Merge pull request #68 from databio/dev

Updated bedbase docs
databio · Apr 15, 2024 · 94ba0d4 · 94ba0d4
2 parents 990a110 + 140691f
commit 94ba0d4
Show file tree

Hide file tree

Showing 41 changed files with 627 additions and 41,199 deletions.
diff --git a/autodoc.py b/autodoc.py
@@ -99,4 +99,4 @@
             with open(out, "w") as stream:
                 stream.write(md_result)
 else:
-    print("Skipping jupyter notebooks")
+    print("Skipping jupyter notebooks")
diff --git a/ci/scripts/count_records.py b/ci/scripts/count_records.py
@@ -7,15 +7,26 @@
 
 parser = ArgumentParser(description="Count records in a PostgreSQL table and verify")
 
-parser.add_argument("-t", "--table", help="Table to count records in", 
-	required=True, type=str)
-parser.add_argument("-e", "--expected-count", help="Expected number of records", 
-	type=int, required=False, default=None)
+parser.add_argument(
+    "-t", "--table", help="Table to count records in", required=True, type=str
+)
+parser.add_argument(
+    "-e",
+    "--expected-count",
+    help="Expected number of records",
+    type=int,
+    required=False,
+    default=None,
+)
 
 args = parser.parse_args()
 
-bbc = BedBaseConf(get_bedbase_cfg('$GITHUB_WORKSPACE/ci/cfg/config_min.yaml'))
+bbc = BedBaseConf(get_bedbase_cfg("$GITHUB_WORKSPACE/ci/cfg/config_min.yaml"))
 row_count = bbc._count_rows(table_name=args.table)
 if args.expected_count:
-	assert row_count == args.expected_count, "Number of records in the '{}' table ({}) not equal {}".format(args.table, row_count, args.expected_count)
+    assert (
+        row_count == args.expected_count
+    ), "Number of records in the '{}' table ({}) not equal {}".format(
+        args.table, row_count, args.expected_count
+    )
 sys.exit(0)
diff --git a/docs/bbconf/README.md b/docs/bbconf/README.md
@@ -1,3 +1,36 @@
-# bbconf
+<h1 align="center">bbconf</h1>
+
+![Run pytests](https://github.com/databio/bbconf/workflows/Run%20pytests/badge.svg)
+[![pypi-badge](https://img.shields.io/pypi/v/bbconf?color=%2334D058)](https://pypi.org/project/bbconf/)
+[![pypi-version](https://img.shields.io/pypi/pyversions/bbconf.svg?color=%2334D058)](https://pypi.org/project/bbconf)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![Github badge](https://img.shields.io/badge/source-github-354a75?logo=github)](https://github.com/databio/bbconf)
+[![coverage](https://coverage-badge.samuelcolvin.workers.dev/databio/bbconf.svg)](https://coverage-badge.samuelcolvin.workers.dev/redirect/databio/bbconf)
+
+
+*BEDBASE* project configuration package (agent)
+
+## What is this?
+
+`bbconf` is a configuration and management tool for BEDbase, facilitating the reading of configuration files, 
+setting up connections to PostgreSQL, PEPhub, S3, and Qdrant databases, managing file paths, and storing transformer models. 
+It formalizes communication pathways for pipelines and downstream tools, ensuring seamless interaction."
+
+---
+
+**Documentation**: <a href="https://docs.bedbase.org/bedboss" target="_blank">https://docs.bedbase.org/bedboss</a>
+
+**Source Code**: <a href="https://github.com/databio/bbconf" target="_blank">https://github.com/databio/bbconf</a>
+
+---
+
+## Installation
+To install `bbclient` use this command: 
+```
+pip install bbclient
+```
+or install the latest version from the GitHub repository:
+```
+pip install git+https://github.com/databio/bbconf.git
+```
 
