dataplaybook 0.0.0__tar.gz

dataplaybook-0.0.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

dataplaybook-0.0.0/PKG-INFO

@@ -0,0 +1,170 @@
+Metadata-Version: 2.3
+Name: dataplaybook
+Version: 0.0.0
+Summary: Playbooks for data. Open, process and save table based data.
+License: Apache-2.0
+Keywords: data,tables,excel,mongodb,generators
+Author: Johann Kellerman
+Author-email: kellerza@gmail.com
+Requires-Python: >3.10
+Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Provides-Extra: all
+Provides-Extra: lxml
+Provides-Extra: mongodb
+Requires-Dist: O365 (>=1.0.4,<2) ; extra == "all"
+Requires-Dist: attrs (>24)
+Requires-Dist: colordict (>=1.2.6,<2.0.0)
+Requires-Dist: colorlog
+Requires-Dist: fuzzywuzzy
+Requires-Dist: icecream
+Requires-Dist: jinja2 (>=3,<4)
+Requires-Dist: lxml (>=5.3.0,<6.0.0) ; extra == "lxml" or extra == "all"
+Requires-Dist: openpyxl (>=3,<4)
+Requires-Dist: pymongo ; extra == "mongodb" or extra == "all"
+Requires-Dist: python-Levenshtein
+Requires-Dist: python-pptx ; extra == "all"
+Requires-Dist: requests (>=2.0.0)
+Requires-Dist: typeguard (>=2,<3)
+Requires-Dist: typing-extensions
+Requires-Dist: voluptuous (>=0.11.5)
+Project-URL: Repository, https://github.com/kellerza/data-playbook
+Description-Content-Type: text/markdown
+
+# Data Playbook
+
+:book: Playbooks for data. Open, process and save table based data.
+[![Workflow Status](https://github.com/kellerza/data-playbook/actions/workflows/main.yml/badge.svg?branch=master)](https://github.com/kellerza/data-playbook/actions)
+[![codecov](https://codecov.io/gh/kellerza/data-playbook/branch/master/graph/badge.svg)](https://codecov.io/gh/kellerza/data-playbook)
+
+Automate repetitive tasks on table based data. Include various input and output tasks.
+
+Install: `pip install dataplaybook`
+
+Use the `@task` and `@playbook` decorators
+
+```python
+from dataplaybook import task, playbook
+from dataplaybook.tasks.io_xlsx
+
+@task
+def print
+```
+
+## Tasks
+
+Tasks are implemented as simple Python functions and the modules can be found in the dataplaybook/tasks folder.
+
+| Module                                                                                     | Functions                                                                                      |
+| :----------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------- |
+| Generic function to work on tables<br>`dataplaybook.tasks`                                 | build_lookup, build_lookup_var, combine, drop, extend, filter, print, replace, unique, vlookup |
+| Fuzzy string matching <br>`dataplaybook.taksk.fuzzy`<br> Requires _pip install fuzzywuzzy_ |                                                                                                |
+| Read/write excel files ()<br>`dataplaybook.tasks.io_xlsx`                                  | read_excel, write_excel                                                                        |
+| Misc IO tasks<br>`dataplaybook.tasks.io_misc`                                              | read_csv, read_tab_delim, read_text_regex, wget, write_csv                                     |
+| MongoDB functions<br>`dataplaybook.tasks.io_mongo`                                         | read_mongo, write_mongo, columns_to_list, list_to_columns                                      |
+| PDF functions. Requires _pdftotext_ on your path<br>`dataplaybook.tasks.io_pdf`            | read_pdf_pages, read_pdf_files                                                                 |
+| Read XML<br>`dataplaybook.tasks.io_xml`                                                    | read_xml                                                                                       |
