wfcommons 1.2__tar.gz → 1.4__tar.gz

{wfcommons-1.2/wfcommons.egg-info → wfcommons-1.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: wfcommons
-Version: 1.2
+Version: 1.4
 Summary: A Framework for Enabling Scientific Workflow Research and Education
 Author-email: WfCommons team <support@wfcommons.org>
 License: GNU General Public License v3 (GPLv3)
@@ -10,19 +10,17 @@ Project-URL: Documentation, https://docs.wfcommons.org
 Project-URL: Tracker, https://github.com/wfcommons/WfCommons/issues
 Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
 Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Education
 Classifier: Intended Audience :: Science/Research
 Classifier: Natural Language :: English
 Classifier: Topic :: Documentation :: Sphinx
 Classifier: Topic :: System :: Distributed Computing
-Requires-Python: >=3.9
+Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: jsonschema
@@ -32,13 +30,14 @@ Requires-Dist: numpy
 Requires-Dist: pandas
 Requires-Dist: python-dateutil
 Requires-Dist: requests
-Requires-Dist: scipy
+Requires-Dist: scipy>=1.16.1
 Requires-Dist: pyyaml
 Requires-Dist: pandas
 Requires-Dist: shortuuid
 Requires-Dist: stringcase
 Requires-Dist: filelock
 Requires-Dist: pathos
+Requires-Dist: tomli-w
 Provides-Extra: test
 Requires-Dist: pytest; extra == "test"
 Requires-Dist: pytest-cov; extra == "test"
@@ -54,52 +53,64 @@ Dynamic: license-file
 [![Codecov][cov-badge]][cov-link]&nbsp;
 [![Downloads](https://static.pepy.tech/personalized-badge/wfcommons?period=total&units=international_system&left_color=grey&right_color=yellowgreen&left_text=Downloads)](https://pepy.tech/project/wfcommons)
 
-<a href="https://wfcommons.org" target="_blank"><img src="https://wfcommons.org/images/wfcommons-horizontal.png" width="350" /></a>
-<br/>_A Framework for Enabling Scientific Workflow Research and Development_
+<a href="https://wfcommons.org" target="_blank"><img src="https://wfcommons.org/images/wfcommons-logo-white.png" width="350" /></a>
+<br/>An open-source ecosystem of workflow execution instances, synthetic workflow generators, and benchmark specifications. It helps the community study scheduling, performance, resilience, and emerging AI-driven workflow automation on modern distributed and HPC platforms.
 
-This Python package provides a collection of tools for:
+- **Real instances:** Workflow executions curated in a common JSON format (WfFormat).
+- **Synthetic realism:** Generate realistic workflows from real traces.
+- **Benchmarks:** Produce executable specs for repeatable experiments and fair comparisons.
 
-- Analyzing instances of actual workflow executions;
-- Producing recipes structures for creating workflow recipes for workflow generation;
-- Generating synthetic realistic workflow instances; and
-- Generating realistic workflow benchmark specifications.
+Quick links: [Documentation](https://wfcommons.readthedocs.io/en/latest/) · [Website](https://wfcommons.org) · [GitHub Issues](https://github.com/wfcommons/wfcommons/issues)
 
-[![Open In Gitpod](https://gitpod.io/button/open-in-gitpod.svg)](https://gitpod.io/#https://github.com/wfcommons/wfcommons/tree/main)
+## Quickstart
 
-## Installation
+WfCommons requires Python 3.11+ and has been tested on Linux and macOS.
 
