Fixes FindSpanin

* Package sync for requirements
  * Drop parser (not used)
* re-implement regex in cpt.py

[#15]

cpt_find_spanins/cpt.py

@@ -4,6 +4,7 @@
 from Bio import SeqIO
 from Bio.Data import CodonTable
 import logging
+import regex as re
 
 logging.basicConfig()
 log = logging.getLogger()
@@ -147,7 +148,7 @@ def break_up_frame(self, s):
             if index % 3 != 0:
                 continue
             n = s[start:index]
-            for (offset, n, t) in self.start_chop_and_trans(n):
+            for offset, n, t in self.start_chop_and_trans(n):
                 if n and len(t) >= self.min_len:
                     yield start + offset, n, t
             start = index
@@ -294,7 +295,7 @@ def break_up_frame(self, s):
             if index % 3 != 0:
                 continue
             n = s[start:index]
-            for (offset, n, t) in self.start_chop_and_trans(n):
+            for offset, n, t in self.start_chop_and_trans(n):
                 if n and len(t) >= self.min_len:
                     yield start + offset, n, t
             start = index

cpt_find_spanins/findSpanin.py

@@ -2,15 +2,12 @@
 ######### Much of this code is very "blocked", in the sense that one thing happens...then a function happens on the return...then another function...etc...etc...
 
 import argparse
-import os
 import re  # new
-import itertools  # new
-from collections import Counter, OrderedDict
+from collections import Counter
 from spaninFuncs import (
     getDescriptions,
     grabLocs,
     spaninProximity,
-    splitStrands,
     tuple_fasta,
     lineWrapper,
 )

cpt_find_spanins/findSpanin.xml

@@ -4,8 +4,11 @@
         <import>macros.xml</import>
 
     </macros>
-    <expand macro="requirements">
-    </expand>
+    <requirements>
+        <requirement type="package" version="3.9">python</requirement>
+        <requirement type="package" version="1.84">biopython</requirement>
+        <requirement type="package" version="2024.9.11">regex</requirement>
+    </requirements>
     <command detect_errors="aggressive"><![CDATA[
 python '$__tool_directory__/findSpanin.py'
 '$putative_isp_fasta_file'

cpt_find_spanins/spaninFuncs.py

@@ -7,8 +7,6 @@
 
 import re
 from Bio import SeqIO
-from Bio import Seq
-from collections import OrderedDict
 
 # Not written in OOP for a LITTLE bit of trying to keep the complication down in case adjustments are needed by someone else.
 # Much of the manipulation is string based; so it should be straightforward as well as moderately quick
@@ -519,7 +517,9 @@ def check_for_usp():
         # try:
         try:
             lipo += find_lipobox(pair=each_pair, regex=2)  # , minimum=8)
-        except TypeError:  # catches if something doesnt have the min/max requirements (something is too small)
+        except (
+            TypeError
+        ):  # catches if something doesnt have the min/max requirements (something is too small)
             continue
         # except:
         # continue