Merge pull request #66 from jjjermiah/development

Development

README.md

@@ -36,6 +36,26 @@ It is made available via PyPI and can be installed using pip:
 pip install nbiatoolkit
 ```
 
+## CLI Usage
+
+### getCollections
+nbia-toolkit also provides a command line interface (CLI) to query the NBIA database for some queries.
+``` bash
+> getCollections --prefix NSCLC
+NSCLC Radiogenomics
+NSCLC-Radiomics
+NSCLC-Radiomics-Genomics
+NSCLC-Radiomics-Interobserver1
+
+> getCollections --prefix TCGA | head -5
+TCGA-BLCA
+TCGA-BRCA
+TCGA-CESC
+TCGA-COAD
+TCGA-ESCA
+```
+
+
 ## Contributing
 
 Interested in contributing? Check out the contributing guidelines. Please note that this project is released with a Code of Conduct. By contributing to this project, you agree to abide by its terms.

pyproject.toml

@@ -9,6 +9,11 @@ readme = "README.md"
 [tool.poetry.scripts]
 DICOMSorter = "nbiatoolkit.dicomsort:DICOMSorter_cli"
 NBIAToolkit = "nbiatoolkit:version"
+getCollections = "nbiatoolkit.nbia_cli:getCollections_cli"
+getPatients = "nbiatoolkit.nbia_cli:getPatients_cli"
+getBodyPartCounts = "nbiatoolkit.nbia_cli:getBodyPartCounts_cli"
+downloadSingleSeries = "nbiatoolkit.nbia_cli:downloadSingleSeries_cli"
+getSeries = "nbiatoolkit.nbia_cli:getSeries_cli"
 
 [tool.poetry.dependencies]
 python = ">=3.11 || 3.12"

src/nbiatoolkit/__init__.py

@@ -8,7 +8,8 @@
 
 
 # import the modules
-from .nbia import NBIAClient, version
+from .nbia import NBIAClient
+from .nbia_cli import version, getCollections_cli
 from .auth import OAuth2
 from .logger.logger import setup_logger
 from .utils.nbia_endpoints import NBIA_ENDPOINTS

src/nbiatoolkit/dicomsort/__init__.py

@@ -10,4 +10,10 @@
 from .dicomsort import DICOMSorter, DICOMSorter_cli
 from .helper_functions import parseDICOMKeysFromFormat, sanitizeFileName, truncateUID
 
-__all__ = ["DICOMSorter", "parseDICOMKeysFromFormat", "sanitizeFileName", "truncateUID", "DICOMSorter_cli"]
+__all__ = [
+    "DICOMSorter",
+    "parseDICOMKeysFromFormat",
+    "sanitizeFileName",
+    "truncateUID",
+    "DICOMSorter_cli",
+]

src/nbiatoolkit/dicomsort/dicomsort.py

@@ -11,6 +11,7 @@
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from tqdm import tqdm
 
+
 class DICOMSorter:
     def __init__(
         self,
@@ -80,7 +81,7 @@ def sortSingleDICOMFile(
         if os.path.exists(targetFilename) and not overwrite:
             print(f"Source File: {filePath}\n")
             print(f"File {targetFilename} already exists. ")
-            sys.exit(
+            raise ValueError(
                 "Pattern is probably not unique or overwrite is set to False. Exiting."
             )
 
@@ -95,20 +96,25 @@ def sortSingleDICOMFile(
 
         return True
 
-    def sortDICOMFiles(self, option: str = "copy", overwrite: bool = False, nParallel: int = 1) -> bool:
+    def sortDICOMFiles(
+        self, option: str = "copy", overwrite: bool = False, nParallel: int = 1
+    ) -> bool:
         dicom_file_paths = self._get_dicom_files()
         result = []
         print("Running with {} parallel threads".format(nParallel))
 
         with ThreadPoolExecutor(max_workers=nParallel) as executor:
-            futures = [executor.submit(self.sortSingleDICOMFile, filePath, option, overwrite) for filePath in dicom_file_paths]
+            futures = [
+                executor.submit(self.sortSingleDICOMFile, filePath, option, overwrite)
+                for filePath in dicom_file_paths
+            ]
 
             for future in tqdm(as_completed(futures), total=len(futures)):
                 result.append(future.result())
 
         return all(result)
-    
-    def _get_dicom_files(self) -> 'list[str]':
+
+    def _get_dicom_files(self) -> "list[str]":
         dicom_file_paths = []
         # Iterate over all files in the source directory
         for root, dirs, files in os.walk(self.sourceDir):
@@ -119,67 +125,77 @@ def _get_dicom_files(self) -> 'list[str]':
 
         return dicom_file_paths
 
+
 # Create command line interface
 
 # Given a source directory, destination directory, and target pattern, sort DICOM files
 # into the destination directory according to the target pattern.
 # The target pattern is a string with placeholders matching '%<DICOMKey>'.
 
+
 def DICOMSorter_cli():
     parser = argparse.ArgumentParser(
         description="Sort DICOM files into destination directory according to target pattern."
     )
 
-    parser.add_argument("sourceDir",
+    parser.add_argument(
+        "sourceDir",
         metavar="sourceDir",
         type=str,