-WfCommons is available on [PyPI](https://pypi.org/project/wfcommons).
-WfCommons requires Python3.9+ and has been tested on Linux and macOS.
+```
+python3 -m venv .venv
+source .venv/bin/activate
+python3 -m pip install wfcommons
+```
 
-### Installation using pip
+Generate a synthetic workflow in a few lines:
 
-While `pip` can be used to install WfCommons, we suggest the following
-approach for reliable installation when many Python environments are available:
+```python
+import pathlib
+from wfcommons.wfchef.recipes import SeismologyRecipe
+from wfcommons import WorkflowGenerator
 
-```
-$ python3 -m pip install wfcommons
+generator = WorkflowGenerator(SeismologyRecipe.from_num_tasks(250))
+workflow = generator.build_workflow()
+workflow.write_json(pathlib.Path("seismology-workflow.json"))
 ```
 
-### Retrieving the latest unstable version
+Next steps:
 
-If you want to use the latest WfCommons unstable version, that will contain
-brand new features (but also contain bugs as the stabilization work is still
-underway), you may consider retrieving the latest unstable version.
+- Learn how to build recipes in the [WfChef guide](https://wfcommons.readthedocs.io/en/latest/generating_workflows_recipe.html).
+- Generate larger workflow families in the [WfGen guide](https://wfcommons.readthedocs.io/en/latest/generating_workflows.html).
+- Produce benchmark specs in the [WfBench guide](https://wfcommons.readthedocs.io/en/latest/generating_workflow_benchmarks.html).
 
-Cloning from [WfCommons's GitHub](https://github.com/wfcommons/wfcommons)
-repository:
+## Installation
+
+WfCommons is available on [PyPI](https://pypi.org/project/wfcommons).
+
+```
+python3 -m pip install wfcommons
+```
+
+### Installing from source (latest)
 
 ```
-$ git clone https://github.com/wfcommons/wfcommons
-$ cd wfcommons
-$ pip install .
+git clone https://github.com/wfcommons/wfcommons
+cd wfcommons
+python3 -m pip install .
 ```
 
 ### Optional Requirements
 
 #### Graphviz
-WfCommons uses _pygraphviz_ for generating visualizations for the workflow task graph. 
-If you want to enable this feature, you will have to install the 
+WfCommons uses _pygraphviz_ for generating visualizations for the workflow task graph.
+If you want to enable this feature, you will have to install the
 [graphviz](https://www.graphviz.org/) package (version 2.16 or later).
 You can install graphviz easily on Linux with your favorite package manager,
 for example for Debian-based distributions:
@@ -130,15 +141,14 @@ python3 -m pip install pydot
 
 ## Get in Touch
 
-The main channel to reach the WfCommons team is via the support email: 
+The main channel to reach the WfCommons team is via the support email:
 [support@wfcommons.org](mailto:support@wfcommons.org).
 
-**Bug Report / Feature Request:** our preferred channel to report a bug or request a feature is via  
+**Bug Report / Feature Request:** our preferred channel to report a bug or request a feature is via
 WfCommons's [Github Issues Track](https://github.com/wfcommons/wfcommons/issues).
 
-
 ## Citing WfCommons
-When citing WfCommons, please use the following paper. You should also actually read 
+When citing WfCommons, please use the following paper. You should also actually read
 that paper, as it provides a recent and general overview on the framework.
 
 ```

{wfcommons-1.2 → wfcommons-1.4}/README.md

@@ -6,52 +6,64 @@
 [![Codecov][cov-badge]][cov-link] 
 [![Downloads](https://static.pepy.tech/personalized-badge/wfcommons?period=total&units=international_system&left_color=grey&right_color=yellowgreen&left_text=Downloads)](https://pepy.tech/project/wfcommons)
 
-<a href="https://wfcommons.org" target="_blank"><img src="https://wfcommons.org/images/wfcommons-horizontal.png" width="350" /></a>
-<br/>_A Framework for Enabling Scientific Workflow Research and Development_
+<a href="https://wfcommons.org" target="_blank"><img src="https://wfcommons.org/images/wfcommons-logo-white.png" width="350" /></a>
+<br/>An open-source ecosystem of workflow execution instances, synthetic workflow generators, and benchmark specifications. It helps the community study scheduling, performance, resilience, and emerging AI-driven workflow automation on modern distributed and HPC platforms.
 
-This Python package provides a collection of tools for:
+- **Real instances:** Workflow executions curated in a common JSON format (WfFormat).
+- **Synthetic realism:** Generate realistic workflows from real traces.
+- **Benchmarks:** Produce executable specs for repeatable experiments and fair comparisons.
 
