genelastic 0.6.1__tar.gz → 0.7.0__tar.gz

genelastic-0.7.0/PKG-INFO

@@ -0,0 +1,105 @@
+Metadata-Version: 2.2
+Name: genelastic
+Version: 0.7.0
+Summary: Generate and store genetic data into an Elasticsearch database.
+Author: CNRGH
+Author-email: Pierrick ROGER <pierrick.roger@cnrgh.fr>, Maxime BLANCHON <maxime.blanchon@cnrgh.fr>
+License: CeCILL
+Keywords: CNRGH,genelastic,generation,storage,elasticsearch,database
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: CEA CNRS Inria Logiciel Libre License, version 2.1 (CeCILL-2.1)
+Classifier: Programming Language :: Python :: 3.11
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+Requires-Dist: elasticsearch
+Requires-Dist: PyVCF3
+Requires-Dist: schema
+Requires-Dist: PyYAML
+Requires-Dist: biophony>=1.2.1
+Requires-Dist: colorlog
+Provides-Extra: tests
+Requires-Dist: pytest; extra == "tests"
+Requires-Dist: mypy; extra == "tests"
+Requires-Dist: coverage; extra == "tests"
+Requires-Dist: yamllint; extra == "tests"
+Requires-Dist: types-PyYAML; extra == "tests"
+Requires-Dist: ruff<0.9,>=0.8.1; extra == "tests"
+Requires-Dist: pre-commit<4.1,>=4.0.1; extra == "tests"
+Requires-Dist: types-requests; extra == "tests"
+Requires-Dist: ansible<10.5,>=10.4.0; extra == "tests"
+Requires-Dist: ansible-lint<25,>=24.12.2; extra == "tests"
+Provides-Extra: docs
+Requires-Dist: sphinx; extra == "docs"
+Requires-Dist: sphinx-autoapi; extra == "docs"
+Requires-Dist: furo; extra == "docs"
+Provides-Extra: api
+Requires-Dist: flask; extra == "api"
+Requires-Dist: elasticsearch; extra == "api"
+Requires-Dist: environs; extra == "api"
+Requires-Dist: connexion[flask,swagger-ui,uvicorn]; extra == "api"
+Provides-Extra: ui
+Requires-Dist: flask; extra == "ui"
+Requires-Dist: requests; extra == "ui"
+Requires-Dist: environs; extra == "ui"
+
+# genelastic
+
+Storing of genetics data into an Elasticsearch database.
+
+## Prerequisites
+
+- `python` >= 3.11
+- `make`
+
+## Installation
+
+To install dependencies, run the following command:
+
+```bash
+python -m venv .venv
+source .venv/bin/activate
+make install.deps
+```
+
+## Configuration
+
+To start the **API server**, the following environment variables should be defined:
+
+- `GENAPI_ES_URL`: URL of the Elasticsearch server,
+- `GENAPI_ES_ENCODED_API_KEY`: Encoded API key,
+- `GENAPI_ES_INDEX_PREFIX`: Prefix to identify indices of interest,
+- `GENAPI_ES_CERT_FP`: Certificate fingerprint of the Elasticsearch server.
+
+Then, run the following command:
+
+```bash
+make start-api
+```
+
+To start the **UI server**, the following environment variables should be defined:
+
+- `GENUI_API_URL`: URL of the API server.
+
+Then, run the following command:
+
+```bash
+make start-ui
+```
+
+## Developers
+
+This project uses [pre-commit](https://pre-commit.com/) to manage Git hooks scripts. To install project hooks, run:
+
+```bash
+pre-commit install
+```
+
+After that, each commit will succeed only if all hooks (defined in `.pre-commit-config.yaml`) pass.
+
+If necessary (though not recommended),
+you can skip these hooks by using the `--no-verify` / `-n` option when committing:
+
+```bash
+git commit -m "My commit message" --no-verify # This commit will not run installed hooks.
+```

