Merge branch 'osw_parquet_chrom_reader_w_xtra_file_ext' into oswpq_xic_parquet_together

Author: jcharkow

massdash/loaders/GenericRawDataLoader.py

@@ -11,7 +11,7 @@
 from .ResultsLoader import ResultsLoader
 # Structs
 from ..structs import TransitionGroup, TransitionGroupFeature
-from ..util import LOGGER, in_notebook
+from ..util import LOGGER, in_notebook, get_base_stem
 
 from scipy.signal import savgol_filter, convolve
 from scipy.signal.windows import gaussian
@@ -34,7 +34,7 @@ def __init__(self, dataFiles: Union[str, List[str]], **kwargs):
             self.dataFiles = dataFiles
 
         ## overwrite run names since we are specifying data files
-        self.runNames = [Path(f).stem for f in self.dataFiles]
+        self.runNames = [get_base_stem(f) for f in self.dataFiles]
 
     @abstractmethod
     def loadTransitionGroups(self, pep_id: str, charge: int, runNames: Union[None, str, List[str]]= None) -> Dict[str, TransitionGroup]:

massdash/loaders/access/MzMLDataAccess.py

@@ -23,7 +23,7 @@
 from ...structs.FeatureMap import FeatureMap
 from ...structs.TransitionGroupFeature import TransitionGroupFeature
 # Internal
-from ...util import LOGGER, method_timer, code_block_timer
+from ...util import LOGGER, method_timer, code_block_timer, get_base_stem
 
 class MzMLDataAccess():
     """
@@ -53,7 +53,7 @@ def __init__(self, filename: str, readOptions="ondisk", verbose=False):
         """
 
         self.filename = filename
-        self.runName = str(Path(filename).stem)
+        self.runName = get_base_stem(filename) 
         self.readOptions = readOptions
         self.exp = po.OnDiscMSExperiment()
         self.meta_data = po.MSExperiment()

massdash/loaders/access/ResultsTSVDataAccess.py

@@ -14,7 +14,7 @@
 # Structs
 from ...structs.TransitionGroupFeature import TransitionGroupFeature
 # Utils
-from ...util import LOGGER
+from ...util import LOGGER, get_base_stem
 
 def convert_spectro_modifications(modified_peptide_series):
     # Define the replacement patterns
@@ -173,7 +173,7 @@ def getTransitionGroupFeatures(self, runname: str, peptide:str, charge: int):
         Returns:
             TransitionGroupFeature: TransitionGroupFeature object containing peak boundaries, intensity and confidence
         '''
-        runname_exact = self.getExactRunName(runname)
+        runname_exact = self.getExactRunName(get_base_stem(runname))
 
         if runname_exact is None:
             LOGGER.debug(f"Error: No matching runs found for {runname}")
@@ -234,7 +234,7 @@ def getTopTransitionGroupFeatureDf(self, runname: str, pep_id: str, charge: int)
         Returns:
             pd.DataFrame: Dataframe with the TransitionGroupFeatures
         '''
-        runname_exact = self.getExactRunName(runname)
+        runname_exact = self.getExactRunName(get_base_stem(runname))
         if runname_exact is None:
             return pd.DataFrame(columns=self.columns)
         else:
@@ -284,7 +284,7 @@ def getRunNames(self) -> List[str]:
         Returns:
             list: List of run names
         '''
-        return [ Path(r).stem for r in self.runs]
+        return [ get_base_stem(r) for r in self.runs]
 
     def getIdentifiedPrecursors(self, qvalue: float = 0.01, run:Optional[str] = None, precursorLevel = False) -> Union[set, Dict[str, set]]:
         '''

massdash/loaders/access/SqMassDataAccess.py

@@ -53,15 +53,15 @@
 # Structs
 from ...structs.Chromatogram import Chromatogram
 # Utils
-from ...util import check_sqlite_column_in_table, check_sqlite_table
+from ...util import check_sqlite_column_in_table, check_sqlite_table, get_base_stem
 
 class SqMassDataAccess:
 
     def __init__(self, filename):
         self.conn = sqlite3.connect(filename, check_same_thread=False)
         self.c = self.conn.cursor()
         self.filename = filename
-        self.runName = str(Path(filename).stem)
+        self.runName = get_base_stem(filename)
 
     def getPrecursorChromIDs(self, precursor_id):
         """

massdash/loaders/access/XICParquetDataAccess.py

@@ -11,6 +11,7 @@
 
 # Structs
 from ...structs import TransitionGroup, Chromatogram
+from ...util import get_base_stem
 
 class XICParquetDataAccess:
     '''
@@ -19,7 +20,7 @@ class XICParquetDataAccess:
     RT_MULTIPLIER = 60
     def __init__(self, filename):
         self.filename = filename
-        self.runName = str(Path(filename).stem)
+        self.runName = get_base_stem(filename) 
         self.parquet = pq.ParquetFile(filename)
 
         ## Read the index

massdash/util.py

@@ -579,3 +579,17 @@ def in_notebook() -> bool:
     except AttributeError:
         return False
     return True
+
+
+def get_base_stem(file_path: str) -> str:
+    """
+    Get the base name of a file without the extension.
+
+    Args:
+        file_path (str): The path to the file.
+
+    Returns:
+        str: The base name of the file without the extension.
+    """
+    stripped_extensions = file_path.rstrip(''.join(Path(file_path).suffixes))
+    return Path(stripped_extensions).stem

test/loaders/test_XICParquetDataLoader.py

@@ -15,7 +15,7 @@
 
 @pytest.fixture
 def loader():
-    return XICParquetDataLoader(dataFiles=[TEST_PATH / 'diann_xic.parquet'], rsltsFile=str(TEST_PATH / 'diann_report_small_xic.tsv'))
+    return XICParquetDataLoader(dataFiles=[str(TEST_PATH / 'diann_xic.parquet')], rsltsFile=str(TEST_PATH / 'diann_report_small_xic.tsv'))
 
 @pytest.fixture
 def snapshot_pandas(snapshot):