scmcp-shared 0.1.0__tar.gz

scmcp_shared-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,49 @@
+name: Publishing
+on:
+  release:
+    types: [published]
+
+jobs:
+  release-build:
+    name: Build distribution
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          enable-cache: true
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v5
+        with:
+          python-version-file: "pyproject.toml"
+
+      - name: Build
+        run: uv build
+
+      - name: Upload artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: release-dists
+          path: dist/
+
+  pypi-publish:
+    name: Upload release to PyPI
+    runs-on: ubuntu-latest
+    environment: pypi
+    needs:
+      - release-build
+    permissions:
+      id-token: write # IMPORTANT: this permission is mandatory for trusted publishing
+
+    steps:
+      - name: Retrieve release distributions
+        uses: actions/download-artifact@v4
+        with:
+          name: release-dists
+          path: dist/
+
+      - name: Publish package distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

scmcp_shared-0.1.0/LICENSE

@@ -0,0 +1,28 @@
+BSD 3-Clause License
+
+Copyright (c) 2025, scmcphub
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

scmcp_shared-0.1.0/PKG-INFO

@@ -0,0 +1,44 @@
+Metadata-Version: 2.4
+Name: scmcp_shared
+Version: 0.1.0
+Summary: A shared function libray for scmcphub
+Author-email: shuang <hsh-me@outlook.com>
+License: BSD 3-Clause License
+        
+        Copyright (c) 2025, scmcphub
+        
+        Redistribution and use in source and binary forms, with or without
+        modification, are permitted provided that the following conditions are met:
+        
+        1. Redistributions of source code must retain the above copyright notice, this
+           list of conditions and the following disclaimer.
+        
+        2. Redistributions in binary form must reproduce the above copyright notice,
+           this list of conditions and the following disclaimer in the documentation
+           and/or other materials provided with the distribution.
+        
+        3. Neither the name of the copyright holder nor the names of its
+           contributors may be used to endorse or promote products derived from
+           this software without specific prior written permission.
+        
+        THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+        AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+        IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+        DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+        FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+        DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+        SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+        CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+        OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+        OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+License-File: LICENSE
+Requires-Python: >=3.10
+Requires-Dist: fastmcp>=2.3.0
+Requires-Dist: mcp>=1.8.0
+Requires-Dist: pydantic
+Requires-Dist: scanpy
+Description-Content-Type: text/markdown
+
+# scmcp-shared
+
+Shared functions for scmcphub

scmcp_shared-0.1.0/README.md

@@ -0,0 +1,3 @@
+# scmcp-shared
+
+Shared functions for scmcphub

scmcp_shared-0.1.0/pyproject.toml

@@ -0,0 +1,33 @@
+[project]
+name = "scmcp_shared"
+dynamic = ["version"] 
+description = "A shared function libray for scmcphub"
+readme = "README.md"
+license = { file = "LICENSE" }
+authors = [
+    { name = "shuang", email = "hsh-me@outlook.com" }
+]
+requires-python = ">=3.10"
+dependencies = [
+    "scanpy",
+    "mcp>=1.8.0",
+    "fastmcp>=2.3.0",
+    "pydantic",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+
+[dependency-groups]
+dev = [
+    "pytest>=8.3.4",
+]
+
+[tool.hatch.version]
+path = "src/scmcp_shared/__init__.py"  
+
+[tool.pytest.ini_options]
+asyncio_mode = "strict"
+asyncio_default_fixture_loop_scope = "function"

scmcp_shared-0.1.0/src/scmcp_shared/__init__.py

@@ -0,0 +1,3 @@
+
+__version__ = "0.1.0"
+

scmcp_shared-0.1.0/src/scmcp_shared/logging_config.py

@@ -0,0 +1,31 @@
+import logging
+import sys
+import os
+from .util import get_env
+
+def setup_logger(name="sc-mcp-server", log_file=None):
+
+    logger = logging.getLogger(name)
+    logger.setLevel(logging.INFO)
+    if logger.handlers:
+        return logger
+    
+    formatter = logging.Formatter(
+        '%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+        '%Y-%m-%d %H:%M:%S'
+    )
+    if log_file is None:
+        log_file = get_env("LOG_FILE")
+    if log_file:
+        log_handler = logging.FileHandler(log_file)
+        log_handler.setFormatter(formatter)
+        logger.addHandler(log_handler)
+        
+        logger.info(f"logging output: {log_file}")
+    else:
+        log_handler = logging.StreamHandler(sys.stdout)
+        log_handler.setFormatter(formatter)
+        logger.addHandler(log_handler)
+        logger.info(f"loggin file output: stdout")
+    return logger
+    