genelastic-0.7.0/README.md

@@ -0,0 +1,60 @@
+# genelastic
+
+Storing of genetics data into an Elasticsearch database.
+
+## Prerequisites
+
+- `python` >= 3.11
+- `make`
+
+## Installation
+
+To install dependencies, run the following command:
+
+```bash
+python -m venv .venv
+source .venv/bin/activate
+make install.deps
+```
+
+## Configuration
+
+To start the **API server**, the following environment variables should be defined:
+
+- `GENAPI_ES_URL`: URL of the Elasticsearch server,
+- `GENAPI_ES_ENCODED_API_KEY`: Encoded API key,
+- `GENAPI_ES_INDEX_PREFIX`: Prefix to identify indices of interest,
+- `GENAPI_ES_CERT_FP`: Certificate fingerprint of the Elasticsearch server.
+
+Then, run the following command:
+
+```bash
+make start-api
+```
+
+To start the **UI server**, the following environment variables should be defined:
+
+- `GENUI_API_URL`: URL of the API server.
+
+Then, run the following command:
+
+```bash
+make start-ui
+```
+
+## Developers
+
+This project uses [pre-commit](https://pre-commit.com/) to manage Git hooks scripts. To install project hooks, run:
+
+```bash
+pre-commit install
+```
+
+After that, each commit will succeed only if all hooks (defined in `.pre-commit-config.yaml`) pass.
+
+If necessary (though not recommended),
+you can skip these hooks by using the `--no-verify` / `-n` option when committing:
+
+```bash
+git commit -m "My commit message" --no-verify # This commit will not run installed hooks.
+```

genelastic-0.7.0/pyproject.toml

@@ -0,0 +1,114 @@
+[build-system]
+requires = ["setuptools >= 70.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "genelastic"
+version = "0.7.0"
+dependencies = [
+    "elasticsearch",
+    "PyVCF3",
+    "schema",
+    "PyYAML",
+    "biophony>=1.2.1",
+    "colorlog",
+]
+requires-python = ">= 3.11"
+authors = [
+    { name = "CNRGH" },
+    { name = "Pierrick ROGER", email = "pierrick.roger@cnrgh.fr" },
+    { name = "Maxime BLANCHON", email = "maxime.blanchon@cnrgh.fr" }]
+description = "Generate and store genetic data into an Elasticsearch database."
+readme = "README.md"
+license = { text = "CeCILL" }
+keywords = ["CNRGH", "genelastic", "generation", "storage", "elasticsearch", "database"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: CEA CNRS Inria Logiciel Libre License, version 2.1 (CeCILL-2.1)",
+    "Programming Language :: Python :: 3.11"
+]
+
+[project.optional-dependencies]
+tests = [
+    "pytest",
+    "mypy",
+    "coverage",
+    "yamllint",
+    "types-PyYAML",
+    "ruff >= 0.8.1, < 0.9",
+    "pre-commit >= 4.0.1, < 4.1",
+    "types-requests",
+    "ansible >= 10.4.0, < 10.5",
+    "ansible-lint >= 24.12.2, < 25"
+]
+docs = [
+    "sphinx",
+    "sphinx-autoapi",
+    "furo"
+]
+
+api = [
+    "flask",
+    "elasticsearch",
+    "environs",
+    "connexion[flask,swagger-ui,uvicorn]"
+]
+
+ui = [
+    "flask",
+    "requests",
+    "environs"
+]
+
+[project.scripts]
+gnl-data = "genelastic.import_data.cli_gen_data:main"
+gnl-import = "genelastic.import_data.cli_import:main"
+gnl-info = "genelastic.import_data.cli_info:main"
+gnl-integrity = "genelastic.import_data.cli_integrity:main"
+gnl-validate = "genelastic.import_data.cli_validate:main"
+
+[tool.ruff]
+line-length = 80
+target-version = "py311"
+
+[tool.ruff.lint]
+ignore = [
+    "E501",
+    "D100",
+    "D103",
+    "D104",
+    "D105",
+    "D107",
+    "D205",
+    "D415",
+    "TRY400",
+    "S311", # Disable rule 'Standard pseudo-random generators are not suitable for cryptographic purposes'.
+    # Bellow are rules disabled as they conflict with 'ruff format'.
+    # https://docs.astral.sh/ruff/formatter/#conflicting-lint-rules
+    "W191",
+    "E111",
+    "E114",
+    "E117",
+    "D206",
+    "D300",
+    "Q000",
+    "Q001",
+    "Q002",
+    "Q003",
+    "COM812",
+    "COM819",
+    "ISC001",
+    "ISC002",
+]
+select = ["ALL"]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/*" = [
+    "S101", # Disable "Use of assert detected" rule.
+    "PLR2004", # Disable "Magic value used in comparison" rule.
+    "SLF001"  # Disable "Private member accessed" rule.
+]
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"