+
+```bash
+$ dataplaybook --all -vvv
+dataplaybook.tasks
+- build_lookup "(table: list[RowData], key: str, columns: list[str]) -> RowDataGen"
+- build_lookup_dict "(table: list[RowData], key: str | list[str], columns: list[str] | None = None) -> dict[str | tuple, Any]"
+- combine "(tables: list[list[RowData]], key: str, columns: list[str], value: Union[Literal[True], str] = True) -> list[RowData]"
+- ensure_lists "(tables: Sequence[list[RowData]], columns: Sequence[str]) -> None"
+- filter_rows "(table: list[RowData], include: dict[str, str] | None = None, exclude: dict[str, str] | None = None) -> RowDataGen"
+- print_table "(*, table: list[RowData] | None = None, tables: dict[str, list[RowData]] | None = None) -> None"
+- remove_null "(tables: Sequence[list[RowData]]) -> None"
+- replace "(table: list[RowData], replace_dict: dict[str, str], columns: list[str]) -> None"
+- unique "(table: list[RowData], key: str) -> RowDataGen"
+- vlookup "(table0: list[RowData], acro: list[RowData], columns: list[str]) -> None"
+dataplaybook.tasks.fuzzy
+- fuzzy_match "(table1: list[RowData], table2: list[RowData], t1_column: str, t2_column: str, t1_target_column: str) -> None"
+dataplaybook.tasks.ietf
+- add_standards_column "(table: list[RowData], columns: list[str], rfc_col: str) -> None"
+- extract_standards_from_table "(table: list[RowData], extract_columns: list[str], include_columns: list[str] | None = None, name: str = '', line_offset: int = 1) -> RowDataGen"
+dataplaybook.tasks.gis
+- linestring "(table: list[RowData], lat_a: str = 'latA', lat_b: str = 'latB', lon_a: str = 'lonA', lon_b: str = 'lonB', linestring_column: str = 'linestring', error: str = '22 -22') -> list[RowData]"
+dataplaybook.tasks.io_mail
+- mail "(to_addrs: list[str] | str, from_addr: str, subject: str, server: str, files: list[str] | None = None, priority: int = 4, body: str | None = '', html: str | None = '', cc_addrs: list[str] | None = None, bcc_addrs: list[str] | None = None) -> None"
+dataplaybook.tasks.io_misc
+- file_rotate "(file: str, count: int = 3) -> None"
+- glob "(patterns: list[str]) -> RowDataGen"
+- read_csv "(file: str, columns: dict[str, str] | None = None) -> RowDataGen"
+- read_json "(file: str) -> list[RowData]"
+- read_tab_delim "(file: str, headers: list[str]) -> RowDataGen"
+- read_text_regex "(filename: str, newline: Pattern, fields: Optional[Pattern]) -> RowDataGen"
+- wget "(url: str, file: str, age: int = 172800) -> None"
+- write_csv "(table: list[RowData], file: str, header: list[str] | None = None) -> None"
+- write_json "(data: dict[str, list[RowData]] | list[RowData], file: str, only_var: bool = False) -> None"
+dataplaybook.tasks.io_mongo
+- columns_to_list "(table: 'list[RowData]', *, list_column: 'str', columns: 'Columns') -> 'None'"
+- list_to_columns "(table: 'list[RowData]', *, list_column: 'str', columns: 'Columns') -> 'None'"
+- mongo_delete_sids "(*, mdb: 'MongoURI', sids: 'list[str]') -> 'None'"
+- mongo_list_sids "(mdb: 'MongoURI') -> 'list[str]'"
+- mongo_sync_sids "(*, mdb_local: 'MongoURI', mdb_remote: 'MongoURI', ignore_remote: 'Sequence[str] | None' = None, only_sync_sids: 'Sequence[str] | None' = None) -> 'None'"
+- read_mongo "(mdb: 'MongoURI', *, set_id: 'str | None' = None) -> 'RowDataGen'"
+- write_mongo "(table: 'list[RowData]', mdb: 'MongoURI', *, set_id: 'str | None' = None, force: 'bool' = False) -> 'None'"
+dataplaybook.tasks.io_pdf
+- read_pdf_files "(folder: str, pattern: str = '*.pdf', *, layout: bool = True, args: list[str] | None = None) -> RowDataGen"
+- read_pdf_pages "(filename: str, *, layout: bool = True, args: list[str] | None = None) -> RowDataGen"