-- Analyzing instances of actual workflow executions;
-- Producing recipes structures for creating workflow recipes for workflow generation;
-- Generating synthetic realistic workflow instances; and
-- Generating realistic workflow benchmark specifications.
+Quick links: [Documentation](https://wfcommons.readthedocs.io/en/latest/) · [Website](https://wfcommons.org) · [GitHub Issues](https://github.com/wfcommons/wfcommons/issues)
 
-[![Open In Gitpod](https://gitpod.io/button/open-in-gitpod.svg)](https://gitpod.io/#https://github.com/wfcommons/wfcommons/tree/main)
+## Quickstart
 
-## Installation
+WfCommons requires Python 3.11+ and has been tested on Linux and macOS.
 
-WfCommons is available on [PyPI](https://pypi.org/project/wfcommons).
-WfCommons requires Python3.9+ and has been tested on Linux and macOS.
+```
+python3 -m venv .venv
+source .venv/bin/activate
+python3 -m pip install wfcommons
+```
 
-### Installation using pip
+Generate a synthetic workflow in a few lines:
 
-While `pip` can be used to install WfCommons, we suggest the following
-approach for reliable installation when many Python environments are available:
+```python
+import pathlib
+from wfcommons.wfchef.recipes import SeismologyRecipe
+from wfcommons import WorkflowGenerator
 
-```
-$ python3 -m pip install wfcommons
+generator = WorkflowGenerator(SeismologyRecipe.from_num_tasks(250))
+workflow = generator.build_workflow()
+workflow.write_json(pathlib.Path("seismology-workflow.json"))
 ```
 
-### Retrieving the latest unstable version
+Next steps:
 
-If you want to use the latest WfCommons unstable version, that will contain
-brand new features (but also contain bugs as the stabilization work is still
-underway), you may consider retrieving the latest unstable version.
+- Learn how to build recipes in the [WfChef guide](https://wfcommons.readthedocs.io/en/latest/generating_workflows_recipe.html).
+- Generate larger workflow families in the [WfGen guide](https://wfcommons.readthedocs.io/en/latest/generating_workflows.html).
+- Produce benchmark specs in the [WfBench guide](https://wfcommons.readthedocs.io/en/latest/generating_workflow_benchmarks.html).
 
-Cloning from [WfCommons's GitHub](https://github.com/wfcommons/wfcommons)
-repository:
+## Installation
+
+WfCommons is available on [PyPI](https://pypi.org/project/wfcommons).
+
+```
+python3 -m pip install wfcommons
+```
+
+### Installing from source (latest)
 
 ```
-$ git clone https://github.com/wfcommons/wfcommons
-$ cd wfcommons
-$ pip install .
+git clone https://github.com/wfcommons/wfcommons
+cd wfcommons
+python3 -m pip install .
 ```
 
 ### Optional Requirements
 
 #### Graphviz
-WfCommons uses _pygraphviz_ for generating visualizations for the workflow task graph. 
-If you want to enable this feature, you will have to install the 
+WfCommons uses _pygraphviz_ for generating visualizations for the workflow task graph.
+If you want to enable this feature, you will have to install the
 [graphviz](https://www.graphviz.org/) package (version 2.16 or later).
 You can install graphviz easily on Linux with your favorite package manager,
 for example for Debian-based distributions:
@@ -82,15 +94,14 @@ python3 -m pip install pydot
 
 ## Get in Touch
 
-The main channel to reach the WfCommons team is via the support email: 
+The main channel to reach the WfCommons team is via the support email:
 [support@wfcommons.org](mailto:support@wfcommons.org).
 
-**Bug Report / Feature Request:** our preferred channel to report a bug or request a feature is via  
+**Bug Report / Feature Request:** our preferred channel to report a bug or request a feature is via
 WfCommons's [Github Issues Track](https://github.com/wfcommons/wfcommons/issues).
 
-
 ## Citing WfCommons
-When citing WfCommons, please use the following paper. You should also actually read 
+When citing WfCommons, please use the following paper. You should also actually read
 that paper, as it provides a recent and general overview on the framework.
 
