bbmapy 0.0.2__tar.gz

bbmapy-0.0.2/.github/workflows/python-publish.yml

@@ -0,0 +1,39 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python#publishing-to-package-registries
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  contents: read
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install build
+    - name: Build package
+      run: python -m build
+    - name: Publish package
+      uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+      with:
+        user: __token__
+        password: ${{ secrets.PYPI_API_TOKEN }}

bbmapy-0.0.2/.gitignore

@@ -0,0 +1,164 @@
+# vendor
+test
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

bbmapy-0.0.2/LICENSE

@@ -0,0 +1 @@
+

bbmapy-0.0.2/PKG-INFO

@@ -0,0 +1,148 @@
+Metadata-Version: 2.1
+Name: bbmapy
+Version: 0.0.2
+Summary: A Python wrapper for BBTools
+License: 
+        
+Project-URL: Homepage, https://github.com/urineri/bbmapy
+Project-URL: Repository, https://github.com/urineri/bbmapy.git
+Project-URL: BBTools Repository, https://bitbucket.org/berkeleylab/jgi-bbtools/src/master/
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3.10
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: rich>=10.0.0
+
+# ppby
+
+A Python wrapper for BBTools.
+
+## Installation
+1. Lazy way - Clone this repository, download bbmap, and install the package:
+   ```
+   git clone https://github.com/urineri/ppby.git
+   cd ppby
+   cd vendor
+   rm bb* -rf
+   wget https://sourceforge.net/projects/bbmap/files/latest/download -O bbtools.tar.gz
+   tar -xf bbtools.tar.gz
+   cd ..
+   pip install -e .
+   generate-ppby-commands
+   ```
+   
+2. Unlazy way - is commented out below this line, that's how much it isn't suggested.
+<!-- Add the BBTools submodule:
+   ```
+   git submodule add https://bitbucket.org/berkeleylab/jgi-bbtools.git vendor/bbtools
+   ```
+
+3. Initialize and update the submodule:
+   ```
+   git submodule init
+   git submodule update
+   ```
+
+4. Install the package:
+   ```
+   pip install .
+   ```
+
+5. Generate the commands:
+   ```
+   generate-ppby-commands
+   ```
+6. Now actually delete the git submodule in vendor and replace it with the sourceforge version (i.e. the lazy way):
+```
+cd vendor/
+rm bb* -rf
+wget https://sourceforge.net/projects/bbmap/files/latest/download -O bbtools.tar.gz
+tar -xf bbtools.tar.gz
+
+``` -->
+<!-- 
+Note: Steps 2 and 3 are only necessary if you're setting up the project for the first time or if the submodule hasn't been added yet. If you're cloning the repository and the submodule has already been added, you can use: -->
+<!-- 
+```
+git clone --recurse-submodules https://github.com/yourusername/ppby.git
+```
+
+This will clone the repository and initialize the submodule in one step... I think? -->
+
+
+
+## Dependencies
+- Java  
+- BBmap  (the above steps should download it to the vendor subdirectory...).  
+If you rather this to use your own bbmap etc, go to the base.py script and comment out line 51, then uncomment line 52.
+- rich (for pretty printing)
+
+## Usage
+
+After installation, you can use ppby in your Python scripts like this:
+
+```python
+from ppby import bbduk
+
+# Basic usage
+bbduk(
+    in_file="input.fastq",
+    out="output.fastq",
+    ktrim="r",
+    k="23",
+    mink="11",
+    hdist="1",
+    tbo=True,
+    tpe=True,
+    minlen="45",
+    ref="adapters",
+    ftm="5",
+    maq="6",
+    maxns="1",
+    ordered=True,
+    threads="4",
+    overwrite="t",
+    stats="stats.txt"
+)
+
+# Using Java flags alongside other arguments
+bbduk(
+    Xmx="2g",  # Set maximum heap size
+    da=True,   # Enable assertions
+    eoom=True, # Enable out-of-memory termination
+    in_file="input.fastq",
+    out="output.fastq",
+    ktrim="r",
+    k="23"
+)
+
+# To capture output
+stdout, stderr = bbduk(
+    capture_output=True,
+    Xmx="2g",
+    in_file="input.fastq",
+    out="stdout.fastq",
+    # ... other parameters ...
+)
+```
+
+#### Notes:
+ * `in` can be a protected word in python and other code, it is replaced by `in_file` in function calls. `in1`, `in2` are still valid.
+ * Java flags (such as `Xmx`, `Xms`, `da`, `ea`, `eoom`) are automatically recognized and handled appropriately. Include them in your function calls just like any other argument.
+ * the `capture_output` argument might be switched (stderr --> out and vice verse). 
+ 
+
+
+## License
+
+This project is only a wrapper, please see the actual bbtools repository for license etc.  
+Neither the developers of bbtools nor of ppby take any responsibility for how you use this code. All accountability is on you.
+
+## Acknowledgments
+
+This project only (crudely) wraps BBTools (a.k.a bbmap), which is developed by Brian Bushnell.  
+If you use ppby and things don't quite work like you'd like, don't expect the developer of bbmap to help you with this whacky python wrapper.  
+If 
+Please see the [BBTools website](https://jgi.doe.gov/data-and-tools/bbtools/) for more information about the underlying tools.  