+dataplaybook.tasks.io_xlsx
+- read_excel "(*, tables: dict[str, list[RowData]], file: str, sheets: list[RowData] | None = None) -> list[str]"
+- write_excel "(*, tables: dict[str, list[RowData]], file: str, include: list[str] | None = None, header: list[str] | None = None, headers: list[Any] | None = None, ensure_string: bool = False) -> None"
+dataplaybook.tasks.io_xml
+- read_xml "(tables: dict[str, list[RowData]], file: str, targets: list[str]) -> None"
+```
+
+## Local development
+
+Poetry is used for dependency management. Install poetry and run `poetry install` to install the dependencies.
+
+```bash
+poetry install -E all
+```
+
+pre-commit is used for code formatting and linting. Install pre-commit and run `pre-commit install` to install the git hooks.
+
+```bash
+pip install pre-commit && pre-commit install
+```
+
+Test locally using pre-commit (ruff, codespell, mypy & pylint)
+
+```bash
+git add . && pre-commit run --all
+poetry run pylint dataplaybook tests
+```
+
+## Data Playbook v0 - origins
+
+Data playbooks was created to replace various snippets of code I had lying around. They were all created to ensure repeatability of some menial task, and generally followed a similar structure of load something, process it and save it. (Process network data into GIS tools, network audits & reporting on router & NMS output, Extract IETF standards to complete SOCs, read my bank statements into my Excel budgeting tool, etc.)
+
+For many of these tasks I have specific processing code (`tasks_x.py`, loaded with `modules: [tasks_x]` in the playbook), but in almost all cases input & output tasks (and configuring these names etc) are common. The idea of the modular tasks originally came from Home Assistant, where I started learning Python and the idea of "custom components" to add your own integrations, although one could argue this also has similarities to Ansible playbooks.
+
+In many cases I have a 'loose' coupling to actual file names, using Everything search (`!es search_pattern` in the playbook) to resolve a search pattern to the correct file used for input.
+
+It has some parts in common with Ansible Playbooks, especially the name was chosen after I was introduced to Ansible Playbooks. The task structure has been updated in 2019 to match the Ansible Playbooks 2.0/2.5+ format and allow names. This format will also be easier to introduce loop mechanisms etc.
+
+### Comparison to Ansible Playbooks
+
+Data playbooks is intended to create and modify variables in the environment (similar to **inventory**). Data playbooks starts with an empty environment (although you can read the environment from various sources inside the play).
+Although new variables can be created using **register:** in Ansible, data playbook functions requires the output to be captured through `target:`.
+
+Data playbook tasks are different form Ansible's **actions**:
+
+- They are mostly not idempotent, since the intention is to modify tables as we go along,
+- they can return lists containing rows or be Python iterators (that `yield` rows of a table)
+- if they dont return any tabular data (a list), the return value will be added to the `var` table in the environment
+- Each have a strict voluptuous schema, evaluated when loading and during runtime (e.g. to expand templates) to allow quick troubleshooting
+
+You could argue I can do this with Ansible, but it won't be as elegant with single item hosts files, `gather_facts: no` and `delegate_to: localhost` throughout the playbooks. It will likely only be half as much fun trying to force it into my way of thinking.
+