 ```

{wfcommons-1.2 → wfcommons-1.4}/bin/wfbench

@@ -341,7 +341,7 @@ def begin_flowcept(args):
                  bundle_exec_id=args.workflow_id,
                  start_persistence=False, save_workflow=False)
     f.start()
-    t = FlowceptTask(workflow_id=args.workflow_id, used={**args.__dict__})
+    t = FlowceptTask(task_id=f"{args.workflow_id}_{args.name}", workflow_id=args.workflow_id, used={**args.__dict__})
     return f, t
 
 
@@ -457,7 +457,11 @@ def main():
         if args.time:
             time.sleep(int(args.time))
             for proc in procs:
-                os.killpg(os.getpgid(proc.pid), signal.SIGTERM)
+                if isinstance(proc, multiprocessing.Process):
+                    if proc.is_alive():
+                        proc.terminate()
+                elif isinstance(proc, subprocess.Popen):
+                    proc.terminate()
         else:
             for proc in procs:
                 if isinstance(proc, subprocess.Popen):

{wfcommons-1.2 → wfcommons-1.4}/pyproject.toml

@@ -7,16 +7,14 @@ name = "wfcommons"
 authors = [{name = "WfCommons team", email = "support@wfcommons.org"}]
 description = "A Framework for Enabling Scientific Workflow Research and Education"
 readme = "README.md"
-requires-python = ">=3.9"
+requires-python = ">=3.11"
 classifiers = [
     "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
     "Operating System :: OS Independent",
-    "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.9",
-    "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
     "Intended Audience :: Developers",
     "Intended Audience :: Education",
     "Intended Audience :: Science/Research",
@@ -33,13 +31,14 @@ dependencies = [
     "pandas",
     "python-dateutil",
     "requests",
-    "scipy",
+    "scipy>=1.16.1",
     "pyyaml",
     "pandas",
     "shortuuid",
     "stringcase",
     "filelock",
     "pathos",
+    "tomli-w"
 ]
 dynamic = ["version", "entry-points", "scripts"]
 
@@ -56,6 +55,12 @@ flowcept = ["flowcept"]
 [tool.setuptools.dynamic]
 version = {attr = "wfcommons.version.__version__"}
 
+[tool.coverage.run]
+omit = [
+    "wfcommons/wfinstances/logs/pegasusrec.py",
+    "wfcommons/wfbench/translator/templates"
+]
+
 [tool.pytest.ini_options]
 addopts="""
 --cov-context test  \
@@ -63,7 +68,6 @@ addopts="""
 --cov-report xml:coverage.xml \
 --cov-report term-missing \
 --cov ./wfcommons \
---ignore wfcommons/wfbench/translator/templates \
 --no-cov-on-fail \
 -ra \
 -W ignore"""

{wfcommons-1.2 → wfcommons-1.4}/setup.cfg

@@ -1,5 +1,5 @@
 [metadata]
-description-file = README.md
+description_file = README.md
 
