From fcade690de59249a2789c26e8f668f36f8f4e075 Mon Sep 17 00:00:00 2001
From: Frederick Muriuki Muriithi
Date: Mon, 2 May 2022 13:04:03 +0300
Subject: Optimise strain names parsing

- Use a way faster way of parsing the strains file
---
 qc_app/parse.py | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

(limited to 'qc_app')

diff --git a/qc_app/parse.py b/qc_app/parse.py
index 795cc01..baad9a6 100644
--- a/qc_app/parse.py
+++ b/qc_app/parse.py
@@ -19,8 +19,7 @@ from quality_control.parsing import (
     FileType,
     parse_file,
     strain_names,
-    parse_errors,
-    parse_strains)
+    parse_errors)
 
 parsebp = Blueprint("parse", __name__)
 
@@ -34,8 +33,7 @@ def queued_parse(
         try:
             job_meta = jobs.update_meta(
                 dbconn, job_id, status = "in-progress", progress = 0)
-            parsed = parse_file(
-                filepath, filetype, strain_names(parse_strains(strainsfile)))
+            parsed = parse_file(filepath, filetype, strain_names(strainsfile))
             for line, curr_size in parsed:
                 job_meta = jobs.update_meta(
                     dbconn, job_id,
@@ -174,11 +172,10 @@ def queued_collect_errors(
             dbconn = sqlite3.connect(dbpath)
             job_meta = jobs.retrieve_meta(dbconn, job.get_id())
             for error in parse_errors(
-                    filepath, filetype, strain_names(parse_strains(strainsfile)),
+                    filepath, filetype, strain_names(strainsfile),
                     seek_pos):
                 count = count + 1
                 progress  = ((error["position"] / job_meta["filesize"]) * 100)
-                print(f"CURRENT PROGRESS: {progress}")
                 job_meta = jobs.update_meta(
                     dbconn, job_id, message = f"Collected {count} errors",
                     progress = progress)
-- 
cgit v1.2.3