dataplaybook-0.0.0/README.md

@@ -0,0 +1,128 @@
+# Data Playbook
+
+:book: Playbooks for data. Open, process and save table based data.
+[![Workflow Status](https://github.com/kellerza/data-playbook/actions/workflows/main.yml/badge.svg?branch=master)](https://github.com/kellerza/data-playbook/actions)
+[![codecov](https://codecov.io/gh/kellerza/data-playbook/branch/master/graph/badge.svg)](https://codecov.io/gh/kellerza/data-playbook)
+
+Automate repetitive tasks on table based data. Include various input and output tasks.
+
+Install: `pip install dataplaybook`
+
+Use the `@task` and `@playbook` decorators
+
+```python
+from dataplaybook import task, playbook
+from dataplaybook.tasks.io_xlsx
+
+@task
+def print
+```
+
+## Tasks
+
+Tasks are implemented as simple Python functions and the modules can be found in the dataplaybook/tasks folder.
+
+| Module                                                                                     | Functions                                                                                      |
+| :----------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------- |
+| Generic function to work on tables<br>`dataplaybook.tasks`                                 | build_lookup, build_lookup_var, combine, drop, extend, filter, print, replace, unique, vlookup |
+| Fuzzy string matching <br>`dataplaybook.taksk.fuzzy`<br> Requires _pip install fuzzywuzzy_ |                                                                                                |
+| Read/write excel files ()<br>`dataplaybook.tasks.io_xlsx`                                  | read_excel, write_excel                                                                        |
+| Misc IO tasks<br>`dataplaybook.tasks.io_misc`                                              | read_csv, read_tab_delim, read_text_regex, wget, write_csv                                     |
+| MongoDB functions<br>`dataplaybook.tasks.io_mongo`                                         | read_mongo, write_mongo, columns_to_list, list_to_columns                                      |
+| PDF functions. Requires _pdftotext_ on your path<br>`dataplaybook.tasks.io_pdf`            | read_pdf_pages, read_pdf_files                                                                 |
+| Read XML<br>`dataplaybook.tasks.io_xml`                                                    | read_xml                                                                                       |
+
+```bash
+$ dataplaybook --all -vvv
+dataplaybook.tasks
+- build_lookup "(table: list[RowData], key: str, columns: list[str]) -> RowDataGen"
+- build_lookup_dict "(table: list[RowData], key: str | list[str], columns: list[str] | None = None) -> dict[str | tuple, Any]"
+- combine "(tables: list[list[RowData]], key: str, columns: list[str], value: Union[Literal[True], str] = True) -> list[RowData]"
+- ensure_lists "(tables: Sequence[list[RowData]], columns: Sequence[str]) -> None"
+- filter_rows "(table: list[RowData], include: dict[str, str] | None = None, exclude: dict[str, str] | None = None) -> RowDataGen"
+- print_table "(*, table: list[RowData] | None = None, tables: dict[str, list[RowData]] | None = None) -> None"
+- remove_null "(tables: Sequence[list[RowData]]) -> None"
+- replace "(table: list[RowData], replace_dict: dict[str, str], columns: list[str]) -> None"
+- unique "(table: list[RowData], key: str) -> RowDataGen"
+- vlookup "(table0: list[RowData], acro: list[RowData], columns: list[str]) -> None"
+dataplaybook.tasks.fuzzy
+- fuzzy_match "(table1: list[RowData], table2: list[RowData], t1_column: str, t2_column: str, t1_target_column: str) -> None"
+dataplaybook.tasks.ietf
+- add_standards_column "(table: list[RowData], columns: list[str], rfc_col: str) -> None"
+- extract_standards_from_table "(table: list[RowData], extract_columns: list[str], include_columns: list[str] | None = None, name: str = '', line_offset: int = 1) -> RowDataGen"
+dataplaybook.tasks.gis
+- linestring "(table: list[RowData], lat_a: str = 'latA', lat_b: str = 'latB', lon_a: str = 'lonA', lon_b: str = 'lonB', linestring_column: str = 'linestring', error: str = '22 -22') -> list[RowData]"
+dataplaybook.tasks.io_mail
+- mail "(to_addrs: list[str] | str, from_addr: str, subject: str, server: str, files: list[str] | None = None, priority: int = 4, body: str | None = '', html: str | None = '', cc_addrs: list[str] | None = None, bcc_addrs: list[str] | None = None) -> None"
+dataplaybook.tasks.io_misc
+- file_rotate "(file: str, count: int = 3) -> None"
+- glob "(patterns: list[str]) -> RowDataGen"
+- read_csv "(file: str, columns: dict[str, str] | None = None) -> RowDataGen"
+- read_json "(file: str) -> list[RowData]"
+- read_tab_delim "(file: str, headers: list[str]) -> RowDataGen"
+- read_text_regex "(filename: str, newline: Pattern, fields: Optional[Pattern]) -> RowDataGen"