 [egg_info]
 tag_build = 

wfcommons-1.4/setup.py

@@ -0,0 +1,74 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Copyright (c) 2020-2026 The WfCommons Team.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+import sys
+import subprocess
+import os
+
+from setuptools import setup, find_packages
+from setuptools.command.build_ext import build_ext
+
+class Build(build_ext):
+    """Customized setuptools build command - builds cpu-benchmark on build."""
+
+    def run(self):
+        # Try to build the cpu-benchmark, but make it optional
+        # This allows installation on Windows where make/g++ may not be available
+        try:
+            result = subprocess.call(["make"], stderr=subprocess.DEVNULL, stdout=subprocess.DEVNULL)
+            if result != 0:
+                sys.stderr.write("Warning: 'make' build failed. cpu-benchmark will not be available.\n")
+                sys.stderr.write("This is expected on Windows. To build cpu-benchmark, install make and g++.\n")
+        except (FileNotFoundError, OSError):
+            sys.stderr.write("Warning: 'make' is not installed. cpu-benchmark will not be available.\n")
+            sys.stderr.write("This is expected on Windows. To build cpu-benchmark, install make and g++.\n")
+        super().run()
+
+# Conditionally include cpu-benchmark based on platform
+data_files = []
+if sys.platform != 'win32':
+    # On Unix-like systems (Linux, macOS, Docker), always try to include it
+    # The Build class will create it during the build process
+    data_files.append(('bin', ['bin/cpu-benchmark']))
+else:
+    # On Windows, only include if it exists (e.g., if user manually compiled it)
+    cpu_benchmark_path = 'bin/cpu-benchmark'
+    if os.path.exists(cpu_benchmark_path):
+        data_files.append(('bin', [cpu_benchmark_path]))
+
+setup(
+    packages=find_packages(),
+    include_package_data=True,
+    has_ext_modules=lambda: True,
+    cmdclass={
+        'build_ext': Build,
+    },
+    data_files=data_files,
+    scripts=[
+        'bin/wfbench'
+    ],
+    entry_points={
+        'console_scripts': [
+            'wfchef=wfcommons.wfchef.chef:main',
+        ],
+        'workflow_recipes': [
+            'epigenomics_recipe = wfcommons.wfchef.recipes:EpigenomicsRecipe',
+            'montage_recipe = wfcommons.wfchef.recipes:MontageRecipe',
+            'cycles_recipe = wfcommons.wfchef.recipes:CyclesRecipe',
+            'seismology_recipe = wfcommons.wfchef.recipes:SeismologyRecipe',
+            'soykb_recipe = wfcommons.wfchef.recipes:SoykbRecipe',
+            'srasearch_recipe = wfcommons.wfchef.recipes:SrasearchRecipe',
+            'genome_recipe = wfcommons.wfchef.recipes:GenomeRecipe',
+            'blast_recipe = wfcommons.wfchef.recipes:BlastRecipe',
+            'bwa_recipe = wfcommons.wfchef.recipes:BwaRecipe',
+            'rnaseq_recipe = wfcommons.wfchef.recipes:RnaseqRecipe',
+        ]
+    },
+)

