
+ - notifications on success/failure - slack, email, etc
58
+ - Highly available server architecture - database server + multi-node workers and front ends.
59
+
60
+ Example use cases:
61
+
62
+ - Once per day SSH into my database server and copy the latest *.bkup file to a central storage location.
63
+ - Monitor a local network share directory for new files and automatically upload them to a cloud storage bucket.
64
+ - Schedule a weekly job to synchronize files between two remote servers.
65
+ - Move log files from a SSH available web server older than 30 days to a cold storage location.
66
+ - Copy file yyyy-MM-dd.zip from a remote server, where yyyy-MM-dd matches todays date, to a local directory and then unzip it.
67
+ - Download any file in an S3 bucket larger than 1GB and store it in a local directory.
68
+
69
+ ### Installation
70
+
71
+ Install `prefect-managedfiletransfer` with `pip`. (Requires an installation of Python 3.10+.)
72
+
73
+ ```bash
74
+ pip install prefect-managedfiletransfer
75
+ # or
76
+ uv add prefect-managedfiletransfer
77
+ ```
78
+
79
+ We recommend using a Python virtual environment manager such as uv, pipenv, conda or virtualenv.
80
+
81
+ In one (venv) terminal start a prefect server with logs enabled
82
+
83
+ ```bash
84
+ export PREFECT_LOGGING_LEVEL="INFO"
85
+ export PREFECT_LOGGING_EXTRA_LOGGERS="prefect_managedfiletransfer"
86
+ prefect server start
87
+ # OR uv run prefect server start
88
+ ```
89
+
90
+ There are many ways to manage infrastructure and code with prefect - here we demonstate starting a local worker:
91
+
92
+ ```bash
93
+ export PREFECT_API_URL=http://127.0.0.1:4200/api
94
+ # or perhaps export PREFECT_API_URL=http://host.docker.internal:4200/api
95
+ export PREFECT_LOGGING_EXTRA_LOGGERS="prefect_managedfiletransfer"
96
+ export PREFECT_LOGGING_LEVEL="INFO"
97
+ # [Optional] add all logs: export PREFECT_LOGGING_ROOT_LEVEL="INFO"
98
+
99
+
100
+ prefect worker start --pool 'default-pool' --type process
101
+ # OR prefect worker start --pool 'default-pool' --type docker
102
+
103
+ ```
104
+
105
+ Install the blocks using the prefect CLI
106
+
107
+ ```bash
108
+ prefect block register -m prefect_managedfiletransfer
109
+ ```
110
+
111
+ And then deploy the flows.
112
+
113
+ ```bash
114
+ # deploy the flows to run locally
115
+ python -m prefect_managedfiletransfer.deploy --local
116
+
117
+ # OR deploy to run with a docker image - see deploy.py
118
+ python -m prefect_managedfiletransfer.deploy --docker
119
+
120
+ # or a version of the above using uv run:
121
+ uv run python -m prefect_managedfiletransfer.deploy --local
122
+ uv run python -m prefect_managedfiletransfer.deploy --docker
123
+ ```
124
+
125
+ Visit the server UI http://localhost:4200.
126
+ 1. Create 2 blocks, one source and one destination
127
+ 2. On the deployments page start a `transfer_files_flow`. Configure your flow run to copy/move files between the 2 blocks.
128
+
129
+ ### Installation via docker
130
+
131
+ ```bash
132
+ # run prefect server in a container port-forwarded to your local machine’s 4200 port:
133
+ docker run -d -p 4200:4200 prefecthq/prefect:3-latest -- prefect server start --host 0.0.0.0
134
+ ```
135
+
136
+ ### List of components
137
+
138
+ Blocks
139
+ - ServerWithBasicAuthBlock - A block for connecting to a server using basic authentication.
140
+ - ServerWithPublicKeyAuthBlock - A block for connecting to a server using public key authentication.
141
+ - RCloneConfigFileBlock - A block for managing RClone configuration files.
142
+
143
+ Tasks
144
+ - list_remote_files_task - A task for listing files in a remote directory.
145
+ - download_file_task - A task for downloading a single file from a remote server.
146
+ - upload_file_task - A task for uploading a single file to a remote server.
147
+ - [TODO] delete_file_task
148
+
149
+ Flows
150
+ - transfer_files_flow - a fully featured flow for transferring files between different storage locations.
151
+ - upload_file_flow - a flow for uploading a file to a remote server. Supports pattern matching by date
152
+
153
+ ### Feedback
154
+
155
+ If you encounter any bugs while using `prefect-managedfiletransfer`, feel free to open an issue in the [prefect-managedfiletransfer](https://github.com/ImperialCollegeLondon/prefect-managedfiletransfer) repository.