+- wget "(url: str, file: str, age: int = 172800) -> None"
+- write_csv "(table: list[RowData], file: str, header: list[str] | None = None) -> None"
+- write_json "(data: dict[str, list[RowData]] | list[RowData], file: str, only_var: bool = False) -> None"
+dataplaybook.tasks.io_mongo
+- columns_to_list "(table: 'list[RowData]', *, list_column: 'str', columns: 'Columns') -> 'None'"
+- list_to_columns "(table: 'list[RowData]', *, list_column: 'str', columns: 'Columns') -> 'None'"
+- mongo_delete_sids "(*, mdb: 'MongoURI', sids: 'list[str]') -> 'None'"
+- mongo_list_sids "(mdb: 'MongoURI') -> 'list[str]'"
+- mongo_sync_sids "(*, mdb_local: 'MongoURI', mdb_remote: 'MongoURI', ignore_remote: 'Sequence[str] | None' = None, only_sync_sids: 'Sequence[str] | None' = None) -> 'None'"
+- read_mongo "(mdb: 'MongoURI', *, set_id: 'str | None' = None) -> 'RowDataGen'"
+- write_mongo "(table: 'list[RowData]', mdb: 'MongoURI', *, set_id: 'str | None' = None, force: 'bool' = False) -> 'None'"
+dataplaybook.tasks.io_pdf
+- read_pdf_files "(folder: str, pattern: str = '*.pdf', *, layout: bool = True, args: list[str] | None = None) -> RowDataGen"
+- read_pdf_pages "(filename: str, *, layout: bool = True, args: list[str] | None = None) -> RowDataGen"
+dataplaybook.tasks.io_xlsx
+- read_excel "(*, tables: dict[str, list[RowData]], file: str, sheets: list[RowData] | None = None) -> list[str]"
+- write_excel "(*, tables: dict[str, list[RowData]], file: str, include: list[str] | None = None, header: list[str] | None = None, headers: list[Any] | None = None, ensure_string: bool = False) -> None"
+dataplaybook.tasks.io_xml
+- read_xml "(tables: dict[str, list[RowData]], file: str, targets: list[str]) -> None"
+```
+
+## Local development
+
+Poetry is used for dependency management. Install poetry and run `poetry install` to install the dependencies.
+
+```bash
+poetry install -E all
+```
+
+pre-commit is used for code formatting and linting. Install pre-commit and run `pre-commit install` to install the git hooks.
+
+```bash
+pip install pre-commit && pre-commit install
+```
+
+Test locally using pre-commit (ruff, codespell, mypy & pylint)
+
+```bash
+git add . && pre-commit run --all
+poetry run pylint dataplaybook tests
+```
+
+## Data Playbook v0 - origins
+
+Data playbooks was created to replace various snippets of code I had lying around. They were all created to ensure repeatability of some menial task, and generally followed a similar structure of load something, process it and save it. (Process network data into GIS tools, network audits & reporting on router & NMS output, Extract IETF standards to complete SOCs, read my bank statements into my Excel budgeting tool, etc.)
+
+For many of these tasks I have specific processing code (`tasks_x.py`, loaded with `modules: [tasks_x]` in the playbook), but in almost all cases input & output tasks (and configuring these names etc) are common. The idea of the modular tasks originally came from Home Assistant, where I started learning Python and the idea of "custom components" to add your own integrations, although one could argue this also has similarities to Ansible playbooks.
+
+In many cases I have a 'loose' coupling to actual file names, using Everything search (`!es search_pattern` in the playbook) to resolve a search pattern to the correct file used for input.
+
+It has some parts in common with Ansible Playbooks, especially the name was chosen after I was introduced to Ansible Playbooks. The task structure has been updated in 2019 to match the Ansible Playbooks 2.0/2.5+ format and allow names. This format will also be easier to introduce loop mechanisms etc.
+
+### Comparison to Ansible Playbooks
+
+Data playbooks is intended to create and modify variables in the environment (similar to **inventory**). Data playbooks starts with an empty environment (although you can read the environment from various sources inside the play).
+Although new variables can be created using **register:** in Ansible, data playbook functions requires the output to be captured through `target:`.
+
+Data playbook tasks are different form Ansible's **actions**:
+
+- They are mostly not idempotent, since the intention is to modify tables as we go along,
+- they can return lists containing rows or be Python iterators (that `yield` rows of a table)
+- if they dont return any tabular data (a list), the return value will be added to the `var` table in the environment
+- Each have a strict voluptuous schema, evaluated when loading and during runtime (e.g. to expand templates) to allow quick troubleshooting
+
+You could argue I can do this with Ansible, but it won't be as elegant with single item hosts files, `gather_facts: no` and `delegate_to: localhost` throughout the playbooks. It will likely only be half as much fun trying to force it into my way of thinking.

