treating tabular as tsv files

Author: acquayefrank

RIAssigner/__main__.py

@@ -17,14 +17,14 @@ def create_parser():
                           action=LoadDataAction,
                           nargs=3,
                           help="""Reference dataset containing retention times and indices.
-                          Path to msp, csv, tsv or parquet filetype and retention time unit.""")
+                          Path to msp, csv, tsv/tabular or parquet filetype and retention time unit.""")
     required.add_argument("--query",
                           required=True,
                           type=str,
                           action=LoadDataAction,
                           nargs=3,
                           help="""Query dataset for which to compute retention indices.
-                          Path to msp, csv, tsv or parquet filetype and retention time unit.""")
+                          Path to msp, csv, tsv/tabular or parquet filetype and retention time unit.""")
     required.add_argument("--method",
                           required=True,
                           type=str,

RIAssigner/__version__.py

@@ -1 +1 @@
-__version__ = '0.5.0'
+__version__ = '0.5.1'

RIAssigner/cli/LoadDataAction.py

@@ -30,8 +30,8 @@ def __call__(self, parser, namespace, values, option_string=None):
         rt_unit = values[2]
         if filetype == 'msp':
             data = MatchMSData(filename, filetype, rt_unit)
-        elif filetype in ['csv', 'tsv', 'parquet']:
+        elif filetype in ['csv', 'tsv', 'tabular', 'parquet']:
             data = PandasData(filename, filetype, rt_unit)
         else:
-            raise ValueError(f"Unsupported file type: {filetype}. Supported types are 'msp', 'csv', 'tsv', and 'parquet'.")
+            raise ValueError(f"Unsupported file type: {filetype}. Supported types are 'msp', 'csv', 'tsv', 'tabular' and 'parquet'.")
         setattr(namespace, self.dest, data)

RIAssigner/data/PandasData.py

@@ -30,19 +30,19 @@ def _read(self):
 
     def _read_into_dataframe(self)  -> None:
         """ Read the data from file into dataframe. """
-        if(self._filetype in ['csv', 'tsv']):
+        if(self._filetype in ['csv', 'tsv', 'tabular']):
             self._data = read_csv(self._filename, sep=None, engine="python")
         elif self._filetype == 'parquet':
             self._data = read_parquet(self._filename)
         else:
-            raise NotImplementedError("File formats different from ['csv', 'tsv'] are not implemented yet.")
+            raise NotImplementedError("File formats different from ['csv', 'tsv', 'tabular', 'parquet'] are not implemented yet.")
         self._data.columns = clean_column_names(self._data.columns)
 
     def write(self, filename: str) -> None:
-        """ Write data on disk. Supports 'csv', 'tsv', and 'parquet' formats. """
+        """ Write data on disk. Supports 'csv', 'tsv', 'tabular' and 'parquet' formats. """
         if filename.endswith(".parquet"):
             self._data.to_parquet(filename, index=False)
-        elif filename.endswith((".csv", ".tsv")):
+        elif filename.endswith((".csv", ".tsv", ".tabular")):
             separator = define_separator(filename)
             self._data.to_csv(filename, index=False, sep=separator)
         else:

RIAssigner/utils.py

@@ -13,7 +13,7 @@ def get_first_common_element(first: Iterable[T], second: Iterable[T]) -> T:
         first (Iterable[T]): First list.
         second (Iterable[T]): Second list.
 
-    Returns:    
+    Returns:
         T: First common element or None if no common element is found.
     """
     return next((item for item in first if item in second), None)
@@ -24,11 +24,12 @@ def define_separator(filename: str) -> str:
 
     Args:
         filename (str): Filename for which to get the separator.
-    
+
     Returns:
         str: Separator for data values.
     """
-    if filename.endswith(".tsv"):
+    if filename.endswith((".tsv", ".tabular")):
+        # Use tab as separator for TSV and tabular files
         separator = "\t"
     else:
         separator = ","
@@ -60,7 +61,7 @@ def is_sorted(values) -> bool:
 
 def clean_column_names(column_names: List[str]) -> List[str]:
     """ Clean column names by removing leading and trailing whitespaces, converting to lowercase.
-    
+
     Args:
         column_names (List[str]): List of column names to clean.
 

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "RIAssigner"
-version = "0.5.0"
+version = "0.5.1"
 description = "Python library for retention index calculation."
 authors = ["Helge Hecht <helge.hecht@recetox.muni.cz>", "Maksym Skoryk <maksym.skoryk@recetox.muni.cz>"]