bbmapy 0.0.41__tar.gz → 0.0.43__tar.gz

bbmapy-0.0.43/.gitignore

@@ -0,0 +1,175 @@
+# vendor
+# bbmapy/vendor/  # Commented out to allow vendor directory in package
+test
+.vscode/**  
+.cursorignore
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+.vscode
+.pypirc
+.pypi
+.pypi-version
+
+# 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/
+.vscode/settings.json
+.vscode/settings.json
+.vscode/settings.json

bbmapy-0.0.43/PKG-INFO

@@ -0,0 +1,153 @@
+Metadata-Version: 2.4
+Name: bbmapy
+Version: 0.0.43
+Summary: A Python wrapper for BBTools
+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/
+License: see https://bitbucket.org/berkeleylab/jgi-bbtools/src/master/license.txt
+License-File: LICENSE
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3.9
+Requires-Python: >=3.9
+Requires-Dist: install-jdk
+Requires-Dist: rich
+Description-Content-Type: text/markdown
+
+# bbmapy
+
+A Python wrapper for BBTools.
+Current version of bbmapy is v39.20.
+
+## Installation
+
+```bash
+conda install -c bioconda -c conda-forge bbmapy # not yet available on conda-forge
+```  
+Also available on pip (but does not ensure java is available):
+```bash
+pip install bbmapy
+```
+
+## Usage
+
+bbmapy let's you call bbtools stuff from python. To the shell only one CLI is available:  
+- `bbmapy-test`: Run tests to verify installation
+
+### Example
+
+```python
+from bbmapy import bbmap
+
+# Run bbmap.sh
+bbmap.bbmap(
+    in1="reads1.fastq",
+    in2="reads2.fastq",
+    out="mapped.sam",
+    ref="reference.fasta"
+)
+```
+
+## Dependencies
+
+- Python >= 3.9
+- rich
+- install-jdk (this will be used to install a JRE if needed)
+
+## Usage
+
+After installation, you can use bbmapy in your Python scripts like this:
+
+```python
+from bbmapy 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
+```python
+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
+You need to set `capture_output=True` in the function call, AND out="stdout.fastq" (or any other file format you like). 
+```python
+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). 
+ * Flags (i.e. argument that do not take value in the OG bbmap version) are set with Boolean values. e.g.:
+ ``` 
+ flag : True
+ ```
+ Not to be mistaken for lower case, fouble qouted `"true"` and `"false"` for boolian arguments to be passed to bbtools, e.g.:
+ ```
+ argument : "true"
+ ```
+ 
+### Citation
+BBMerge manuscript: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0185056
+Please cite this paper if you use bbmap in your work.
+
+
+
+## License
+
+This project is only a wrapper, please see the actual bbtools repository for (license)[https://bitbucket.org/berkeleylab/jgi-bbtools/src/master/license.txt] etc.  
+Neither the developers of bbtools nor of bbmapy 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 bbmapy 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.  
+
+
+### to build and upload to pypi
+
+```bash
+rm -rf dist build egg-info
+python bbmapy/update.py # fetch latest version of bbtools and update version in pyproject.toml
+rm bbmapy/vendor/bbmap/pytools -rf # remove the pytools folder
+pip install --upgrade build twine
+python -m build
+twine upload dist/*
+
+```

bbmapy-0.0.43/README.md

@@ -0,0 +1,136 @@
+# bbmapy
+
+A Python wrapper for BBTools.
+Current version of bbmapy is v39.20.
+
+## Installation
+
+```bash
+conda install -c bioconda -c conda-forge bbmapy # not yet available on conda-forge
+```  
+Also available on pip (but does not ensure java is available):
+```bash
+pip install bbmapy
+```
+
+## Usage
+
+bbmapy let's you call bbtools stuff from python. To the shell only one CLI is available:  
+- `bbmapy-test`: Run tests to verify installation
+
+### Example
+
+```python
+from bbmapy import bbmap
+
+# Run bbmap.sh
+bbmap.bbmap(
+    in1="reads1.fastq",
+    in2="reads2.fastq",
+    out="mapped.sam",
+    ref="reference.fasta"
+)
+```
+
+## Dependencies
+
+- Python >= 3.9
+- rich
+- install-jdk (this will be used to install a JRE if needed)
+
+## Usage
+
+After installation, you can use bbmapy in your Python scripts like this:
+
+```python
+from bbmapy 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
+```python
+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
+You need to set `capture_output=True` in the function call, AND out="stdout.fastq" (or any other file format you like). 
+```python
+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). 
+ * Flags (i.e. argument that do not take value in the OG bbmap version) are set with Boolean values. e.g.:
+ ``` 
+ flag : True
+ ```
+ Not to be mistaken for lower case, fouble qouted `"true"` and `"false"` for boolian arguments to be passed to bbtools, e.g.:
+ ```
+ argument : "true"
+ ```
+ 
+### Citation
+BBMerge manuscript: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0185056
+Please cite this paper if you use bbmap in your work.
+
+
+
+## License
+
+This project is only a wrapper, please see the actual bbtools repository for (license)[https://bitbucket.org/berkeleylab/jgi-bbtools/src/master/license.txt] etc.  
+Neither the developers of bbtools nor of bbmapy 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 bbmapy 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.  
+
+
+### to build and upload to pypi
+
+```bash
+rm -rf dist build egg-info
+python bbmapy/update.py # fetch latest version of bbtools and update version in pyproject.toml
+rm bbmapy/vendor/bbmap/pytools -rf # remove the pytools folder
+pip install --upgrade build twine
+python -m build
+twine upload dist/*
+
+```

