feat(gherkin): add gherkin parser for workflow testing (#464)

Closes #463

Co-Authored-By: Giuseppe Steduto <[email protected]>

AUTHORS.md

@@ -4,6 +4,7 @@ The list of contributors in alphabetical order:
 
 - [Adelina Lintuluoto](https://orcid.org/0000-0002-0726-1452)
 - [Agisilaos Kounelis](https://orcid.org/0000-0001-9312-3189)
+- [Alastair Lyall](https://orcid.org/0009-0000-4955-8935)
 - [Audrius Mecionis](https://orcid.org/0000-0002-3759-1663)
 - [Bruno Rosendo](https://orcid.org/0000-0002-0923-3148)
 - [Burt Holzman](https://orcid.org/0000-0001-5235-6314)

MANIFEST.in

@@ -23,3 +23,4 @@ recursive-include docs *.txt
 recursive-include reana_commons *.json
 recursive-include reana_commons *.py
 recursive-include tests *.py
+recursive-include tests *.feature

reana_commons/gherkin_parser/__init__.py

@@ -0,0 +1,9 @@
+# -*- coding: utf-8 -*-
+#
+# This file is part of REANA.
+# Copyright (C) 2019, 2021 CERN.
+#
+# REANA is free software; you can redistribute it and/or modify it
+# under the terms of the MIT License; see LICENSE file for more details.
+
+"""REANA-Commons gherkin parser package."""

reana_commons/gherkin_parser/data_fetcher.py

@@ -0,0 +1,95 @@
+# This file is part of REANA.
+# Copyright (C) 2024 CERN.
+#
+# REANA is free software; you can redistribute it and/or modify it
+# under the terms of the MIT License; see LICENSE file for more details.
+
+
+# This file provides primitives required for gherkin_parser/functions.py, allowing for different
+# implementations in both the client side (api calls) and server side (database access). This avoids
+# circular dependencies between reana-commons and reana-client.
+"""Base class for fetching data related to a workflow."""
+
+from abc import ABC, abstractmethod
+
+
+class DataFetcherBase(ABC):
+    """Base class for fetching date related to a workflow."""
+
+    @abstractmethod
+    def list_files(self, workflow, file_name=None, page=None, size=None, search=None):
+        """Return the list of files for a given workflow workspace.
+
+        :param workflow: name or id of the workflow.
+        :param file_name: file name(s) (glob) to list.
+        :param page: page number of returned file list.
+        :param size: page size of returned file list.
+        :param search: filter search results by parameters.
+        :returns: a list of dictionaries that have the ``name``, ``size`` and
+                    ``last-modified`` keys.
+        """
+        pass
+
+    @abstractmethod
+    def get_workflow_disk_usage(self, workflow, parameters):
+        """Display disk usage workflow.
+
+        :param workflow: name or id of the workflow.
+        :param parameters: a dictionary to customize the response. It has the following
+            (optional) keys:
+
+            - ``summarize``: a boolean value to indicate whether to summarize the response
+            to include only the total workspace disk usage
+            - ``search``: a string to filter the response by file name
+
+        :return: a dictionary containing the ``workflow_id``, ``workflow_name``, and the ``user`` ID, with
+                a ``disk_usage_info`` keys that contains a list of dictionaries, each of one corresponding
+                to a file, with the ``name`` and ``size`` keys.
+        """
+        pass
+
+    @abstractmethod
+    def get_workflow_logs(self, workflow, steps=None, page=None, size=None):
+        """Get logs from a workflow engine.
+
+        :param workflow: name or id of the workflow.
+        :param steps: list of step names to get logs for.
+        :param page: page number of returned log list.
+        :param size: page size of returned log list.
+
+        :return: a dictionary with a ``logs`` key containing a JSON string that
+                contains the requested logs.
+        """
+        pass
+
+    @abstractmethod
+    def get_workflow_status(self, workflow):
+        """Get status of previously created workflow.
+
+        :param workflow: name or id of the workflow.
+        :return: a dictionary with the information about the workflow status.
+                The dictionary has the following keys: ``id``, ``logs``, ``name``,
+                ``progress``, ``status``, ``user``.
+        """
+        pass
+
+    @abstractmethod
+    def get_workflow_specification(self, workflow):
+        """Get specification of previously created workflow.
+
+        :param workflow: name or id of the workflow.
+        :returns: a dictionary that cointains two top-level keys: ``parameters``, and
+                ``specification`` (which contains a dictionary created from the workflow specification).
+        """
+        pass
+
+    @abstractmethod
+    def download_file(self, workflow, file_name):
+        """Download the requested file if it exists.
+
+        :param workflow: name or id of the workflow.
+        :param file_name: file name or path to the file requested.
+        :return: a tuple containing file binary content, filename and whether
+            the returned file is a zip archive containing multiple files.
+        """
+        pass

reana_commons/gherkin_parser/errors.py

@@ -0,0 +1,24 @@
+# This file is part of REANA.
+# Copyright (C) 2024 CERN.
+#
+# REANA is free software; you can redistribute it and/or modify it
+# under the terms of the MIT License; see LICENSE file for more details.
+"""Gherkin parser errors."""
+
+
+class StepDefinitionNotFound(Exception):
+    """The step definition was not found."""
+
+    pass
+
+
+class StepSkipped(Exception):
+    """The step was skipped."""
+
+    pass
+
+
+class FeatureFileError(Exception):
+    """The feature file is invalid."""
+
+    pass