-`bbconf` defines `BedBaseConf` class which is an in-memory representation of the configuration file for the *BEDBASE* project. This is the source of the project-wide constant variables. Additionally it implements multiple convenience methods for interacting with the database backend, i.e. [PostgreSQL](https://www.postgresql.org/)
diff --git a/docs/bbconf/bbc_api.md b/docs/bbconf/bbc_api.md
@@ -1,191 +1 @@
-Final targets: BedBaseConf, get_bedbase_cfg
-<script>
-document.addEventListener('DOMContentLoaded', (event) => {
-  document.querySelectorAll('h3 code').forEach((block) => {
-    hljs.highlightBlock(block);
-  });
-});
-</script>
-
-<style>
-h3 .content { 
-    padding-left: 22px;
-    text-indent: -15px;
- }
-h3 .hljs .content {
-    padding-left: 20px;
-    margin-left: 0px;
-    text-indent: -15px;
-    martin-bottom: 0px;
-}
-h4 .content, table .content, p .content, li .content { margin-left: 30px; }
-h4 .content { 
-    font-style: italic;
-    font-size: 1em;
-    margin-bottom: 0px;
-}
-
-</style>
-
-
-# Package `bbconf` Documentation
-
-## <a name="BedBaseConf"></a> Class `BedBaseConf`
-This class standardizes reporting of bedstat and bedbuncher results. It formalizes a way for these pipelines and downstream tools to communicate -- the produced results can easily and reliably become an input for the server. The object exposes API for interacting with the results and is backed by a [PostgreSQL](https://www.postgresql.org/) database.
-
-
-```python
-def __init__(self, config_path=None, database_only=False)
-```
-
-Initialize the object
-#### Parameters:
-
-- `config_path` (`str`):  path to the bedbase configuration file
-- `database_only` (`bool`):  whether the database managers should notkeep an in-memory copy of the data in the database
-
-
-
-
-```python
-def bed(self)
-```
-
-PipestatManager of the bedfiles table
-#### Returns:
-
-- `pipestat.PipestatManager`:  manager of the bedfiles table
-
-
-
-
-```python
-def bedset(self)
-```
-
-PipestatManager of the bedsets table
-#### Returns:
-
-- `pipestat.PipestatManager`:  manager of the bedsets table
-
-
-
-
-```python
-def config(self)
-```
-
-Config used to initialize the object
-#### Returns:
-
-- `yacman.YacAttMap`:  bedbase configuration file contents
-
-
-
-
-```python
-def get_bedbuncher_output_path(self, remote=False)
-```
-
-Get path to the output of the bedbuncher pipeline
-#### Parameters:
-
-- `remote` (`bool`):  whether to use remote url base
-
-
-#### Returns:
-
-- `str`:  path to the bedbuncher pipeline output
-
-
-
-
-```python
-def get_bedstat_output_path(self, remote=False)
-```
-
-Get path to the output of the bedstat pipeline
-#### Parameters:
-
-- `remote` (`bool`):  whether to use remote url base
-
-
-#### Returns:
-
-- `str`:  path to the bedstat pipeline output
-
-
-
-
-```python
-def remove_relationship(self, bedset_id, bedfile_ids=None)
-```
-
-Remove entries from the relationships table
-#### Parameters:
-
-- `bedset_id` (`str`):  id of the bedset to remove
-- `bedfile_ids` (`list[str]`):  ids of the bedfiles to remove for theselected bedset. If none provided, all the relationsips for the selected bedset will be removed.
-
-
-
-
-```python
-def report_relationship(self, bedset_id, bedfile_id)
-```
-
-Report a bedfile for bedset.
-
-Inserts the ID pair into the relationship table, which allows to
-manage many to many bedfile bedset relationships
-#### Parameters:
-
-- `bedset_id` (`int`):  id of the bedset to report bedfile for
-- `bedfile_id` (`int`):  id of the bedfile to report
-
-
-
-
-```python
-def select_bedfiles_for_bedset(self, condition=None, condition_val=None, bedfile_col=None)
-```
-
-Select bedfiles that are part of a bedset that matches the query
-#### Parameters:
-
-- `condition` (`str`):  bedsets table query to restrict the results with,for instance `"id=%s"`
-- `condition_val` (`list[str]`):  values to populate the condition stringwith
-- `bedfile_col` (`list[str] | str`):  bedfile columns to include in theresult, if none specified all columns will be included
-
-
-#### Returns:
-
-- `list[psycopg2.extras.DictRow]`:  matched bedfiles table contents
-
-
-
-
-```python
-def get_bedbase_cfg(cfg=None)
-```
-
-Determine path to the bedbase configuration file
-
-The path can be either explicitly provided
-or read from a $BEDBASE environment variable
-#### Parameters:
-
-- `cfg` (`str`):  path to the config file.Optional, the $BEDBASE config env var will be used if not provided
-
-
-#### Returns:
-
-- `str`:  configuration file path
-
-
-
-
-
-
-
-*Version Information: `bbconf` v0.1.0, generated by `lucidoc` v0.4.3*
+### 🚧 Docs in progress! Stay tuned for updates. We're working hard to bring you valuable content soon!
diff --git a/docs/bbconf/changelog.md b/docs/bbconf/changelog.md
@@ -2,12 +2,45 @@
 
 This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html) and [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) format.
 
-## [0.4.0] - 2023-10-17
+# [0.5.1] - 2024-04-09
+## Changed
+
+- updated qdrant uploader
+- bedset bedfile list query improvement
+- other minor fixes in uploading
+
+# [0.5.0] - 2024-04-08
+### Changed
+
+- Rebuild bbconf
+- Introduced new DB schema
+- Added bbagent that will be used to interact with the database
+- Updated config schema
+- Added new functionality to the bbagent
+- New tests
+
+
+## [0.4.2] - 2024-03-12
+### Change
+- Updated logger
+- Updated requirements
+- Added `upload_status` column to the `bedfile` table
+
+
+## [0.4.1] - 2024-01-01
+### Fix
+- Requirements
+
+
+## [0.4.0] - 2023-12-18
 ### Change
-- bbconf to use pipestat v0.4.1 and SQLModel
-- Added qdrant search, and insert methods
+- bbconf to use pipestat v0.6.0 and SQLModel
 - Fixed tests
 
+### Added
+- `qdrant` search, insert and update functionality
+- functions that return results in the DRS format for both bed and bedhost. [DRS](https://ga4gh.github.io/data-repository-service-schemas/preview/release/drs-1.2.0/docs/)
+
 ## [0.3.0] - 2022-08-18
 ### Change
 - update select_bedfiles_for_distance