wfcommons-1.4/tests/test_helpers.py

@@ -0,0 +1,168 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Copyright (c) 2025-2026 The WfCommons Team.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+import pathlib
+import shutil
+import tarfile
+import os
+import io
+import sys
+import docker
+import networkx
+from docker.errors import ImageNotFound
+
+from wfcommons.common import Workflow
+
+
+def _create_fresh_local_dir(path: str) -> pathlib.Path:
+    dirpath = pathlib.Path(path)
+    if dirpath.exists():
+        shutil.rmtree(dirpath)
+    dirpath.mkdir(parents=True, exist_ok=True)
+    return dirpath
+
+def _remove_local_dir_if_it_exists(path: str) -> None:
+    dirpath = pathlib.Path(path)
+    if dirpath.exists():
+        shutil.rmtree(dirpath)
+
+
+def _make_tarfile_of_wfcommons():
+    source_dir = os.getcwd() # This assumes the testing is run from the root
+    tar_stream = io.BytesIO()
+    with tarfile.open(fileobj=tar_stream, mode='w') as tar:
+        tar.add(source_dir, arcname=os.path.basename(source_dir))
+    tar_stream.seek(0)
+    return tar_stream
+
+
+def _install_WfCommons_on_container(container):
+    # sys.stderr.write("Installing WfCommons on the container...\n")
+    # Copy the WfCommons code to it (removing stuff that should be removed)
+    target_path = '/tmp/'  # inside container
+    tar_data = _make_tarfile_of_wfcommons()
+    container.put_archive(target_path, tar_data)
+    # Cleanup files that came from the host
+    exit_code, output = container.exec_run("sudo /bin/rm -rf /tmp/WfCommons/build/", stdout=True, stderr=True)
+    exit_code, output = container.exec_run("sudo /bin/rm -rf /tmp/WfCommons/*.egg-info/", stdout=True, stderr=True)
+    # Clean up and force a rebuild of cpu-benchmark (because it may be compiled for the wrong architecture)
+    exit_code, output = container.exec_run("sudo /bin/rm -rf /tmp/WfCommons/bin/cpu-benchmark.o", stdout=True,
+                                           stderr=True)
+    exit_code, output = container.exec_run("sudo /bin/rm -rf /tmp/WfCommons/bin/cpu-benchmark", stdout=True,
+                                           stderr=True)
+
+    # Install WfCommons on the container (to install wfbench and cpu-benchmark really)
+    exit_code, output = container.exec_run("sudo python3 -m pip install . --break-system-packages",
+                                           workdir="/tmp/WfCommons", stdout=True, stderr=True)
+    # print(output.decode())
+    if exit_code != 0:
+        raise RuntimeError("Failed to install WfCommons on the container")
+
+def _start_docker_container(backend, mounted_dir, working_dir, bin_dir, command=None):
+    if command is None:
+        command = ["sleep", "infinity"]
+    # Pulling the Docker image
+    client = docker.from_env()
+    image_name = f"wfcommons/wfcommons-testing-{backend}"
+
+    try:
+        image = client.images.get(image_name)
+        sys.stderr.write(f"[{backend}] Image '{image_name}' is available locally\n")
+    except ImageNotFound:
+        sys.stderr.write(f"[{backend}] Pulling image '{image_name}'...\n")
+        client.images.pull(image_name)
+
+    # Launch the docker container to actually run the translated workflow
+    sys.stderr.write(f"[{backend}] Starting Docker container...\n")
+    container = client.containers.run(
+        image=image_name,
+        command=command,
+        volumes={mounted_dir: {'bind': mounted_dir, 'mode': 'rw'}},
+        working_dir=working_dir,
+        tty=True,
+        detach=True
+    )
+
+    # Installing WfCommons on container
+    _install_WfCommons_on_container(container)
+
+    # Copy over the wfbench and cpu-benchmark executables to where they should go on the container
+    if bin_dir:
+        sys.stderr.write(f"[{backend}] Copying wfbench and cpu-benchmark...\n")
+        exit_code, output = container.exec_run(["sh", "-c", "sudo cp -f `which wfbench` " + bin_dir],
+                                               stdout=True, stderr=True)
+        if exit_code != 0:
+            raise RuntimeError("Failed to copy wfbench script to the bin directory")
+
+        exit_code, output = container.exec_run(["sh", "-c", "sudo cp -f `which cpu-benchmark` " + bin_dir],
+                                               stdout=True, stderr=True)
+        if exit_code != 0:
+            raise RuntimeError("Failed to copy cpu-benchmark executable to the bin directory")
+    else:
+        sys.stderr.write(f"[{backend}] Not Copying wfbench and cpu-benchmark...\n")
+
+    # Change file permissions
+    exit_code, output = container.exec_run(["sh", "-c", "sudo chown -R wfcommons:wfcommons "],
+                                           stdout=True, stderr=True)
+
+
+    container.backend = backend
+    return container
+
+def _shutdown_docker_container_and_remove_image(container):
+    image = container.image
+    sys.stderr.write(f"[{container.backend}] Terminating container if need be...\n")
+    try:
+        container.stop()
+        container.remove()
+    except Exception as e:
+        pass
+
+    # Remove the images as we go, if running on GitHub
+    if os.getenv('CI') or os.getenv('GITHUB_ACTIONS'):
+        sys.stderr.write(f"[{container.backend}] Removing Docker image...\n")
+        try:
+            image.remove(force=True)
+        except Exception as e:
+            sys.stderr.write(f"[{container.backend}] Warning: Error while removing image: {e}\n")
+
+def _get_total_size_of_directory(directory_path: str):
+    total_size = 0
+    for dirpath, dirnames, filenames in os.walk(directory_path):
+        for filename in filenames:
+            filepath = os.path.join(dirpath, filename)
+            total_size += os.path.getsize(filepath)
+    return total_size
+
+def _compare_workflows(workflow_1: Workflow, workflow_2: Workflow):
+    
+    # Test the number of tasks
+    assert (len(workflow_1.tasks) == len(workflow_2.tasks))
+    # Test the task graph topology
+    assert (networkx.is_isomorphic(workflow_1, workflow_2))
+    # Test the total file size sum
+    workflow1_input_bytes, workflow2_input_bytes = 0, 0
+    workflow1_output_bytes, workflow2_output_bytes = 0, 0
+    for workflow1_task, workflow2_task in zip(workflow_1.tasks.values(), workflow_2.tasks.values()):
+        # sys.stderr.write(f"WORKFLOW1: {workflow1_task.task_id}  WORKFLOW2 TASK: {workflow2_task.task_id}\n")
+        for input_file in workflow1_task.input_files:
+            # sys.stderr.write(f"WORKFLOW1 INPUT FILE: {input_file.file_id} {input_file.size}\n")
+            workflow1_input_bytes += input_file.size
+        for input_file in workflow2_task.input_files:
+            # sys.stderr.write(f"WORKFLOW2 INPUT FILE: {input_file.file_id} {input_file.size}\n")
+            workflow2_input_bytes += input_file.size
+        for output_file in workflow1_task.output_files:
+            # sys.stderr.write(f"WORKFLOW1 OUTPUT FILE: {output_file.file_id} {output_file.size}\n")
+            workflow1_output_bytes += output_file.size
+        for output_file in workflow2_task.output_files:
+            # sys.stderr.write(f"WORKFLOW2 OUTPUT FILE: {output_file.file_id} {output_file.size}\n")
+            workflow2_output_bytes += output_file.size
+    assert (workflow1_input_bytes == workflow2_input_bytes)
+    assert (workflow1_output_bytes == workflow2_output_bytes)