156
+
157
+
158
+ Feel free to star or watch [`prefect-managedfiletransfer`](https://github.com/ImperialCollegeLondon/prefect-managedfiletransfer) for updates too!
159
+
160
+ ### Contributing
161
+
162
+ If you'd like to help contribute to fix an issue or add a feature to `prefect-managedfiletransfer`, please [propose changes through a pull request from a fork of the repository](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request-from-a-fork).
163
+
164
+ Here are the steps:
165
+
166
+ 1. [Fork the repository](https://docs.github.com/en/get-started/quickstart/fork-a-repo#forking-a-repository)
167
+ 2. [Clone the forked repository](https://docs.github.com/en/get-started/quickstart/fork-a-repo#cloning-your-forked-repository)
168
+ 3. Install the repository and its dependencies:
169
+ ```
170
+ # install uv first, then
171
+ uv sync
172
+ ```
173
+
174
+ You can also access all the prefect CLI tooling inside a uv managed venv
175
+ ```
176
+ uv venv
177
+ source .venv/bin/activate
178
+ prefect server start
179
+ ```
180
+
181
+ 4. Make desired changes
182
+ 5. Add tests
183
+ 6. Insert an entry to [CHANGELOG.md](https://github.com/ImperialCollegeLondon/prefect-managedfiletransfer/blob/main/CHANGELOG.md)
184
+ 7. Install `pre-commit` to perform quality checks prior to commit:
185
+ ```
186
+ pre-commit install
187
+ ```
188
+ 8. use the build script to run all the checks and tests:
189
+
190
+ ```
191
+ ./build.sh
192
+ ```
193
+ 8. `git commit`, `git push`, and create a pull request
@@ -0,0 +1,169 @@
1
+ # Prefect Managed File Transfer
2
+
3
+ <p align="center">
4
+ <!--- Insert a cover image here -->
5
+ <!--- <br> -->
6
+ <a href="https://pypi.python.org/pypi/prefect-managedfiletransfer/" alt="PyPI version">
7
+ <img alt="PyPI" src="https://img.shields.io/pypi/v/prefect-managedfiletransfer?color=0052FF&labelColor=090422"></a>
8
+ <a href="https://github.com/ImperialCollegeLondon/prefect-managedfiletransfer/" alt="Stars">
9
+ <img src="https://img.shields.io/github/stars/ImperialCollegeLondon/prefect-managedfiletransfer?color=0052FF&labelColor=090422" /></a>
10
+ <a href="https://pypistats.org/packages/prefect-managedfiletransfer/" alt="Downloads">
11
+ <img src="https://img.shields.io/pypi/dm/prefect-managedfiletransfer?color=0052FF&labelColor=090422" /></a>
12
+ <a href="https://github.com/ImperialCollegeLondon/prefect-managedfiletransfer/pulse" alt="Activity">
13
+ <img src="https://img.shields.io/github/commit-activity/m/ImperialCollegeLondon/prefect-managedfiletransfer?color=0052FF&labelColor=090422" /></a>
14
+ <br>
15
+ </p>
16
+
17
+ Turn a prefect.io server into a managed file transfer solution. UI and Programatic creation of cron style jobs (aka Flows!) to upload and download files easily between servers. Support local, SFTP remotes plus any Cloud storage supported by rclone - so thats aws, azure, google, sharepoint, and [many more](https://rclone.org/overview/) out of the box.
18
+
19
+ Using prefect for managed file transfer means retries, logging, multi node and [high availability](https://docs.prefect.io/v3/advanced/self-hosted) come as standard - turning prefect into a reliable enterprise ready file transfer solution.
20
+
21
+ This package is not the fastest solution to move files around, but it prioritises reliability and ease of use, making it an excellent choice for replacing both quick cron job copy scripts and enterprise managed file transfer applicances.
22
+
23
+ Key features
24
+
25
+ - Copy and move files between almost any storage system easily.
26
+ - Reliable file moving with checksumming, file size checking etc.
27
+ - Smart and safe moving - settings to allow/block overwriting and to only copy files if they are new or changed.
28
+ - Unzip/Untar compressed folders after downloading them.
29
+ - Repath files as you move them.
30
+ - Complex filtering and ordering of files - by path, age, size etc. Pattern matching with regular expressions.
31
+ - Leverage Prefect.IO built in scheduling and orchestration capabilities:
32
+ - Transfer files on complex cron schedules
33
+ - notifications on success/failure - slack, email, etc
34
+ - Highly available server architecture - database server + multi-node workers and front ends.
35
+
36
+ Example use cases:
37
+
38
+ - Once per day SSH into my database server and copy the latest *.bkup file to a central storage location.