genelastic-0.7.0/src/genelastic/api/extends/example.py

@@ -0,0 +1,6 @@
+from flask import Response, jsonify
+
+
+def ping_2() -> Response:
+    """Test route to verify that the server is online."""
+    return jsonify({"message": "pong_2"})

genelastic-0.7.0/src/genelastic/api/routes.py

@@ -0,0 +1,221 @@
+from importlib.metadata import version
+from pathlib import Path
+from typing import Any
+
+from flask import Response, current_app, jsonify
+
+
+def ping() -> Response:
+    """Test route to verify that the server is online."""
+    return jsonify({"message": "pong"})
+
+
+def list_indices() -> Response:
+    """Route to list Elasticsearch indexes."""
+    return current_app.elastic_query_conn.get_indices()  # type: ignore[attr-defined, no-any-return]
+
+
+def retrieve_document(index_id: str, document_id: str) -> Response:
+    """Route to retrieve a document by its ID."""
+    document = current_app.elastic_query_conn.get_document_by_id(  # type: ignore[attr-defined]
+        index_id, document_id
+    )
+    return jsonify(document)
+
+
+def list_wet_processes() -> Response:
+    """Route to list wet processes."""
+    wet_processes_index = (
+        f"{current_app.config['GENAPI_ES_INDEX_PREFIX']}-wet_processes"
+    )
+    result = current_app.elastic_query_conn.get_field_values(  # type: ignore[attr-defined]
+        wet_processes_index, "proc_id"
+    )
+    return jsonify(list(result))
+
+
+def list_bi_processes() -> Response:
+    """Route to list bi processes."""
+    bi_processes_index = (
+        f"{current_app.config['GENAPI_ES_INDEX_PREFIX']}-bi_processes"
+    )
+    result = current_app.elastic_query_conn.get_field_values(  # type: ignore[attr-defined]
+        bi_processes_index, "proc_id"
+    )
+    return jsonify(list(result))
+
+
+def list_analyses() -> Response:
+    """Route to list analyses."""
+    analyses_index = f"{current_app.config['GENAPI_ES_INDEX_PREFIX']}-analyses"
+    result = current_app.elastic_query_conn.get_field_values(  # type: ignore[attr-defined]
+        analyses_index, "path"
+    )
+    filenames = [Path(path).name for path in result]
+    return jsonify(filenames)
+
+
+def list_analyses_wet_processes(proc_id: str) -> Response:
+    """Route to list analyses one of specific wet process"""
+    analyses_index = f"{current_app.config['GENAPI_ES_INDEX_PREFIX']}-analyses"
+
+    search_query = {
+        "query": {
+            "term": {
+                "metadata.wet_process.keyword": proc_id,
+            }
+        }
+    }
+    response = current_app.elastic_query_conn.client.search(  # type: ignore[attr-defined]
+        index=analyses_index, body=search_query
+    )
+    result = [hit["_source"]["path"] for hit in response["hits"]["hits"]]
+
+    return jsonify(result)
+
+
+def list_analyses_bi_processes(proc_id: str) -> Response:
+    """Route to list analyses one of specific bi process"""
+    analyses_index = f"{current_app.config['GENAPI_ES_INDEX_PREFIX']}-analyses"
+
+    search_query = {
+        "query": {
+            "term": {
+                "metadata.bi_process.keyword": proc_id,
+            }
+        }
+    }
+    response = current_app.elastic_query_conn.client.search(  # type: ignore[attr-defined]
+        index=analyses_index, body=search_query
+    )
+    result = [hit["_source"]["path"] for hit in response["hits"]["hits"]]
+
+    return jsonify(result)
+
+
+def list_snv_documents() -> Response:
+    """Route to list all documents containing a mutation at a single position (SNV)."""
+    index_pattern = "genelastic-file-*"
+    target_value = "SNV"
+
+    search_query = {
+        "aggs": {
+            "snv_docs": {
+                "composite": {
+                    "sources": [
