Fix Docker runtime issues, add CI checks, and refactor eFP schemas

.flake8

@@ -1,16 +1,12 @@
 [flake8]
-max-line-length = 120
-extend-ignore = E203, W503, E501
+ignore = E501, E203, E121, E123, E126, W503, W504
 exclude =
     .git,
-    __pycache__,
-    docs/source/conf.py,
-    old,
-    build,
-    dist,
-    venv,
-    env,
     .venv,
-    ./venv-docs,
+    __pycache__,
+    api/Archive,
+    data,
     docs,
-    .env
+    instance,
+    output,
+    venv

.github/workflows/bar-api.yml

@@ -12,6 +12,7 @@ jobs:
 
     runs-on: ubuntu-24.04
     strategy:
+      fail-fast: false
       matrix:
         python-version: [3.10.18, 3.11, 3.12, 3.13]
 

.github/workflows/codeql.yml

@@ -29,16 +29,16 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v2
+      uses: github/codeql-action/init@v3
       with:
         languages: ${{ matrix.language }}
 
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@v2
+      uses: github/codeql-action/autobuild@v3
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v2
+      uses: github/codeql-action/analyze@v3
       with:
         category: "/language:${{matrix.language}}"

.gitignore

@@ -141,3 +141,6 @@ dmypy.json
 output/*
 !output
 !output/placeholder.txt
+
+# Local sqlite mirrors generated from MySQL dumps
+config/databases/*.db

README.md

@@ -4,4 +4,4 @@
 
 [![Website Status](https://img.shields.io/website?url=http%3A%2F%2Fbar.utoronto.ca%2Fapi%2F)](http://bar.utoronto.ca/api/) ![GitHub repo size](https://img.shields.io/github/repo-size/BioAnalyticResource/BAR_API) [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black) [![Documentation Status](https://readthedocs.org/projects/bar-api/badge/?version=latest)](https://bar-api.readthedocs.io/en/latest/?badge=latest)
 
-This is the official repository for the Bio-Analytic Resource API. The API documentation can be found [here](https://bar-api.readthedocs.io/en/latest/).
+This is the official repository for the Bio-Analytic Resource API. The API documentation can be found [here](https://bar-api.readthedocs.io/en/latest/).

api/__init__.py

@@ -64,6 +64,7 @@ def create_app():
     from api.resources.efp_image import efp_image
     from api.resources.fastpheno import fastpheno
     from api.resources.llama3 import llama3
+    from api.resources.efp_proxy import efp_proxy_ns
 
     bar_api.add_namespace(gene_information)
     bar_api.add_namespace(rnaseq_gene_expression)
@@ -78,6 +79,7 @@ def create_app():
     bar_api.add_namespace(efp_image)
     bar_api.add_namespace(fastpheno)
     bar_api.add_namespace(llama3)
+    bar_api.add_namespace(efp_proxy_ns)
     bar_api.init_app(bar_app)
     return bar_app
 

api/models/bar_utils.py

@@ -0,0 +1,4 @@
+# Bridge file to maintain backward compatibility with imports
+from api.utils.bar_utils import BARUtils
+
+__all__ = ['BARUtils']

api/models/efp_dynamic.py

@@ -0,0 +1,88 @@
+"""
+Dynamic SQLAlchemy model generation for simple eFP databases.
+
+This module provides runtime generation of SQLAlchemy ORM models from schema
+definitions, enabling dynamic database access without hardcoded model classes.
+"""
+
+from __future__ import annotations
+
+from typing import Dict
+
+from sqlalchemy import Float, Integer, String, Text
+from sqlalchemy.dialects.mysql import INTEGER
+
+from api import db
+from api.models.efp_schemas import SIMPLE_EFP_DATABASE_SCHEMAS
+
+
+def _to_sqla_type(column_spec):
+    """
+    Map a column specification dictionary to a SQLAlchemy column type.
+
+    Converts the simple type descriptors used in schema definitions to the
+    appropriate SQLAlchemy type objects for ORM model generation.
+
+    :param column_spec: Column specification with 'type', 'length', and 'unsigned' keys
+    :type column_spec: Dict[str, Any]
+    :return: SQLAlchemy column type (String, Integer, Float, or Text)
+    :rtype: sqlalchemy.types.TypeEngine
+    :raises ValueError: If column type is not one of: string, integer, float, text
+
+    Example::
+
+        col_spec = {"type": "string", "length": 24}
+        sqla_type = _to_sqla_type(col_spec)  # Returns String(24)
+    """
+    col_type = column_spec.get("type")
+    if col_type == "string":
+        return String(column_spec["length"])
+    if col_type == "integer":
+        if column_spec.get("unsigned"):
+            return INTEGER(unsigned=True)
+        return Integer
+    if col_type == "float":
+        return Float
+    if col_type == "text":
+        return Text
+    raise ValueError(f"Unsupported column type: {col_type}")
+
+
+def _generate_model(bind_key: str, spec) -> db.Model:
+    """
+    Build a concrete SQLAlchemy model class for the given schema specification.
+
+    Dynamically creates an ORM model with the specified table name, bind key,
+    and columns based on the schema definition. The generated model class can
+    be used like any Flask-SQLAlchemy model.
+
+    :param bind_key: Database bind key (e.g., 'cannabis', 'embryo')
+    :type bind_key: str
+    :param spec: Database schema specification from SIMPLE_EFP_DATABASE_SCHEMAS
+    :type spec: Dict[str, Any]
+    :return: Dynamically generated SQLAlchemy model class
+    :rtype: db.Model
+
+    Example::
+
+        schema = SIMPLE_EFP_DATABASE_SCHEMAS['cannabis']
+        CannabisModel = _generate_model('cannabis', schema)
+        # Returns class: CannabisSampleData(db.Model)
+    """
+    attrs = {"__bind_key__": bind_key, "__tablename__": spec["table_name"]}
+
+    for column in spec["columns"]:
+        kwargs = {"nullable": column.get("nullable", True)}
+        if column.get("primary_key"):
+            kwargs["primary_key"] = True
+        attrs[column["name"]] = db.mapped_column(_to_sqla_type(column), **kwargs)
+
+    class_name = "".join([part.capitalize() for part in bind_key.split("_")]) + "SampleData"
+    return type(class_name, (db.Model,), attrs)
+
+
+SIMPLE_EFP_SAMPLE_MODELS: Dict[str, db.Model] = {
+    db_name: _generate_model(db_name, spec) for db_name, spec in SIMPLE_EFP_DATABASE_SCHEMAS.items()
+}
+
+__all__ = ["SIMPLE_EFP_SAMPLE_MODELS"]