bbmapy-0.0.2/README.md

@@ -0,0 +1,131 @@
+# ppby
+
+A Python wrapper for BBTools.
+
+## Installation
+1. Lazy way - Clone this repository, download bbmap, and install the package:
+   ```
+   git clone https://github.com/urineri/ppby.git
+   cd ppby
+   cd vendor
+   rm bb* -rf
+   wget https://sourceforge.net/projects/bbmap/files/latest/download -O bbtools.tar.gz
+   tar -xf bbtools.tar.gz
+   cd ..
+   pip install -e .
+   generate-ppby-commands
+   ```
+   
+2. Unlazy way - is commented out below this line, that's how much it isn't suggested.
+<!-- Add the BBTools submodule:
+   ```
+   git submodule add https://bitbucket.org/berkeleylab/jgi-bbtools.git vendor/bbtools
+   ```
+
+3. Initialize and update the submodule:
+   ```
+   git submodule init
+   git submodule update
+   ```
+
+4. Install the package:
+   ```
+   pip install .
+   ```
+
+5. Generate the commands:
+   ```
+   generate-ppby-commands
+   ```
+6. Now actually delete the git submodule in vendor and replace it with the sourceforge version (i.e. the lazy way):
+```
+cd vendor/
+rm bb* -rf
+wget https://sourceforge.net/projects/bbmap/files/latest/download -O bbtools.tar.gz
+tar -xf bbtools.tar.gz
+
+``` -->
+<!-- 
+Note: Steps 2 and 3 are only necessary if you're setting up the project for the first time or if the submodule hasn't been added yet. If you're cloning the repository and the submodule has already been added, you can use: -->
+<!-- 
+```
+git clone --recurse-submodules https://github.com/yourusername/ppby.git
+```
+
+This will clone the repository and initialize the submodule in one step... I think? -->
+
+
+
+## Dependencies
+- Java  
+- BBmap  (the above steps should download it to the vendor subdirectory...).  
+If you rather this to use your own bbmap etc, go to the base.py script and comment out line 51, then uncomment line 52.
+- rich (for pretty printing)
+
+## Usage
+
+After installation, you can use ppby in your Python scripts like this:
+
+```python
+from ppby import bbduk
+
+# Basic usage
+bbduk(
+    in_file="input.fastq",
+    out="output.fastq",
+    ktrim="r",
+    k="23",
+    mink="11",
+    hdist="1",
+    tbo=True,
+    tpe=True,
+    minlen="45",
+    ref="adapters",
+    ftm="5",
+    maq="6",
+    maxns="1",
+    ordered=True,
+    threads="4",
+    overwrite="t",
+    stats="stats.txt"
+)
+
+# Using Java flags alongside other arguments
+bbduk(
+    Xmx="2g",  # Set maximum heap size
+    da=True,   # Enable assertions
+    eoom=True, # Enable out-of-memory termination
+    in_file="input.fastq",
+    out="output.fastq",
+    ktrim="r",
+    k="23"
+)
+
+# To capture output
+stdout, stderr = bbduk(
+    capture_output=True,
+    Xmx="2g",
+    in_file="input.fastq",
+    out="stdout.fastq",
+    # ... other parameters ...
+)
+```
+
+#### Notes:
+ * `in` can be a protected word in python and other code, it is replaced by `in_file` in function calls. `in1`, `in2` are still valid.
+ * Java flags (such as `Xmx`, `Xms`, `da`, `ea`, `eoom`) are automatically recognized and handled appropriately. Include them in your function calls just like any other argument.
+ * the `capture_output` argument might be switched (stderr --> out and vice verse). 
+ 
+
+
+## License
+
+This project is only a wrapper, please see the actual bbtools repository for license etc.  
+Neither the developers of bbtools nor of ppby take any responsibility for how you use this code. All accountability is on you.
+
+## Acknowledgments
+
+This project only (crudely) wraps BBTools (a.k.a bbmap), which is developed by Brian Bushnell.  
+If you use ppby and things don't quite work like you'd like, don't expect the developer of bbmap to help you with this whacky python wrapper.  
+If 
+Please see the [BBTools website](https://jgi.doe.gov/data-and-tools/bbtools/) for more information about the underlying tools.  

