impc-api 2.0.0__tar.gz → 2.1.0__tar.gz

{impc_api-2.0.0 → impc_api-2.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: impc_api
-Version: 2.0.0
+Version: 2.1.0
 Summary: A package to facilitate making API requests to the IMPC Solr API
 Author: MPI2, Marina Kan, Diego Pava
 License-Expression: Apache-2.0
@@ -11,7 +11,7 @@ Requires-Dist: pandas>=2.2.0
 Requires-Dist: requests>=2.33.0
 Requires-Dist: tqdm>=4.66.4
 Requires-Dist: pydantic>=2.9
-Requires-Python: >=3.10
+Requires-Python: >=3.12
 Project-URL: Homepage, https://github.com/mpi2/impc-api
 Description-Content-Type: text/markdown
 
@@ -21,7 +21,8 @@ Description-Content-Type: text/markdown
 
 ## Installation Instructions
 
-0. Ensure that Python is installed on your system. The minimum required version is 3.10.
+0. Ensure that Python is installed on your system. The minimum required version is 3.12.
+   Python 3.10 will not be supported after version 2.0.0.
 
 1. **Create a virtual environment (optional but recommended)**:
 On Mac or Linux:
@@ -76,6 +77,17 @@ num_found, df = solr_request(
 )
 ```
 
+To use another compatible Solr deployment, override the base URL. The same
+argument is available on `batch_solr_request`:
+
+```python
+num_found, df = solr_request(
+    core='genotype-phenotype',
+    params={'q': '*:*', 'rows': 10},
+    base_url='http://solr-host:8983/solr',
+)
+```
+
 ## a. Facet request
 
 `solr_request` allows facet requests
@@ -258,4 +270,4 @@ get_core_fields("genotype-phenotype")
 
 The complete list is returned. An unknown core returns an empty list. Skills and
 other integrations should call this function instead of maintaining their own
-copies of core field names.
+copies of core field names.

{impc_api-2.0.0 → impc_api-2.1.0}/README.md

@@ -4,7 +4,8 @@
 
 ## Installation Instructions
 
-0. Ensure that Python is installed on your system. The minimum required version is 3.10.
+0. Ensure that Python is installed on your system. The minimum required version is 3.12.
+   Python 3.10 will not be supported after version 2.0.0.
 
 1. **Create a virtual environment (optional but recommended)**:
 On Mac or Linux:
@@ -59,6 +60,17 @@ num_found, df = solr_request(
 )
 ```
 
+To use another compatible Solr deployment, override the base URL. The same
+argument is available on `batch_solr_request`:
+
+```python
+num_found, df = solr_request(
+    core='genotype-phenotype',
+    params={'q': '*:*', 'rows': 10},
+    base_url='http://solr-host:8983/solr',
+)
+```
+
 ## a. Facet request
 
 `solr_request` allows facet requests
@@ -241,4 +253,4 @@ get_core_fields("genotype-phenotype")
 
 The complete list is returned. An unknown core returns an empty list. Skills and
 other integrations should call this function instead of maintaining their own
-copies of core field names.
+copies of core field names.

{impc_api-2.0.0 → impc_api-2.1.0}/impc_api/batch_solr_request.py

@@ -16,7 +16,7 @@ from impc_api.utils.warnings import (
     UnsupportedDownloadFormatError,
     LargeRequestMemoryWarning
 )
-from .solr_request import solr_request
+from .solr_request import DEFAULT_SOLR_BASE_URL, solr_request
 
 # Initialise warning config
 warning_config()
@@ -30,6 +30,7 @@ def batch_solr_request(
     download: bool = False,
     batch_size: int = 5000,
     filename: str = "batch_request",
+    base_url: str = DEFAULT_SOLR_BASE_URL,
 ) -> pd.DataFrame:
     """Function for large API requests (>1,000,000 results). Fetches the data in batches and
     produces a Pandas DataFrame or downloads a file in json or csv formats.
@@ -42,6 +43,8 @@ def batch_solr_request(
         download (bool, optional): True for download a local file, False to display results as a DataFrame. Defaults to False.
         batch_size (int, optional): Size of batches to fetch the data. Defaults to 5000.
         filename (str, optional): When download=True, select the name of the file. Defaults to 'batch_request'.
+        base_url (str, optional): default public IMPC Solr endpoint.
+            Override this to use another compatible Solr deployment.
 
 
     Returns:
@@ -81,7 +84,10 @@ def batch_solr_request(
 
     # Determine the total number of rows. Note that we do not request any data (rows = 0).
     num_results, _ = solr_request(
-        core=core, params={**params, "start": 0, "rows": 0, "wt": "json"}, silent=True
+        core=core,
+        params={**params, "start": 0, "rows": 0, "wt": "json"},
+        silent=True,
+        base_url=base_url,
     )
     print(f"Number of found documents: {num_results}")
 
@@ -95,7 +101,7 @@ def batch_solr_request(
             # Implement loop behaviour
             print("Downloading file...")
             filename_path = Path(f"{filename}.{params['wt']}")
-            gen = _batch_solr_generator(core, params, num_results)
+            gen = _batch_solr_generator(core, params, num_results, base_url=base_url)
             _solr_downloader(params, filename_path, gen)
             print(f"File saved as: {filename_path}")
         except UnsupportedDownloadFormatError as e:
@@ -117,11 +123,14 @@ def batch_solr_request(
             message="This request may exceed available memory. If the download fails, set 'download=True' and try again.",
             category=LargeRequestMemoryWarning,
         )
-    return _batch_to_df(core, params, num_results)
+    return _batch_to_df(core, params, num_results, base_url=base_url)
 
