Move get_circular_pattern() to edgecaselib.util

edgecaselib/kmerscanner.py

@@ -1,7 +1,7 @@
 from sys import stdout, stderr
-from regex import compile, IGNORECASE
 from numpy import zeros, array, cumsum, nan
 from multiprocessing import Pool
+from edgecaselib.util import get_circular_pattern
 from edgecaselib.formats import filter_bam
 from edgecaselib.tailchopper import get_cigar_clip_length
 from pysam import AlignmentFile, FastxFile
@@ -67,19 +67,6 @@
 )
 
 
-def get_circular_pattern(motif, repeats=2):
-    """Convert motif into circular regex pattern (e.g., r'TCGA|CGAT|GATC|ATCG' for TCGA)"""
-    atom_pattern = compile(r'[ACGT.]|\[[ACGT]+\]', flags=IGNORECASE)
-    atoms = atom_pattern.findall(motif)
-    if "".join(atoms) != motif:
-        raise ValueError("Could not parse motif: {}".format(motif))
-    repeated_inversions = {
-        "".join(atoms[i:] + atoms[:i]) * repeats
-        for i in range(len(atoms))
-    }
-    return compile(r'|'.join(repeated_inversions), flags=IGNORECASE)
-
-
 def get_edge_density(entry, pattern, head_test, tail_test):
     """Calculate density of pattern in head_test or tail_test of read"""
     if (entry.query_sequence is None) or (len(entry.query_sequence) == 0):

edgecaselib/repeatfinder.py

@@ -3,8 +3,8 @@
 from pysam import AlignmentFile, FastxFile
 from os import path
 from edgecaselib.util import get_executable, progressbar, revcomp
+from edgecaselib.util import get_circular_pattern
 from edgecaselib.formats import filter_bam
-from edgecaselib.kmerscanner import get_circular_pattern
 from functools import lru_cache
 from subprocess import check_output
 from pandas import read_csv, concat

edgecaselib/util.py

@@ -1,5 +1,5 @@
 from sys import stderr
-from regex import compile
+from regex import compile, IGNORECASE as REGEX_IGNORECASE
 from re import split, search, IGNORECASE
 from shutil import which
 from os import path, access, X_OK
@@ -50,6 +50,19 @@ def motif_revcomp(motif, ignorecase=True):
         raise ValueError("Unsupported character(s) in motif: {}".format(motif))
 
 
+def get_circular_pattern(motif, repeats=2):
+    """Convert motif into circular regex pattern (e.g., r'TCGA|CGAT|GATC|ATCG' for TCGA)"""
+    atom_pattern = compile(r'[ACGT.]|\[[ACGT]+\]', flags=REGEX_IGNORECASE)
+    atoms = atom_pattern.findall(motif)
+    if "".join(atoms) != motif:
+        raise ValueError("Could not parse motif: {}".format(motif))
+    repeated_inversions = {
+        "".join(atoms[i:] + atoms[:i]) * repeats
+        for i in range(len(atoms))
+    }
+    return compile(r'|'.join(repeated_inversions), flags=REGEX_IGNORECASE)
+
+
 def chromosome_natsort(chrom):
     """Natural order sorting that undestands chr1, 4, chr10, chr14_K*, 7ptel etc"""
     keyoder = []