39
+ - Monitor a local network share directory for new files and automatically upload them to a cloud storage bucket.
40
+ - Schedule a weekly job to synchronize files between two remote servers.
41
+ - Move log files from a SSH available web server older than 30 days to a cold storage location.
42
+ - Copy file yyyy-MM-dd.zip from a remote server, where yyyy-MM-dd matches todays date, to a local directory and then unzip it.
43
+ - Download any file in an S3 bucket larger than 1GB and store it in a local directory.
44
+
45
+ ### Installation
46
+
47
+ Install `prefect-managedfiletransfer` with `pip`. (Requires an installation of Python 3.10+.)
48
+
49
+ ```bash
50
+ pip install prefect-managedfiletransfer
51
+ # or
52
+ uv add prefect-managedfiletransfer
53
+ ```
54
+
55
+ We recommend using a Python virtual environment manager such as uv, pipenv, conda or virtualenv.
56
+
57
+ In one (venv) terminal start a prefect server with logs enabled
58
+
59
+ ```bash
60
+ export PREFECT_LOGGING_LEVEL="INFO"
61
+ export PREFECT_LOGGING_EXTRA_LOGGERS="prefect_managedfiletransfer"
62
+ prefect server start
63
+ # OR uv run prefect server start
64
+ ```
65
+
66
+ There are many ways to manage infrastructure and code with prefect - here we demonstate starting a local worker:
67
+
68
+ ```bash
69
+ export PREFECT_API_URL=http://127.0.0.1:4200/api
70
+ # or perhaps export PREFECT_API_URL=http://host.docker.internal:4200/api
71
+ export PREFECT_LOGGING_EXTRA_LOGGERS="prefect_managedfiletransfer"
72
+ export PREFECT_LOGGING_LEVEL="INFO"
73
+ # [Optional] add all logs: export PREFECT_LOGGING_ROOT_LEVEL="INFO"
74
+
75
+
76
+ prefect worker start --pool 'default-pool' --type process
77
+ # OR prefect worker start --pool 'default-pool' --type docker
78
+
79
+ ```
80
+
81
+ Install the blocks using the prefect CLI
82
+
83
+ ```bash
84
+ prefect block register -m prefect_managedfiletransfer
85
+ ```
86
+
87
+ And then deploy the flows.
88
+
89
+ ```bash
90
+ # deploy the flows to run locally
91
+ python -m prefect_managedfiletransfer.deploy --local
92
+
93
+ # OR deploy to run with a docker image - see deploy.py
94
+ python -m prefect_managedfiletransfer.deploy --docker
95
+
96
+ # or a version of the above using uv run:
97
+ uv run python -m prefect_managedfiletransfer.deploy --local
98
+ uv run python -m prefect_managedfiletransfer.deploy --docker
99
+ ```
100
+
101
+ Visit the server UI http://localhost:4200.
102
+ 1. Create 2 blocks, one source and one destination
103
+ 2. On the deployments page start a `transfer_files_flow`. Configure your flow run to copy/move files between the 2 blocks.
104
+
105
+ ### Installation via docker
106
+
107
+ ```bash
108
+ # run prefect server in a container port-forwarded to your local machine’s 4200 port:
109
+ docker run -d -p 4200:4200 prefecthq/prefect:3-latest -- prefect server start --host 0.0.0.0
110
+ ```
111
+
112
+ ### List of components
113
+
114
+ Blocks
115
+ - ServerWithBasicAuthBlock - A block for connecting to a server using basic authentication.
116
+ - ServerWithPublicKeyAuthBlock - A block for connecting to a server using public key authentication.
117
+ - RCloneConfigFileBlock - A block for managing RClone configuration files.
118
+
119
+ Tasks
120
+ - list_remote_files_task - A task for listing files in a remote directory.
121
+ - download_file_task - A task for downloading a single file from a remote server.
122
+ - upload_file_task - A task for uploading a single file to a remote server.
123
+ - [TODO] delete_file_task
124
+
125
+ Flows
126
+ - transfer_files_flow - a fully featured flow for transferring files between different storage locations.
127
+ - upload_file_flow - a flow for uploading a file to a remote server. Supports pattern matching by date
128
+
129
+ ### Feedback
130
+
131
+ If you encounter any bugs while using `prefect-managedfiletransfer`, feel free to open an issue in the [prefect-managedfiletransfer](https://github.com/ImperialCollegeLondon/prefect-managedfiletransfer) repository.
132
+
133
+
134
+ Feel free to star or watch [`prefect-managedfiletransfer`](https://github.com/ImperialCollegeLondon/prefect-managedfiletransfer) for updates too!
