formatting, fix tests

Author: nickzoic

countess/core/pipeline.py

@@ -1,10 +1,10 @@
-from enum import Enum
 import logging
 import re
 import secrets
+import threading
 import time
+from enum import Enum
 from typing import Any, Iterable, Optional
-import threading
 
 import duckdb
 
@@ -15,13 +15,15 @@
 
 logger = logging.getLogger(__name__)
 
+
 class PipelineNodeStatus(Enum):
     INIT = 0
     WAIT = 1
     WORK = 2
     DONE = 3
     STOP = 4
 
+
 class PipelineNode:
     name: str
     uuid: str
@@ -87,7 +89,7 @@ def load_config(self):
 
     cursor = None
     thread = None
-    status : PipelineNodeStatus = PipelineNodeStatus.INIT
+    status: PipelineNodeStatus = PipelineNodeStatus.INIT
     table_name = None
 
     def start(self, ddbc, row_limit: Optional[int] = None):
@@ -122,7 +124,6 @@ def _run():
             self.status = PipelineNodeStatus.WORK
             logger.debug("PipelineNode.start _run work %s", self.name)
 
-
             sources = {pn.name: self.cursor.table(pn.table_name) for pn in self.parent_nodes if pn.table_name}
             logger.debug("PipelineNode.start _run sources %s", sources.keys())
             self.plugin.prepare_multi(ddbc, sources)

countess/core/plugins.py

@@ -219,7 +219,7 @@ class DuckdbLoadFilePlugin(DuckdbInputPlugin):
     files = FileArrayParam("Files", LoadFileMultiParam("File"))
     file_types: Sequence[tuple[str, Union[str, list[str]]]] = [("Any", "*")]
 
-    progress : float = 0
+    progress: float = 0
 
     def __init__(self, *a, **k):
         super().__init__(*a, **k)
@@ -307,8 +307,6 @@ def load_file(
 
 
 class DuckdbParallelLoadFilePlugin(DuckdbLoadFilePlugin):
-
-
     def execute(
         self, ddbc: DuckDBPyConnection, source: None, row_limit: Optional[int] = None
     ) -> Optional[DuckDBPyRelation]:
@@ -362,7 +360,6 @@ def load_file(
         raise NotImplementedError(f"{self.__class__}.load_file")
 
 
-
 class DuckdbLoadFileWithTheLotPlugin(LoadFileDeGlobMixin, LoadFileWithFilenameMixin, DuckdbParallelLoadFilePlugin):
     """This recombines the various parts which got broken out into mixins back into
     the original one-with-the-lot load file plugin base"""

countess/gui/main.py

@@ -211,7 +211,6 @@ def show_preview_subframe(self):
         if not self.node.plugin.show_preview:
             return
 
-
         if isinstance(self.node.result, DuckDBPyRelation):
             self.preview_subframe = TabularDataFrame(self.frame, cursor="arrow")
             self.preview_subframe.set_table(self.ddbc, self.node.result)
@@ -254,7 +253,6 @@ def config_change_task_callback(self):
         """Called when the user makes a change and had paused for a bit"""
         self.config_change_task = None
         logger.debug("config_change_task_callback")
-        #pos1, pos2 = self.config_scrollbar.get()
 
         self.node.stop()
         self.node.start(self.ddbc, preview_row_limit)
@@ -287,7 +285,6 @@ def config_change_poll_done(self):
         self.config_canvas.yview_moveto(pos1)
         self.config_scrollbar.set(pos1, pos2)
 
-
     def choose_plugin(self, plugin_class):
         self.node.plugin = plugin_class()
         # self.node.prerun()
@@ -663,6 +660,8 @@ def main() -> None:
     args = sys.argv[1:]
     global preview_row_limit  # pylint: disable=global-statement
 
+    logging.getLogger().setLevel('INFO')
+
     try:
         options, args = getopt.getopt(args, "", ["help", "version", "preview=", "log="])
     except getopt.GetoptError as exc:

countess/gui/tabular.py

@@ -1,9 +1,9 @@
 import io
 import logging
+import threading
 import tkinter as tk
 from functools import partial
 from math import ceil, floor, isinf, isnan
-import threading
 from tkinter import ttk
 from typing import Callable, Optional, Union
 
@@ -301,7 +301,6 @@ def _create_index_monitor():
         else:
             _create_index_continue()
 
-
     def _label_button_1(self, num, event):
         """Click on column labels to set sort order"""
         self.set_sort_order(num)
@@ -390,5 +389,5 @@ def _column_copy(self, _):
 
         # Dump TSV into a StringIO and push it onto the clipboard
         buf = io.StringIO()
-        table.to_csv(buf, sep="\t", index=False)
+        table.to_df().to_csv(buf, sep="\t", index=False)
         copy_to_clipboard(buf.getvalue())

countess/plugins/csv.py

@@ -27,7 +27,6 @@
 from countess.core.plugins import (
     DuckdbLoadFilePlugin,
     DuckdbSaveFilePlugin,
-    DuckdbParallelLoadFilePlugin,
     LoadFileDeGlobMixin,
     LoadFileWithFilenameMixin,
 )

countess/plugins/variant.py

@@ -112,7 +112,7 @@ def transform(self, data: dict[str, Any]) -> Optional[dict[str, Any]]:
                     minus_strand=self.variant.minus_strand.value,
                 )
             except TooManyVariationsException:
-                return None
+                pass
             except (ValueError, TypeError, KeyError, IndexError) as exc:
                 logger.warning("Exception", exc_info=exc)
 
@@ -128,7 +128,7 @@ def transform(self, data: dict[str, Any]) -> Optional[dict[str, Any]]:
                     offset=int(self.protein.offset.get_value_from_dict(data) or 0),
                 )
             except TooManyVariationsException:
-                return None
+                pass
             except (ValueError, TypeError, KeyError, IndexError) as exc:
                 logger.warning("Exception", exc_info=exc)
 
@@ -171,7 +171,7 @@ def sql(self, table_name: str, columns: Iterable[str]) -> Optional[str]:
         """
 
 
-def _translate_aa(expr: str, expr1: str = None) -> str:
+def _translate_aa(expr: str, expr1: str = '') -> str:
     # This looks ludicrous but it pushes all the work down into SQL so that
     # duckdb can run it without translating rows into Python etc.
     return (

tests/gui/test_tabular.py

@@ -43,5 +43,8 @@ def test_tabular_copy():
 
     x = root.selection_get(selection="CLIPBOARD")
     assert (
-        x == "x\ty\tz\n30\t6255274016445075936\t1382406602978853548\n31\t13285076694688170502\t14198994021025867918\n\n"
+        x == """x\ty\tz
+29\t687214525942812148\t13438185942843147596
+30\t6255274016445075936\t1382406602978853548
+31\t13285076694688170502\t14198994021025867918\n\n"""
     )

tests/plugins/test_csv.py

@@ -58,7 +58,7 @@ def test_filename_column():
     plugin.set_parameter("filename_column", True)
     output = plugin.execute(ddbc, None)
     assert "filename" in output.columns
-    assert output.df()["filename"].iloc[1] == "input1"
+    assert output.df()["filename"].iloc[1] == "tests/input1.csv"
 
 
 df = pd.DataFrame([[1, 2.01, "three"], [4, 5.5, "six"], [7, 8.8, "nine"]], columns=["a", "b", "c"])