add todos and rearrange md5 function

README.md

@@ -15,7 +15,12 @@ See Documentation at [NBIA-Toolkit Read The Docs](https://nbia-toolkit.readthedo
     TODO::nbia.py::implement better error handling
     TODO::nbia.py::implement better logging & logger configuration
     TODO::nbia.py::enforce type checking for all functions and add type hints
-    TODO::nbia.py::implement return formats for dict, and pandas.DataFrame
+    TODO::nbia.py::implement return formats for dict, and pandas.DataFrames
+    TODO::nbia.py::handle error case of if resposne is not bytes 
+    TODO::nbia.py::add tests for download Series
+    TODO::nbia.py::add functionality for downloadSeries to take in a list of seriesUIDs
+    TODO::md5.py::add tests
+    TODO::md5.py::add logging and error handling for non-existent files
     TODO::dicomsort.py::come up with more efficient algorithm for sorting
     TODO::dicomsort.py::implement better error handling
     TODO::dicomsort.py::come up with solution to only use part of UIDs (last 5 digits)?

src/nbiatoolkit/nbia.py

@@ -1,10 +1,11 @@
 from nbiatoolkit.auth import OAuth2
 from nbiatoolkit.utils.nbia_endpoints import NBIA_ENDPOINTS
 from nbiatoolkit.utils.logger import setup_logger
+from nbiatoolkit.utils.md5 import validateMD5
 import requests
 from requests.exceptions import JSONDecodeError as JSONDecodeError
 import io, zipfile, os
-import hashlib
+
 
 class NBIAClient:
     """
@@ -137,17 +138,13 @@ def getSeries(self,
 
         return response
 
-    def downloadSeries(self,
-        SeriesInstanceUID: str,
-        downloadDir: str,
+    def downloadSeries(
+        self, SeriesInstanceUID: str, downloadDir: str,
         ) -> bool:
 
-
-
         params = dict()
         params["SeriesInstanceUID"] = SeriesInstanceUID
 
-
         response = self.query_api(
             endpoint = NBIA_ENDPOINTS.DOWNLOAD_SERIES,
             params = params)
@@ -157,7 +154,7 @@ def downloadSeries(self,
             seriesDir = os.path.join(downloadDir, SeriesInstanceUID)
             file.extractall(path=seriesDir)
 
-            self.validateMD5(seriesDir=seriesDir)
+            validateMD5(seriesDir=seriesDir)
         else:
         # Handle the case where the expected binary data is not received
         # Log error or raise an exception
@@ -166,38 +163,6 @@ def downloadSeries(self,
         return True
 
 
-    def _calculateMD5(self,
-        filepath: str
-        ) -> str:
-
-
-        hash_md5 = hashlib.md5()
-        with open(filepath, "rb") as f:
-            for chunk in iter(lambda: f.read(4096), b""):
-                hash_md5.update(chunk)
-        return hash_md5.hexdigest()
 
-    def validateMD5(self,
-        seriesDir: str
-        ) -> bool:
-
-        md5File = os.path.join(seriesDir, "md5hashes.csv")
-        assert os.path.isfile(md5File), "MD5 hash file not found in download directory."
-
-        with open(md5File, "r") as f:
-            lines = f.readlines()
-
-        for line in lines[1:]:           
-            filepath = os.path.join(seriesDir, line.split(",")[0])
-            if not os.path.isfile(filepath):
-                print(f"File not found in seriesDir: {filepath}")
-                return False
-
-            md5hash = line.split(",")[1].strip().lower()
-            md5 = self._calculateMD5(filepath)
-
-            assert md5 == md5hash, f"MD5 hash mismatch for file: {filepath}"       
-        # delete the md5 file if all hashes match
-        os.remove(md5File)
-        return True
+
 

src/nbiatoolkit/utils/md5.py

@@ -0,0 +1,30 @@
+import hashlib, os
+
+def calculateMD5(filepath: str) -> str:
+        hash_md5 = hashlib.md5()
+        with open(filepath, "rb") as f:
+            for chunk in iter(lambda: f.read(4096), b""):
+                hash_md5.update(chunk)
+        return hash_md5.hexdigest()
+
+def validateMD5(seriesDir: str) -> bool:
+
+    md5File = os.path.join(seriesDir, "md5hashes.csv")
+    assert os.path.isfile(md5File), "MD5 hash file not found in download directory."
+
+    with open(md5File, "r") as f:
+        lines = f.readlines()
+
+    for line in lines[1:]:           
+        filepath = os.path.join(seriesDir, line.split(",")[0])
+        if not os.path.isfile(filepath):
+            print(f"File not found in seriesDir: {filepath}")
+            return False
+
+        md5hash = line.split(",")[1].strip().lower()
+        md5 = calculateMD5(filepath)
+
+        assert md5 == md5hash, f"MD5 hash mismatch for file: {filepath}"       
+    # delete the md5 file if all hashes match
+    os.remove(md5File)
+    return True