bbmapy-0.0.2/bbmapy/__init__.py

@@ -0,0 +1,9 @@
+import os
+from bbmapy.scanner import scan_bbtools
+
+# Generate commands.py if it doesn't exist
+if not os.path.exists(os.path.join(os.path.dirname(__file__), "commands.py")):
+    scan_bbtools()
+
+# Import all functions from commands
+from bbmapy.commands import *

bbmapy-0.0.2/bbmapy/_version.py

@@ -0,0 +1,16 @@
+# file generated by setuptools_scm
+# don't change, don't track in version control
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from typing import Tuple, Union
+    VERSION_TUPLE = Tuple[Union[int, str], ...]
+else:
+    VERSION_TUPLE = object
+
+version: str
+__version__: str
+__version_tuple__: VERSION_TUPLE
+version_tuple: VERSION_TUPLE
+
+__version__ = version = '0.1.dev7+ge98552b.d20240903'
+__version_tuple__ = version_tuple = (0, 1, 'dev7', 'ge98552b.d20240903')

bbmapy-0.0.2/bbmapy/base.py

@@ -0,0 +1,78 @@
+import os
+import sys
+import subprocess
+from typing import List, Dict, Union, Tuple
+from rich import print as rprint
+
+def find_bbtools_path():
+    # Check if we're running from an installed package
+    if getattr(sys, 'frozen', False):
+        # We're running from a bundle (e.g., PyInstaller)
+        base_path = sys._MEIPASS
+    else:
+        # We're running from a normal Python environment
+        base_path = os.path.abspath(os.path.dirname(__file__))
+    
+    # Navigate up to the project root
+    while not os.path.exists(os.path.join(base_path, 'vendor')):
+        base_path = os.path.dirname(base_path)
+        if base_path == os.path.dirname(base_path):  # We've reached the root directory
+            raise FileNotFoundError("Could not find BBTools directory")
+    
+    bbtools_path = os.path.join(base_path, 'vendor', 'bbmap')
+    
+    if not os.path.exists(bbtools_path):
+        raise FileNotFoundError(f"BBTools directory not found at {bbtools_path}")
+    
+    return bbtools_path
+
+BBTOOLS_PATH = find_bbtools_path()
+os.environ["PATH"] = f"{BBTOOLS_PATH}/current/:{os.environ["PATH"]}"
+
+def _pack_args(kwargs: Dict[str, Union[str, bool, int]]) -> List[str]:
+    args = []
+    
+    for key, value in kwargs.items():
+        if key in ['Xmx', 'Xms', 'da', 'ea', 'eoom']:
+            if isinstance(value, bool) and value:
+                args.append(f"-{key}")
+            elif value is not None:
+                args.append(f"-{key}{value}")
+        elif key == "in_file":
+            args.append(f"in={value}")
+        elif isinstance(value, bool) and value:
+            args.append(key)
+        elif value is not None:
+            args.append(f"{key}={value}")
+    
+    return args
+
+def _run_command(tool: str, args: List[str], capture_output: bool = False) -> Union[None, Tuple[str, str]]:
+    command = [os.path.join(BBTOOLS_PATH,tool)] + args # ,
+    # command = [tool] + args # ,
+
+    
+    if capture_output:
+        result = subprocess.run(command, capture_output=True, text=True)
+        if result.returncode != 0:
+            raise RuntimeError(f"Command failed: {' '.join(command)}\nError: {result.stderr}")
+        return result.stdout, result.stderr
+    else:
+        process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
+        
+        while True:
+            stdout_line = process.stdout.readline()
+            stderr_line = process.stderr.readline()
+            
+            if not stdout_line and not stderr_line and process.poll() is not None:
+                break
+            
+            if stdout_line:
+                rprint(stdout_line.strip())
+            if stderr_line:
+                rprint("[bold red]" + stderr_line.strip() + "[/bold red]")
+        
+        if process.returncode != 0:
+            raise RuntimeError(f"Command failed: {' '.join(command)}")
+        
+        return None