+                        {"alt_value": {"terms": {"field": "alt.keyword"}}}
+                    ],
+                    "size": 1000,
+                }
+            }
+        },
+        "query": {"term": {"alt.keyword": target_value}},
+        "size": 0,
+    }
+
+    all_documents = []
+    buckets = current_app.elastic_query_conn.run_composite_aggregation(  # type: ignore[attr-defined]
+        index_pattern, search_query
+    )
+
+    for bucket in buckets:
+        alt_value = bucket["key"]["alt_value"]
+
+        search_query_docs = {
+            "query": {"term": {"alt.keyword": alt_value}},
+            "size": 1000,
+        }
+
+        response = current_app.elastic_query_conn.client.search(  # type: ignore[attr-defined]
+            index=index_pattern, body=search_query_docs
+        )
+
+        all_documents.extend(response["hits"]["hits"])
+
+    return jsonify(all_documents)
+
+
+def build_snv_search_query(
+    target_alt: str, target_svtype: str
+) -> dict[str, Any]:
+    """Helper function to build the search query for SNV documents with specified alt and SVTYPE."""
+    return {
+        "query": {
+            "bool": {
+                "must": [
+                    {"term": {"alt.keyword": target_alt}},
+                    {"term": {"info.SVTYPE.keyword": target_svtype}},
+                ]
+            }
+        },
+        "size": 1000,
+    }
+
+
+def build_snv_mutation_search_query(
+    target_svtypes: list[str],
+) -> dict[str, Any]:
+    """Helper function to build the search query for SNV mutations with specified SVTYPE values."""
+    return {
+        "query": {
+            "bool": {
+                "must": [
+                    {"term": {"alt.keyword": "SNV"}},
+                    {"terms": {"info.SVTYPE.keyword": target_svtypes}},
+                ]
+            }
+        },
+        "size": 1000,
+    }
+
+
+def list_snv_insertion_documents() -> Response:
+    """Route to list all documents containing an insertion (INS) at a single position (SNV)."""
+    index_pattern = "genelastic-file-*"
+    search_query = build_snv_search_query(target_alt="SNV", target_svtype="INS")
+
+    response = current_app.elastic_query_conn.client.search(  # type: ignore[attr-defined]
+        index=index_pattern, body=search_query
+    )
+
+    all_documents = [hit["_source"] for hit in response["hits"]["hits"]]
+
+    return jsonify(all_documents)
+
+
+def list_snv_deletion_documents() -> Response:
+    """Route to list all documents containing a deletion (DEL) at a single position (SNV)."""
+    index_pattern = "genelastic-file-*"
+    search_query = build_snv_search_query(target_alt="SNV", target_svtype="DEL")
+
+    response = current_app.elastic_query_conn.client.search(  # type: ignore[attr-defined]
+        index=index_pattern, body=search_query
+    )
+
+    all_documents = [hit["_source"] for hit in response["hits"]["hits"]]
+
+    return jsonify(all_documents)
+
+
+def list_snv_mutation_documents() -> Response:
+    """Route to list all documents containing a mutation at a single position (SNV)."""
+    index_pattern = "genelastic-file-*"
+    target_svtypes = ["INS", "DEL"]
+
+    search_query = build_snv_mutation_search_query(
+        target_svtypes=target_svtypes
+    )
+
+    response = current_app.elastic_query_conn.client.search(  # type: ignore[attr-defined]
+        index=index_pattern, body=search_query
+    )
+
+    all_documents = [hit["_source"] for hit in response["hits"]["hits"]]
+
+    return jsonify(all_documents)
+
+
+def get_genelastic_version() -> Response:
+    """Retourne la version du package genelastic."""
+    top_level_package = __package__.split(".")[0]
+    return jsonify({"version": version(top_level_package)})