scmcp_shared-0.1.0/src/scmcp_shared/schema/__init__.py

@@ -0,0 +1 @@
+from  .io import *

scmcp_shared-0.1.0/src/scmcp_shared/schema/io.py

@@ -0,0 +1,120 @@
+from pydantic import (
+    Field,
+    ValidationInfo,
+    computed_field,
+    field_validator,
+    model_validator,
+    BaseModel
+)
+from typing import Optional, Union, Literal, Any, Sequence, Dict
+
+
+
+class ReadModel(BaseModel):
+    """Input schema for the read tool."""
+    filename: str = Field(
+        ...,
+        description="Path to the file to read."
+    )
+
+    backed: Literal['r', 'r+'] = Field(
+        default=None,
+        description="If 'r', load AnnData in 'backed' mode instead of fully loading it into memory ('memory' mode). If you want to modify backed attributes of the AnnData object, you need to choose 'r+'."
+    )
+    sheet: str = Field(
+        default=None,
+        description="Name of sheet/table in hdf5 or Excel file."
+    )
+    ext: str = Field(
+        default=None,
+        description="Extension that indicates the file type. If None, uses extension of filename."
+    )
+    delimiter: str = Field(
+        default=None,
+        description="Delimiter that separates data within text file. If None, will split at arbitrary number of white spaces, which is different from enforcing splitting at any single white space."
+    )
+    first_column_names: bool = Field(
+        default=False,
+        description="Assume the first column stores row names. This is only necessary if these are not strings: strings in the first column are automatically assumed to be row names."
+    )
+    first_column_obs: bool = Field(
+        default=True,
+        description="If True, assume the first column stores observations (cell or barcode) names when provide text file. If False, the data will be transposed."
+    )
+    backup_url: str = Field(
+        default=None,
+        description="Retrieve the file from an URL if not present on disk."
+    )
+    cache: bool = Field(
+        default=False,
+        description="If False, read from source, if True, read from fast 'h5ad' cache."
+    )
+    cache_compression: Literal['gzip', 'lzf'] = Field(
+        default=None,
+        description="See the h5py dataset_compression. (Default: settings.cache_compression)"
+    )
+    var_names: str = Field(
+        default="gene_symbols",
+        description="The variables index for 10x mtx format. Either 'gene_symbols' or 'gene_ids'."
+    )
+    make_unique: bool = Field(
+        default=True,
+        description="Whether to make the variables index unique by appending '-1', '-2' etc. or not. Used for 10x mtx format."
+    )
+    gex_only: bool = Field(
+        default=True,
+        description="Only keep 'Gene Expression' data and ignore other feature types, e.g. 'Antibody Capture', 'CRISPR Guide Capture', or 'Custom'. Used for 10x formats."
+    )
+    prefix: str = Field(
+        default=None,
+        description="Any prefix before matrix.mtx, genes.tsv and barcodes.tsv. For instance, if the files are named patientA_matrix.mtx, patientA_genes.tsv and patientA_barcodes.tsv the prefix is patientA_. Used for 10x mtx format."
+    )
+    
+    @field_validator('backed')
+    def validate_backed(cls, v: Optional[str]) -> Optional[str]:
+        if v is not None and v not in ['r', 'r+']:
+            raise ValueError("If backed is provided, it must be either 'r' or 'r+'")
+        return v
+    
+    @field_validator('cache_compression')
+    def validate_cache_compression(cls, v: Optional[str]) -> Optional[str]:
+        if v is not None and v not in ['gzip', 'lzf']:
+            raise ValueError("cache_compression must be either 'gzip', 'lzf', or None")
+        return v
+    
+    @field_validator('var_names')
+    def validate_var_names(cls, v: Optional[str]) -> Optional[str]:
+        if v is not None and v not in ['gene_symbols', 'gene_ids']:
+            raise ValueError("var_names must be either 'gene_symbols' or 'gene_ids'")
+        return v
+
+
+class WriteModel(BaseModel):
+    """Input schema for the write tool."""
+    filename: str = Field(
+        description="Path to save the file. If no extension is provided, the default format will be used."
+    )
+    ext: Literal['h5', 'csv', 'txt', 'npz'] = Field(
+        default=None,
+        description="File extension to infer file format. If None, defaults to scanpy's settings.file_format_data."
+    )
+    compression: Literal['gzip', 'lzf'] = Field(
+        default='gzip',
+        description="Compression format for h5 files."
+    )
+    compression_opts: int = Field(
+        default=None,
+        description="Compression options for h5 files."
+    )
+    
+    @field_validator('filename')
+    def validate_filename(cls, v: str) -> str:
+        # Allow any filename since the extension is optional and can be inferred
+        return v
+    
+    @model_validator(mode='after')
+    def validate_extension_compression(self) -> 'WriteInput':
+        # If ext is provided and not h5, compression should be None
+        if self.ext is not None and self.ext != 'h5' and self.compression is not None:
+            raise ValueError("Compression can only be used with h5 files")
+        return self