dataplaybook-0.0.0/dataplaybook/__init__.py

@@ -0,0 +1,13 @@
+"""DataPlayook init class."""
+
+# ruff: noqa
+from dataplaybook.const import (
+    Column,
+    Columns,
+    RowDataGen,
+    Tables,
+    DataEnvironment,
+    RowData,
+)
+from dataplaybook.main import _ENV as ENV
+from dataplaybook.main import playbook, task, task_validate

dataplaybook-0.0.0/dataplaybook/__main__.py

@@ -0,0 +1,14 @@
+"""Dataplaybook script."""
+
+import sys
+
+from dataplaybook.main import run_playbooks
+
+
+def main() -> int:
+    """Execute a playbook."""
+    sys.exit(run_playbooks(dataplaybook_cmd=True))
+
+
+if __name__ == "__main__":
+    main()

dataplaybook-0.0.0/dataplaybook/config_validation.py

@@ -0,0 +1,35 @@
+"""Data validation helpers for voluptuous."""
+
+import logging
+from typing import Any, Callable
+
+import voluptuous as vol
+
+_LOGGER = logging.getLogger(__name__)
+_LOGGER.setLevel(logging.INFO)
+
+
+def endswith(parts: str) -> Callable[[Any], Any]:
+    """Ensure a string ends with specified part."""
+
+    def _check(_str: str) -> str:
+        """Return the validator."""
+        if _str.endswith(parts):
+            return _str
+        raise vol.Invalid(f"{_str} does not end with {parts}")
+
+    return _check
+
+
+def ensure_tables(value: Any) -> Any:
+    """Ensure you have a dict of tables."""
+    if not isinstance(value, dict):
+        raise vol.Invalid("tables need to be a dict")
+    for key, val in value.items():
+        if key == "var":
+            continue
+        if not isinstance(val, list):
+            raise vol.Invalid(
+                f"tables need to contain lists {key} contains {type(val)}"
+            )
+    return value

dataplaybook-0.0.0/dataplaybook/const.py

@@ -0,0 +1,23 @@
+"""Constants."""
+
+from __future__ import annotations
+import typing
+
+# pylint: disable=unused-import
+from dataplaybook.helpers.env import DataEnvironment  # noqa: F401
+
+VERSION = "1.0.25"
+
+Columns = list[str]
+Column = str
+RowData = dict[str, typing.Any]
+RowDataGen = typing.Generator[RowData, None, None]
+Tables = dict[str, list[RowData]] | DataEnvironment
+
+
+# @attrs.define(slots=True)
+# class Result(list[dict[str, typing.Any]]):
+#     """A table/list with some metadata."""
+
+#     name: str = attrs.field(default="")
+#     headers: int = 0

dataplaybook-0.0.0/dataplaybook/everything/__init__.py

@@ -0,0 +1,55 @@
+r"""Search for files using Everything from voidtools.
+
+Everything HTTP Example:
+    http://localhost:8881/?s=zz%20xls&j=1&path_column=1
+        { "totalResults":25, "results":[ { "type":"file",
+        "name":"filename.xlsx", "path":"C:\\...." }
+"""
+
+from collections import namedtuple
+from pathlib import Path
+from typing import Callable
+
+import requests
+
+SANE = r" !c:\windows !appdata\ !\.git !\.vscode !_old\ !.lnk !~$ !C:\program !c:\$R"
+SERVER = "http://localhost:8881"
+
+Result = namedtuple("Result", ["total", "files", "folders"])
+PathT = namedtuple("PathT", ["path", "name"])
+
+
+def _everything_result(json: dict, class_: Callable) -> Result:
+    """Everything's return value."""
+    result = {"total": -1, "files": [], "folders": []}
+    result["total"] = json["totalResults"]
+    for itm in json["results"]:
+        try:
+            lst = result[itm["type"] + "s"]
+            if isinstance(lst, list):
+                lst.append(class_(itm["path"], itm.get("name", "")))
+        except KeyError as err:
+            print(err)
+    return Result(**result)
+
+
+def search(
+    *terms: str,
+    params: dict | None = None,
+    sane: bool = True,
+    sort: bool = True,
+    max_results: int = 50,
+    class_: Callable = Path,
+) -> Result:
+    """Search for files."""
+    params = dict(
+        {"s": " ".join(terms), "path_column": 1, "json": 1, "count": max_results},
+        **(params or {}),
+    )
+    if sane:
+        params["s"] += SANE
+    if sort:
+        params["sort"] = "date_modified"
+        params["ascending"] = 0
+    res = requests.get(SERVER, params=params, timeout=15)
+    return _everything_result(res.json(), class_)