Merge pull request #73 from compomics/bug-fix

Bug fixes

psm_utils/io/_utils.py

@@ -0,0 +1,27 @@
+import sys
+import csv
+
+
+def set_csv_field_size_limit():
+    """
+    Sets the maximum field size limit for reading CSV files.
+
+    This function sets the maximum field size limit for reading CSV files using the `csv` module.
+    It attempts to set the limit to the maximum integer value (`sys.maxsize`), and if an `OverflowError`
+    occurs, it reduces the limit by dividing it by 10 until it can be set successfully.
+
+    Note:
+        This function should be called before reading any CSV files to ensure that the field size limit
+        is properly set.
+
+
+    """
+    maxInt = sys.maxsize
+
+    while maxInt > 1:
+        print(maxInt)
+        try:
+            csv.field_size_limit(maxInt)
+            break
+        except OverflowError:
+            maxInt = int(maxInt / 10)

psm_utils/io/ionbot.py

@@ -16,6 +16,9 @@
 from psm_utils.peptidoform import Peptidoform
 from psm_utils.psm import PSM
 from psm_utils.psm_list import PSMList
+from psm_utils.io._utils import set_csv_field_size_limit
+
+set_csv_field_size_limit()
 
 REQUIRED_COLUMNS = [
     "database_peptide",
@@ -89,11 +92,11 @@ def _get_peptide_spectrum_match(self, psm_dict: Dict[str, str | float]) -> PSM:
             ),
             spectrum_id=psm_dict["spectrum_title"],
             run=psm_dict["spectrum_file"],
-            is_decoy=True
-            if psm_dict["database"] == "D"
-            else False
-            if psm_dict["database"] == "T"
-            else None,
+            is_decoy=(
+                True
+                if psm_dict["database"] == "D"
+                else False if psm_dict["database"] == "T" else None
+            ),
             score=float(psm_dict["psm_score"]),
             precursor_mz=float(psm_dict["m/z"]),
             retention_time=float(psm_dict["observed_retention_time"]),

psm_utils/io/maxquant.py

@@ -14,6 +14,9 @@
 from psm_utils.io._base_classes import ReaderBase
 from psm_utils.peptidoform import Peptidoform
 from psm_utils.psm import PSM
+from psm_utils.io._utils import set_csv_field_size_limit
+
+set_csv_field_size_limit()
 
 logger = logging.getLogger(__name__)
 

psm_utils/io/msamanda.py

@@ -13,6 +13,9 @@
 from psm_utils.exceptions import PSMUtilsException
 from psm_utils.io._base_classes import ReaderBase
 from psm_utils.psm import PSM, Peptidoform
+from psm_utils.io._utils import set_csv_field_size_limit
+
+set_csv_field_size_limit()
 
 logger = logging.getLogger(__name__)
 

psm_utils/io/peptide_record.py

@@ -66,6 +66,9 @@
 from psm_utils.peptidoform import Peptidoform
 from psm_utils.psm import PSM
 from psm_utils.psm_list import PSMList
+from psm_utils.io._utils import set_csv_field_size_limit
+
+set_csv_field_size_limit()
 
 
 class _PeptideRecord:

psm_utils/io/percolator.py

@@ -25,6 +25,9 @@
 from psm_utils.peptidoform import Peptidoform
 from psm_utils.psm import PSM
 from psm_utils.psm_list import PSMList
+from psm_utils.io._utils import set_csv_field_size_limit
+
+set_csv_field_size_limit()
 
 
 class PercolatorTabReader(ReaderBase):

psm_utils/io/sage.py

@@ -6,7 +6,6 @@
 
 """
 
-
 from __future__ import annotations
 
 import csv
@@ -17,7 +16,9 @@
 
 from psm_utils.io._base_classes import ReaderBase
 from psm_utils.psm import PSM
-from psm_utils.psm_list import PSMList
+from psm_utils.io._utils import set_csv_field_size_limit
+
+set_csv_field_size_limit()
 
 
 class SageReader(ReaderBase):
@@ -88,11 +89,9 @@ def _get_peptide_spectrum_match(self, psm_dict) -> PSM:
             ),
             spectrum_id=psm_dict["scannr"],
             run=Path(psm_dict["filename"]).stem,
-            is_decoy=True
-            if psm_dict["label"] == "-1"
-            else False
-            if psm_dict["label"] == "1"
-            else None,
+            is_decoy=(
+                True if psm_dict["label"] == "-1" else False if psm_dict["label"] == "1" else None
+            ),
             qvalue=psm_dict["spectrum_q"],
             score=float(psm_dict[self.score_column]),
             precursor_mz=self._parse_precursor_mz(psm_dict["expmass"], psm_dict["charge"]),

psm_utils/io/tsv.py

@@ -45,6 +45,7 @@
 
 
 """
+
 from __future__ import annotations
 
 import ast
@@ -59,6 +60,9 @@
 from psm_utils.io.exceptions import PSMUtilsIOException
 from psm_utils.psm import PSM
 from psm_utils.psm_list import PSMList
+from psm_utils.io._utils import set_csv_field_size_limit
+
+set_csv_field_size_limit()
 
 logger = logging.getLogger(__name__)
 

pyproject.toml

@@ -20,7 +20,7 @@ classifiers = [
 dynamic = ["version"]
 requires-python = ">=3.7"
 dependencies = [
-    "pyteomics >= 4",
+    "pyteomics >= 4, <4.7",
     "pyopenms",
     "lxml",
     "psims",