bbmapy-0.0.43/bbmapy/base.py

@@ -0,0 +1,124 @@
+import os
+import site
+import subprocess
+# import sys
+from typing import List, Dict, Union, Tuple
+from rich import print as rprint
+from rich.markup import escape
+# from pathlib import Path
+
+# Initialize global variables
+BBTOOLS_PATH = None
+
+def find_bbtools_path():
+    """
+    Find the BBTools directory by checking multiple possible locations.
+    Returns the path to the BBTools directory or None if not found.
+    """
+    # Get the directory of the current file
+    current_dir = os.path.dirname(os.path.abspath(__file__))
+    
+    # List of possible paths to check
+    possible_paths = [
+        # Check vendor directory relative to this file
+        os.path.join(current_dir, "vendor", "bbmap"),
+        # Check site-packages directory
+        os.path.join(site.getsitepackages()[0], "bbmapy", "vendor", "bbmap"),
+        # Check parent directories
+        os.path.join(os.path.dirname(current_dir), "vendor", "bbmap"),
+        # Check current working directory
+        os.path.join(os.getcwd(), "vendor", "bbmap"),
+    ]
+    
+    # Add conda environment paths if available
+    if 'CONDA_PREFIX' in os.environ:
+        conda_prefix = os.environ['CONDA_PREFIX']
+        possible_paths.extend([
+            os.path.join(conda_prefix, "lib", "python3.*", "site-packages", "bbmapy", "vendor", "bbmap"),
+            os.path.join(conda_prefix, "vendor", "bbmap"),
+        ])
+    
+    # Check each path
+    for path in possible_paths:
+        # Handle glob patterns in path
+        if '*' in path:
+            import glob
+            matches = glob.glob(path)
+            for match in matches:
+                if os.path.exists(match) and os.path.isdir(match):
+                    return match
+        else:
+            if os.path.exists(path) and os.path.isdir(path):
+                return path
+    
+    # If no path is found, return None
+    return None
+
+try:
+    BBTOOLS_PATH = find_bbtools_path()  
+    os.environ["PATH"] = f"{BBTOOLS_PATH}/:{os.environ['PATH']}"
+except FileNotFoundError as e:
+    rprint(f"[red]Error: {e}[/red]")
+    # Don't exit here, as this might be imported before bbtools is installed
+    # We'll check again when functions are actually called
+
+def _pack_args(kwargs: Dict[str, Union[str, bool, int]]) -> List[str]:
+    """Convert Python keyword arguments to BBTools command line arguments."""
+    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}{str(value)}")
+        elif key == "in_file":
+            args.append(f"in={str(value)}")
+        elif isinstance(value, bool) and value:
+            args.append(key)
+        elif value is not None:
+            args.append(f"{key}={str(value)}")
+    
+    return args
+
+
+def _run_command(tool: str, args: List[str], capture_output: bool = False) -> Union[None, Tuple[str, str]]:
+    """Run a BBTools command using subprocess (fallback method)."""
+
+    # Find the BBTools path if not already set
+    global BBTOOLS_PATH
+    if BBTOOLS_PATH is None:
+        BBTOOLS_PATH = find_bbtools_path()
+        if BBTOOLS_PATH is None:
+            raise RuntimeError("BBTools directory not found.")
+        os.environ["PATH"] = f"{BBTOOLS_PATH}/current/:{os.environ['PATH']}"
+    
+    # Build the command
+    command = [os.path.join(BBTOOLS_PATH, tool)] + args
+    escaped_command = ' '.join(escape(str(arg)) for arg in command)
+    
+    if capture_output:
+        result = subprocess.run(command, capture_output=True, text=True)
+        if result.returncode != 0:
+            raise RuntimeError(f"Command failed: {escaped_command}\nError: {escape(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(escape(stdout_line.strip()))
+            if stderr_line:
+                rprint("[bold red]" + escape(stderr_line.strip()) + "[/bold red]")
+        
+        if process.returncode != 0:
+            raise RuntimeError(f"Command failed: {escaped_command}")
+        
+        return None
+