about summary refs log tree commit diff
path: root/scripts/genotypes
diff options
context:
space:
mode:
authorpi coding agent <pi@localhost>2026-10-15 20:44:47 +0000
committerFrederick Muriuki Muriithi <fredmanglis@gmail.com>2026-10-15 16:01:45 -0500
commit6058bcb6c11060647819a1790b05f4ea144bb2b3 (patch)
tree7fcfedcc14d01f7dac5ce3b9dcfe4484c6949e10 /scripts/genotypes
parent87ba0e2fae57764863af2c978a8878f92f043ab2 (diff)
downloadgn-uploader-6058bcb6c11060647819a1790b05f4ea144bb2b3.tar.gz
Relax line-argument annotations to any iterable
Accept `Iterable[str]` for the lines arguments instead of `Iterator[str]`,
since lists of lines are valid inputs, and accept `Sequence[str]` for the
sample names. This fixes the mypy type errors without changing behaviour.
Diffstat (limited to 'scripts/genotypes')
-rw-r--r--scripts/genotypes/preprocess_csv_collect_info.py12
1 files changed, 6 insertions, 6 deletions
diff --git a/scripts/genotypes/preprocess_csv_collect_info.py b/scripts/genotypes/preprocess_csv_collect_info.py
index b153279..6b3b574 100644
--- a/scripts/genotypes/preprocess_csv_collect_info.py
+++ b/scripts/genotypes/preprocess_csv_collect_info.py
@@ -6,7 +6,7 @@ import logging
 import multiprocessing as mproc
 from pathlib import Path
 from dataclasses import asdict, dataclass, field, fields
-from typing import Union, Iterable, Iterator, Optional, Callable
+from typing import Union, Iterable, Iterator, Optional, Callable, Sequence
 from argparse import Namespace, ArgumentParser
 
 from gn_libs.cli import SysExit
@@ -209,7 +209,7 @@ class _ChunkStats:# pylint: disable=[too-many-instance-attributes]
 def _accumulate(
         headers: tuple[str, ...],
         fileconfigs: dict,
-        lines: Iterator[str]
+        lines: Iterable[str]
 ) -> _ChunkStats:
     """Accumulate statistics from the provided lines."""
     is_skippable_line = _make_is_skippable_line(fileconfigs, headers)
@@ -292,7 +292,7 @@ def _merge_all_chunk_stats(
 
 
 def _read_chunks(
-        lines: Iterator[str],
+        lines: Iterable[str],
         chunk_size: int
 ) -> Iterator[list[str]]:
     """Group the lines into chunks of at most ``chunk_size`` lines."""
@@ -319,7 +319,7 @@ def _process_chunk(args: tuple[tuple[str, ...], dict, list[str]]) -> _ChunkStats
 def file_stats_multiprocessing(
         fileconfigs: dict,
         headers: tuple[str, ...],
-        lines: Iterator[str],
+        lines: Iterable[str],
         chunk_size: int = MULTIPROCESSING_CHUNK_SIZE
 ) -> FileStats:
     """File stats from the lines in the file using multiple processes."""
@@ -338,7 +338,7 @@ def file_stats_multiprocessing(
 
 def _as_file_stats(
         stats: _ChunkStats,
-        samples: tuple[str, ...],
+        samples: Sequence[str],
         header_errors: tuple[LineError, ...]
 ) -> FileStats:
     """Convert accumulated statistics into file statistics."""
@@ -385,7 +385,7 @@ def parse_dot_geno_line(line) -> dict[str, str]:
 def file_stats_singlethread(
         fileconfigs: dict,
         headers: tuple[str, ...],
-        lines: Iterator[str]
+        lines: Iterable[str]
 ) -> FileStats:
     """File stats from the lines in the file using a single-threaded process."""
     logger.debug("THE FILE HEADERS: %s", headers)