{wfcommons-1.2 → wfcommons-1.4}/wfcommons/__init__.py

@@ -16,7 +16,7 @@ __credits__ = 'University of Hawaii at Manoa, Oak Ridge National Laboratoy, San
 import logging
 
 from .wfchef.recipes import BlastRecipe, BwaRecipe, CyclesRecipe, EpigenomicsRecipe, GenomeRecipe, MontageRecipe, \
-    SeismologyRecipe, SoykbRecipe, SrasearchRecipe
+    RnaseqRecipe, SeismologyRecipe, SoykbRecipe, SrasearchRecipe
 from .wfgen import WorkflowGenerator
 from .wfinstances import Instance, InstanceAnalyzer, InstanceElement
 

{wfcommons-1.2 → wfcommons-1.4}/wfcommons/common/__init__.py

@@ -9,6 +9,6 @@
 # (at your option) any later version.
 
 from .workflow import Workflow
-from .file import File, FileLink
+from .file import File
 from .task import Task, TaskType
 from .machine import Machine, MachineSystem

{wfcommons-1.2 → wfcommons-1.4}/wfcommons/common/file.py

@@ -16,12 +16,6 @@ from typing import Dict, Optional, Union
 from ..utils import NoValue
 
 
-class FileLink(NoValue):
-    """Type of file link."""
-    INPUT = "input"
-    OUTPUT = "output"
-
-
 class File:
     """Representation of a file.
 
@@ -29,28 +23,24 @@ class File:
     :type file_id: str
     :param size: File size in bytes.
     :type size: int
-    :param link: Type of file link.
-    :type link: FileLink
     :param logger: The logger where to log information/warning or errors.
     :type logger: Optional[Logger]
     """
 
     def __init__(self, file_id: str, 
                  size: int, 
-                 link: FileLink, 
                  logger: Optional[Logger] = None) -> None:
         """A file used by tasks."""
         self.logger: Logger = logger if logger else logging.getLogger(__name__)
 
         self.file_id: str = file_id
         self.size: int = size
-        self.link: FileLink = link
 
-    def as_dict(self) -> Dict[str, Union[str, int, FileLink]]:
+    def as_dict(self) -> Dict[str, Union[str, int]]:
         """A JSON representation of the file.
 
         :return: A JSON object representation of the file.
-        :rtype: Dict[str, Union[str, int, FileLink]]
+        :rtype: Dict[str, Union[str, int]]
         """
         return {
             'id': self.file_id,