genelastic-0.7.0/src/genelastic/api/server.py

@@ -0,0 +1,80 @@
+from pathlib import Path
+from typing import Any
+
+import connexion
+import yaml
+
+from genelastic.common import ElasticQueryConn
+
+
+def load_yaml(file_path: Path) -> Any:  # noqa: ANN401
+    """Load a YAML file and return its content."""
+    content = None
+    with Path.open(file_path, encoding="utf-8") as f:
+        try:
+            content = yaml.safe_load(f)
+        except yaml.YAMLError as exc:
+            raise SystemExit(exc) from exc
+    return content
+
+
+def aggregate_openapi_specs(
+    main_spec_file: Path, additional_spec_path: Path
+) -> Any:  # noqa: ANN401
+    """Aggregate OpenAPI specifications from a main file and a directory
+    of additional specifications.
+    """
+    main_spec = load_yaml(main_spec_file)
+    try:
+        entries = additional_spec_path.iterdir()
+    except OSError as exc:
+        raise SystemExit(exc) from exc
+
+    if "paths" not in main_spec:
+        main_spec["paths"] = []
+
+    for entry in entries:
+        if not entry.is_file():
+            continue
+
+        if entry.suffix not in [".yml", ".yaml"]:
+            continue
+
+        content = load_yaml(entry)
+
+        if "paths" in content:
+            main_spec["paths"].update(content["paths"])
+
+    return main_spec
+
+
+# Initialiser l'application Connexion
+connexion_app = connexion.FlaskApp(__name__)
+connexion_app.app.config.from_object("src.genelastic.api.settings.Config")
+
+# Initialiser le client Elasticsearch
+es_url = connexion_app.app.config["GENAPI_ES_URL"]
+es_cert_fp = connexion_app.app.config["GENAPI_ES_CERT_FP"]
+es_api_key = connexion_app.app.config["GENAPI_ES_ENCODED_API_KEY"]
+
+connexion_app.app.elastic_query_conn = ElasticQueryConn(
+    es_url, es_cert_fp, api_key=es_api_key
+)
+
+connexion_app.app.logger.debug(
+    "Successfully connected to Elasticsearch server: %s",
+    connexion_app.app.elastic_query_conn.client.info(),
+)
+
+# Chemins des fichiers YAML
+main_yaml_file = Path(__file__).parents[0] / "specification.yml"
+additional_yaml_dir = Path(__file__).parents[0] / "extends"
+
+# Charger et combiner les fichiers YAML
+yaml_spec = aggregate_openapi_specs(main_yaml_file, additional_yaml_dir)
+
+# Ajouter la spécification vers OpenAPI
+connexion_app.add_api(yaml_spec)
+
+if __name__ == "__main__":
+    connexion_app.run(debug=True)

{genelastic-0.6.1 → genelastic-0.7.0}/src/genelastic/api/settings.py

@@ -1,11 +1,12 @@
-# pylint: disable=missing-module-docstring
 from environs import Env
 
 env = Env()
 env.read_env()
 
-# pylint: disable=missing-class-docstring,too-few-public-methods
+
 class Config:
+    """Flask config class."""
+
     # Charger toutes les variables d'environnement nécessaires
     GENAPI_ES_URL = env.url("GENAPI_ES_URL").geturl()
     GENAPI_ES_ENCODED_API_KEY = env.str("GENAPI_ES_ENCODED_API_KEY")

genelastic-0.7.0/src/genelastic/common/__init__.py

@@ -0,0 +1,39 @@
+"""Genelastic package for common code between API and import scripts."""
+
+from .cli import add_es_connection_args, add_verbose_control_args
+from .elastic import ElasticImportConn, ElasticQueryConn
+from .exceptions import DBIntegrityError
+from .types import (
+    AnalysisDocument,
+    AnalysisMetaData,
+    BioInfoProcessData,
+    Bucket,
+    BulkItems,
+    BundleDict,
+    MetadataDocument,
+    ProcessDocument,
+    RandomAnalysisData,
+    RandomBiProcessData,
+    RandomWetProcessData,
+    WetProcessesData,
+)
+
+__all__ = [
+    "AnalysisDocument",
+    "AnalysisMetaData",
+    "BioInfoProcessData",
+    "Bucket",
+    "BulkItems",
+    "BundleDict",
+    "DBIntegrityError",
+    "ElasticImportConn",
+    "ElasticQueryConn",
+    "MetadataDocument",
+    "ProcessDocument",
+    "RandomAnalysisData",
+    "RandomBiProcessData",
+    "RandomWetProcessData",
+    "WetProcessesData",
+    "add_es_connection_args",
+    "add_verbose_control_args",
+]