135
+
136
+ ### Contributing
137
+
138
+ If you'd like to help contribute to fix an issue or add a feature to `prefect-managedfiletransfer`, please [propose changes through a pull request from a fork of the repository](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request-from-a-fork).
139
+
140
+ Here are the steps:
141
+
142
+ 1. [Fork the repository](https://docs.github.com/en/get-started/quickstart/fork-a-repo#forking-a-repository)
143
+ 2. [Clone the forked repository](https://docs.github.com/en/get-started/quickstart/fork-a-repo#cloning-your-forked-repository)
144
+ 3. Install the repository and its dependencies:
145
+ ```
146
+ # install uv first, then
147
+ uv sync
148
+ ```
149
+
150
+ You can also access all the prefect CLI tooling inside a uv managed venv
151
+ ```
152
+ uv venv
153
+ source .venv/bin/activate
154
+ prefect server start
155
+ ```
156
+
157
+ 4. Make desired changes
158
+ 5. Add tests
159
+ 6. Insert an entry to [CHANGELOG.md](https://github.com/ImperialCollegeLondon/prefect-managedfiletransfer/blob/main/CHANGELOG.md)
160
+ 7. Install `pre-commit` to perform quality checks prior to commit:
161
+ ```
162
+ pre-commit install
163
+ ```
164
+ 8. use the build script to run all the checks and tests:
165
+
166
+ ```
167
+ ./build.sh
168
+ ```
169
+ 8. `git commit`, `git push`, and create a pull request
@@ -0,0 +1,40 @@
1
+ from datetime import datetime
2
+ from pathlib import Path
3
+
4
+
5
+ class AssetDownloadResult:
6
+ """
7
+ Represents the result of an asset download operation.
8
+ """
9
+
10
+ def __init__(
11
+ self,
12
+ success: bool,
13
+ file_path: Path | None,
14
+ download_skipped: bool = False,
15
+ last_modified: datetime | None = None,
16
+ size: int = 0,
17
+ error: str | None = None,
18
+ ):
19
+ """
20
+ Represents the result of an asset download operation.
21
+ :param success: True if the download was successful, False otherwise.
22
+ :param file_path: The path to the downloaded file, or None if the download failed.
23
+ :param download_skipped: True if the download was skipped because the file was not newer than the destination file.
24
+ :param last_modified: The last modified time of the file, if available.
25
+ """
26
+ self.last_modified = last_modified
27
+ self.success = success
28
+ self.file_path = file_path
29
+ self.download_skipped = download_skipped
30
+ self.error = error
31
+ self.size = size
32
+
33
+ if not success and file_path is not None:
34
+ raise ValueError("If success is False, file_path must be None")
35
+
36
+ def __repr__(self):
37
+ if self.error:
38
+ return f"AssetDownloadResult(success={self.success}, error={self.error})"
39
+
40
+ return f"AssetDownloadResult(success={self.success}, file_path={self.file_path}, download_skipped={self.download_skipped}, last_modified={self.last_modified})"
@@ -0,0 +1,41 @@
1
+ from datetime import timedelta
2
+ from pydantic import BaseModel, Field
3
+ from prefect_managedfiletransfer.SortFilesBy import SortFilesBy
4
+
5
+ from pathlib import Path
6
+
7
+
8
+ class FileMatcher(BaseModel):
9
+ """
10
+ Represents a file matcher with a source path and a pattern to match files.
11
+ This is used to find files in a directory that match a specific pattern.
12
+ """
13
+
14
+ source_folder: Path = Field(
15
+ default=Path("."),
16
+ description="Path to the source directory to look for files.",
17
+ )
18
+ pattern_to_match: str = Field(
19
+ default="*",
20
+ description="Pattern to match files in the source directory. Supports glob patterns like '*.txt' or 'file_*.csv'.",
21
+ )
22
+ minimum_age: str | int | timedelta | None = Field(
23
+ default=None,
24
+ description="Only transfer files older than this in secs (or other time with suffix s|m|h|d|w|month|year). Default off.",
25
+ )
26
+ maximum_age: str | int | timedelta | None = Field(
27
+ default=None,
28
+ description="Only transfer files newer than this in secs (or other time with suffix s|m|h|d|w|month|year). Default off.",
29
+ )
30
+ sort: SortFilesBy = Field(
31
+ default=SortFilesBy.PATH_ASC,
32
+ description="Sort files by a specific attribute. Default is PATH_ASC.",
33
+ )
34
+ skip: int = Field(
35
+ default=0,
36
+ description="Number of files to skip in the sorted list. Default is 0.",
37
+ )
38
+ take: int | None = Field(
39
+ default=None,
40
+ description="Number of files to take from the sorted list. If None, all files are taken. Default is None.",
41
+ )