Add read_sam in sam_handler module

src/DAJIN2/core/preprocess/midsv_caller.py

@@ -215,8 +215,8 @@ def generate_midsv(ARGS, is_control: bool = False, is_insertion: bool = False) -
             path_splice = Path(ARGS.tempdir, name, "sam", f"splice_{allele}.sam")
             path_output_midsv = Path(ARGS.tempdir, name, "midsv", f"{allele}.json")
 
-        sam_ont = sam_handler.remove_overlapped_reads(list(midsv.read_sam(path_ont)))
-        sam_splice = sam_handler.remove_overlapped_reads(list(midsv.read_sam(path_splice)))
+        sam_ont = sam_handler.remove_overlapped_reads(list(sam_handler.read_sam(path_ont)))
+        sam_splice = sam_handler.remove_overlapped_reads(list(sam_handler.read_sam(path_splice)))
         qname_of_map_ont = extract_qname_of_map_ont(sam_ont, sam_splice)
         sam_of_map_ont = filter_sam_by_preset(sam_ont, qname_of_map_ont, preset="map-ont")
         sam_of_splice = filter_sam_by_preset(sam_splice, qname_of_map_ont, preset="splice")

src/DAJIN2/utils/sam_handler.py

@@ -1,6 +1,9 @@
 from __future__ import annotations
 
 import re
+
+from pathlib import Path
+from typing import Generator
 from itertools import groupby
 from DAJIN2.utils.dna_handler import revcomp
 
@@ -22,6 +25,17 @@ def is_mapped(s: list[str]) -> bool:
     return not s[0].startswith("@") and s[9] != "*"
 
 
+###########################################################
+# Read sam
+###########################################################
+
+
+def read_sam(path_of_sam: str | Path) -> Generator[list]:
+    with open(path_of_sam) as f:
+        for line in f:
+            yield line.strip().split("\t")
+
+
 ###########################################################
 # remove_overlapped_reads
 ###########################################################