 # Helper batch_to_df
 def _batch_to_df(
-    core: str, params: Dict[str, Any], num_results: int
+    core: str,
+    params: Dict[str, Any],
+    num_results: int,
+    base_url: str = DEFAULT_SOLR_BASE_URL,
 ) -> pd.DataFrame:
     """Helper function to fetch data in batches and display them in a DataFrame
 
@@ -147,6 +156,7 @@ def _batch_to_df(
                 core=core,
                 params={**params, "start": start, "rows": batch_size},
                 silent=True,
+                base_url=base_url,
             )
 
             # Update progress bar with the number of rows requested.
@@ -161,7 +171,10 @@ def _batch_to_df(
 
 
 def _batch_solr_generator(
-    core: str, params: Dict[str, Any], num_results: int
+    core: str,
+    params: Dict[str, Any],
+    num_results: int,
+    base_url: str = DEFAULT_SOLR_BASE_URL,
 ) -> Iterator[BatchSolrChunk]:
     """Generator function to fetch results from the SOLR API in batches using pagination.
 
@@ -176,8 +189,7 @@ def _batch_solr_generator(
     Yields:
         ([dict, str]): A JSON object or plain text with the results.
     """
-    base_url = "https://www.ebi.ac.uk/mi/impc/solr/"
-    solr_url = base_url + core + "/select"
+    solr_url = f"{base_url.rstrip('/')}/{core}/select"
     start = params["start"]
     batch_size = params["rows"]
 

{impc_api-2.0.0 → impc_api-2.1.0}/impc_api/solr_request.py

@@ -13,6 +13,7 @@ SolrRequestResult = Optional[
 ]
 
 DEFAULT_REQUEST_TIMEOUT: RequestTimeout = 10.0
+DEFAULT_SOLR_BASE_URL = "https://www.ebi.ac.uk/mi/impc/solr/"
 
 # Display the whole dataframe <15
 pd.set_option("display.max_rows", 15)
@@ -26,6 +27,7 @@ def solr_request(
     validate: bool = False,
     url_only: bool = False,
     timeout: RequestTimeout = DEFAULT_REQUEST_TIMEOUT,
+    base_url: str = DEFAULT_SOLR_BASE_URL,
 ) -> SolrRequestResult:
     """Performs a single Solr request to the IMPC Solr API.
 
@@ -42,6 +44,8 @@ def solr_request(
             If true, returns the request URL but no data. 
         timeout (int or float, optional): default 10
             Number of seconds to wait for the API request before timing out.
+        base_url (str, optional): default public IMPC Solr endpoint.
+            Override this to use another compatible Solr deployment.
 
 
     Returns:
@@ -95,8 +99,7 @@ def solr_request(
     if validate:
         CoreParamsValidator(core=core, params=params)
 
-    base_url = "https://www.ebi.ac.uk/mi/impc/solr/"
-    solr_url = base_url + core + "/select"
+    solr_url = f"{base_url.rstrip('/')}/{core}/select"
 
     response = requests.get(solr_url, params=params, timeout=timeout)
 
@@ -176,7 +179,10 @@ def _process_faceting(data: Dict[str, Any], params: Dict[str, Any]) -> pd.DataFr
 
 # Batch request based on solr_request.
 def batch_request(
-    core: str, params: Dict[str, Any], batch_size: int
+    core: str,
+    params: Dict[str, Any],
+    batch_size: int,
+    base_url: str = DEFAULT_SOLR_BASE_URL,
 ) -> pd.DataFrame:
     """Calls `solr_request` multiple times with `params`
      to retrieve results in chunk `batch_size` rows at a time.
@@ -186,7 +192,8 @@ def batch_request(
     Args:
          core (str): name of IMPC solr core.
          params (dict): dictionary containing the API call parameters.
-         batch_size (int): Size of batches (number of docs) per request.
+        batch_size (int): Size of batches (number of docs) per request.
+        base_url (str, optional): default public IMPC Solr endpoint.
 
      Returns:
          pandas.DataFrame: Pandas.DataFrame object with the information requested.
@@ -208,7 +215,10 @@ def batch_request(
         )
     # Determine the total number of rows. Note that we do not request any data (rows = 0).
     num_results, _ = solr_request(
-        core=core, params={**params, "start": 0, "rows": 0}, silent=True
+        core=core,
+        params={**params, "start": 0, "rows": 0},
+        silent=True,
+        base_url=base_url,
     )
     # Initialise everything for data retrieval.
     start = 0
@@ -223,6 +233,7 @@ def batch_request(
                 core=core,
                 params={**params, "start": start, "rows": batch_size},
                 silent=True,
+                base_url=base_url,
             )
             # Record chunk.
             chunks.append(df_chunk)

{impc_api-2.0.0 → impc_api-2.1.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "impc_api"
-version = "2.0.0"
+version = "2.1.0"
 description = "A package to facilitate making API requests to the IMPC Solr API"
 license = "Apache-2.0"
 license-files = ["LICENSE"]
@@ -23,7 +23,7 @@ dependencies = [
 ]
 
 readme = "README.md"
-requires-python = ">=3.10"
+requires-python = ">=3.12"
 
 [dependency-groups]
 dev = [