From d74eaba3fab5538ce58a8d150804503888323d8f Mon Sep 17 00:00:00 2001
From: Edmund Miller <git@edmundmiller.dev>
Date: Mon, 29 Jul 2024 22:33:22 -0500
Subject: [PATCH] refactor: Move script into bin

---
 bin/results2fasta.py                  | 27 +++++++++++++++++++++
 modules/primer3_results2fasta/main.nf | 35 +++------------------------
 2 files changed, 31 insertions(+), 31 deletions(-)
 create mode 100755 bin/results2fasta.py

diff --git a/bin/results2fasta.py b/bin/results2fasta.py
new file mode 100755
index 0000000..cd48e77
--- /dev/null
+++ b/bin/results2fasta.py
@@ -0,0 +1,27 @@
+#!/usr/bin/env python
+import re
+import os
+import os.path
+
+with open("!{results}", "r") as input_handle:
+data = input_handle.read()
+##print(data)
+
+id_match = re.search('SEQUENCE_ID=(.+)',data)
+id = id_match.group(1)
+
+bespoke_regex = '(?P<id>PRIMER_PAIR_[0-9]+)_PENALTY=(?P<penalty>[0-9.]+).+?PRIMER_LEFT_[0-9]+_SEQUENCE=(?P<left>[atcgATCGnN]+).+?PRIMER_RIGHT_[0-9]+_SEQUENCE=(?P<right>[atcgATCGnN]+).+?PRIMER_PAIR_[0-9]+_PRODUCT_SIZE=(?P<size>[0-9]+).+?PRIMER_PAIR_[0-9]+_PRODUCT_TM=[0-9.]+'
+
+matches = list(re.finditer(bespoke_regex,data,flags=re.MULTILINE|re.DOTALL))
+
+output_handle = open("!{results}.fa", "w")
+for m in matches:
+line = ">{ID} primer3 {SUBID} penalty:{PEN} type:LEFT product:{PROD}bp".format(ID=id,SUBID=m.group("id"),PEN=m.group("penalty"),PROD=m.group("size"))+os.linesep
+output_handle.write(line)
+line = m.group("left")+os.linesep
+output_handle.write(line)
+line = ">{ID} primer3 {SUBID} penalty:{PEN} type:RIGHT product:{PROD}bp".format(ID=id,SUBID=m.group("id"),PEN=m.group("penalty"),PROD=m.group("size"))+os.linesep
+output_handle.write(line)
+line = m.group("right")+os.linesep
+output_handle.write(line)
+output_handle.close()
diff --git a/modules/primer3_results2fasta/main.nf b/modules/primer3_results2fasta/main.nf
index 04a43aa..088f048 100644
--- a/modules/primer3_results2fasta/main.nf
+++ b/modules/primer3_results2fasta/main.nf
@@ -9,35 +9,8 @@ process primer3_results2fasta {
     output:
     path "${results}.fa"
 
-    shell:
-    '''
-    #!/usr/bin/env python
-    import re
-    import os
-    import os.path
-    print("hello world!")
-
-    with open("!{results}", "r") as input_handle:
-    data = input_handle.read()
-    ##print(data)
-
-    id_match = re.search('SEQUENCE_ID=(.+)',data)
-    id = id_match.group(1)
-
-    bespoke_regex = '(?P<id>PRIMER_PAIR_[0-9]+)_PENALTY=(?P<penalty>[0-9.]+).+?PRIMER_LEFT_[0-9]+_SEQUENCE=(?P<left>[atcgATCGnN]+).+?PRIMER_RIGHT_[0-9]+_SEQUENCE=(?P<right>[atcgATCGnN]+).+?PRIMER_PAIR_[0-9]+_PRODUCT_SIZE=(?P<size>[0-9]+).+?PRIMER_PAIR_[0-9]+_PRODUCT_TM=[0-9.]+'
-
-    matches = list(re.finditer(bespoke_regex,data,flags=re.MULTILINE|re.DOTALL))
-
-    output_handle = open("!{results}.fa", "w")
-    for m in matches:
-    line = ">{ID} primer3 {SUBID} penalty:{PEN} type:LEFT product:{PROD}bp".format(ID=id,SUBID=m.group("id"),PEN=m.group("penalty"),PROD=m.group("size"))+os.linesep
-    output_handle.write(line)
-    line = m.group("left")+os.linesep
-    output_handle.write(line)
-    line = ">{ID} primer3 {SUBID} penalty:{PEN} type:RIGHT product:{PROD}bp".format(ID=id,SUBID=m.group("id"),PEN=m.group("penalty"),PROD=m.group("size"))+os.linesep
-    output_handle.write(line)
-    line = m.group("right")+os.linesep
-    output_handle.write(line)
-    output_handle.close()
-    '''
+    script:
+    """
+    results2fasta.py ${results} ${results}.fa
+    """
 }