         help="The source directory containing DICOM files.",
     )
 
-    parser.add_argument("destinationDir",
+    parser.add_argument(
+        "destinationDir",
         metavar="destinationDir",
         type=str,
         help="The destination directory to sort DICOM files into.",
     )
 
     # Default is %%PatientName/%%SeriesNumber-%%SeriesInstanceUID/%%InstanceNumber.dcm
-    parser.add_argument("--targetPattern",
+    parser.add_argument(
+        "--targetPattern",
         dest="targetPattern",
         default="%PatientName/%SeriesNumber-%SeriesInstanceUID/%InstanceNumber.dcm",
         type=str,
-        help='The target pattern for sorting DICOM files. Default is %%PatientName/%%SeriesNumber-%%SeriesInstanceUID/%%InstanceNumber.dcm.',
+        help="The target pattern for sorting DICOM files. Default is %%PatientName/%%SeriesNumber-%%SeriesInstanceUID/%%InstanceNumber.dcm.",
     )
 
-    parser.add_argument("--truncateUID",
+    parser.add_argument(
+        "--truncateUID",
         dest="truncateUID",
         action="store_true",
         default=True,
         help="Truncate the UID to the last n characters (includes periods & underscores). Default is True.",
     )
 
-    parser.add_argument("--sanitizeFilename",
+    parser.add_argument(
+        "--sanitizeFilename",
         dest="sanitizeFilename",
         action="store_true",
         help="Sanitize the file name by replacing potentially dangerous characters. Default is True.",
     )
 
-    parser.add_argument("--overwrite",
+    parser.add_argument(
+        "--overwrite",
         dest="overwrite",
         action="store_true",
         help="Overwrite existing files. Default is False.",
     )
 
-    parser.add_argument("--nParallel",
+    parser.add_argument(
+        "--nParallel",
         dest="nParallel",
         action="store",
         type=int,
-        help="Number of parallel threads. Default is 1.",)
-
+        help="Number of parallel threads. Default is 1.",
+    )
+
     parser.set_defaults(truncateUID=True)
     parser.set_defaults(sanitizeFilename=True)
     parser.set_defaults(overwrite=False)
     parser.set_defaults(nParallel=1)
-    
+
     args = parser.parse_args()
 
     sorter = DICOMSorter(
@@ -190,4 +206,6 @@ def DICOMSorter_cli():
         sanitizeFilename=args.sanitizeFilename,
     )
 
-    sorter.sortDICOMFiles(option="copy", overwrite=args.overwrite, nParallel=int(args.nParallel))
+    sorter.sortDICOMFiles(
+        option="copy", overwrite=args.overwrite, nParallel=int(args.nParallel)
+    )

src/nbiatoolkit/nbia.py

@@ -11,18 +11,11 @@
 import zipfile
 from tqdm import tqdm
 from pyfiglet import Figlet
+import os
 
 # set __version__ variable
 __version__ = "0.12.1"
 
-def version():
-
-    f = Figlet(font='slant')
-    print(f.renderText('NBIAToolkit'))
-    print("Version: {}".format(__version__))
-    return 
-
-
 
 class NBIAClient:
     """
@@ -115,7 +108,9 @@ def getCollections(self, prefix: str = "") -> Union[list[str], None]:
                 collections.append(name)
         return collections
 
-    def getModalityValues(self, Collection: str = "", BodyPartExamined: str = "") -> Union[list[str], None]:
+    def getModalityValues(
+        self, Collection: str = "", BodyPartExamined: str = ""
+    ) -> Union[list[str], None]:
         PARAMS = self.parsePARAMS(locals())
 
         response = self.query_api(
@@ -152,14 +147,8 @@ def getPatients(self, Collection: str = "") -> Union[list[dict[str, str]], None]
             ), "PatientId must be a string, but received: %s" % type(
                 patient["PatientId"]
             )
-            patientList.append(
-                {
-                    "PatientId": patient["PatientId"],
-                    "PatientName": patient["PatientName"],
-                    "PatientSex": patient["PatientSex"],
-                    "Collection": patient["Collection"],
-                }
-            )
+
+            patientList.append(patient)
 
         return patientList
 
@@ -271,6 +260,12 @@ def downloadSeries(
 
         with cf.ThreadPoolExecutor(max_workers=nParallel) as executor:
             futures = []
+
+            try:
+                os.makedirs(downloadDir)
+            except FileExistsError:
+                pass
+
             for seriesUID in SeriesInstanceUID:
                 future = executor.submit(
                     self._downloadSingleSeries,
@@ -357,7 +352,6 @@ def parsePARAMS(self, params: dict) -> dict:
         return PARAMS
 
 
-
 # main
 if __name__ == "__main__":
     from pprint import pprint