Merge pull request #2 from jaspervdh/main

parse tsv or csv file and write to Peptidoforms

mumble/mumble.py

@@ -283,6 +283,47 @@ def write_modified_psm_list(self, psm_list, output_file=None, psm_file_type="tsv
         logger.info(f"Writing modified PSM list to {output_file}")
         write_file(psm_list=psm_list, filename=output_file, filetype=psm_file_type)
 
+    def parse_csv_file(self, file_name: str, delimiter: str = "\t") -> list:
+        """
+        Write simple input that takes tsv or csv file with: peptidoform, spectrum_id, precursor_mz and write to Peptidoforms
+        
+        Args:
+        file_name (str): Path to the CSV or TSV file.
+        delimiter (str, optional): Delimiter used in the file. Defaults to "\t"
+
+        return:
+            list of Peptidoforms
+        """
+        try:
+             df = pd.read_csv(file_name, delimiter=delimiter)
+        except FileNotFoundError as e:
+            logging.error(f"File not found: {e}")
+            return []
+        except pd.errors.EmptyDataError as e:
+            logging.error(f"Empty data: {e}")
+            return []
+        except pd.errors.ParserError as e:
+            logging.error(f"Parsing error: {e}")
+            return []
+
+        required_columns = {"peptidoform", "spectrum_id", "precursor_mz"}
+
+        if not required_columns.issubset(df.columns):
+            missing = required_columns - set(df.columns)
+            logging.error(f"Missing required columns: {missing}")
+            return []
+
+        # Clean up any whitespace in DataFrame
+        df = df.map(lambda x: x.strip() if isinstance(x, str) else x)
+
+        peptidoforms = [
+            PSM(peptidoform=row["peptidoform"], spectrum_id=row["spectrum_id"], precursor_mz=row["precursor_mz"])
+            for _, row in df.iterrows()
+        ]
+
+        return peptidoforms
+
+
 
 class _ModificationHandler:
     """Class that handles modifications."""

tests/test_mumble.py

@@ -1,5 +1,7 @@
 import pytest
-from unittest.mock import MagicMock
+from unittest.mock import MagicMock, patch, mock_open
+import pandas as pd
+from io import StringIO
 from collections import namedtuple
 from psm_utils import PSMList, PSM, Peptidoform
 from pyteomics import proforma
@@ -99,6 +101,61 @@ def test_add_modified_psms(self, setup_psmhandler):
         assert isinstance(new_psm_list, PSMList)
         assert len(new_psm_list) > 1
 
+    def test_parse_csv_file_valid(self, setup_psmhandler):
+
+        # psm_handler, mod_handler, psm = setup_psmhandler
+        psm_handler = setup_psmhandler[0]
+
+        # Mock CSV data
+        csv_data = """peptidoform\tspectrum_id\tprecursor_mz
+        ART[Deoxy]HR/2\tspec1\t214.1
+        ABCD/2\tspec2\t300.2
+        """
+
+        with patch("builtins.open", mock_open(read_data=csv_data)), \
+            patch("pandas.read_csv", return_value=pd.read_csv(StringIO(csv_data), delimiter="\t")):
+            peptidoforms = psm_handler.parse_csv_file("dummy_file.tsv")
+
+        assert len(peptidoforms) == 2
+        assert peptidoforms[0].peptidoform == Peptidoform("ART[Deoxy]HR/2")
+        assert peptidoforms[0].spectrum_id == "spec1"
+        assert peptidoforms[0].precursor_mz == 214.1
+
+    def test_parse_csv_file_missing_columns(self, setup_psmhandler):
+        psm_handler = setup_psmhandler[0]
+
+        # Mock CSV data with missing 'precursor_mz' column
+        csv_data = """peptidoform\tspectrum_id
+        ART[Deoxy]HR\tspec1
+        ABCD\tspec2
+        """
+
+        with patch("builtins.open", mock_open(read_data=csv_data)), \
+             patch("pandas.read_csv", return_value=pd.read_csv(StringIO(csv_data), delimiter="\t")):
+            peptidoforms = psm_handler.parse_csv_file("dummy_file.tsv", delimiter="\t")
+
+        assert peptidoforms == []  # Should return an empty list due to missing columns
+
+    def test_parse_csv_file_file_not_found(self, setup_psmhandler):
+        psm_handler = setup_psmhandler[0]
+
+        with patch("builtins.open", side_effect=FileNotFoundError):
+            peptidoforms = psm_handler.parse_csv_file("non_existent_file.tsv", delimiter="\t")
+
+        assert peptidoforms == []  # Should return an empty list due to FileNotFoundError
+
+    def test_parse_csv_file_empty_file(self, setup_psmhandler):
+        psm_handler = setup_psmhandler[0]
+
+        # Mock empty CSV data
+        csv_data = """peptidoform\tspectrum_id\tprecursor_mz"""
+
+        with patch("builtins.open", mock_open(read_data=csv_data)), \
+            patch("pandas.read_csv", return_value=pd.read_csv(StringIO(csv_data), delimiter="\t")):
+            peptidoforms = psm_handler.parse_csv_file("dummy_file.tsv", delimiter="\t")
+
+        assert peptidoforms == []  # Should return an empty list due to empty file
+
 
 class TestModificationHandler: