From aacac4e0a09f2a476ad558eb4789d1c4e3ed6bc2 Mon Sep 17 00:00:00 2001
From: Patrick Jentsch <p.jentsch@uni-bielefeld.de>
Date: Thu, 27 Jan 2022 13:48:16 +0100
Subject: [PATCH] Codestyle enhancements

---
 file-setup | 50 +++++++++++++++++++++++++++++++++++---------------
 1 file changed, 35 insertions(+), 15 deletions(-)

diff --git a/file-setup b/file-setup
index 7d14b9b..f61aa7b 100755
--- a/file-setup
+++ b/file-setup
@@ -7,7 +7,6 @@ __version__ = '0.1.0'
 from argparse import ArgumentParser
 from pyflow import WorkflowRunner
 import json
-import multiprocessing
 import os
 import sys
 
@@ -52,7 +51,9 @@ class CreatePDFWorkflow(WorkflowRunner):
             os.path.join(self.job.output_dir, '{}.pdf'.format(self.job.name))
         )
         cmd += ' && '
-        cmd += 'rm "{}"'.format(os.path.join(self.job.output_dir, 'inputs.txt'))  # noqa
+        cmd += 'rm "{}"'.format(
+            os.path.join(self.job.output_dir, 'inputs.txt')
+        )
         self.addTask(
             'convert',
             command=cmd,
@@ -68,6 +69,7 @@ class MainWorkflow(WorkflowRunner):
         self.jobs = []
 
     def collect_jobs(self):
+        self.jobs = []
         for dir in os.listdir(self.input_dir):
             if not os.path.isdir(os.path.join(self.input_dir, dir)):
                 continue
@@ -102,38 +104,53 @@ class MainWorkflow(WorkflowRunner):
             create_pdf_tasks.append(task)
 
         self.waitForTasks()
-        output_files = []
+        outputs = []
         for job in self.jobs:
             # Track output files
-            relative_output_dir = os.path.relpath(job.output_dir, start=self.output_dir)  # noqa
-            output_files.append(
+            relative_output_dir = os.path.relpath(
+                job.output_dir,
+                start=self.output_dir
+            )
+            outputs.append(
                 {
                     'description': 'PDF file without text layer.',
-                    'file': os.path.join(relative_output_dir, '{}.pdf'.format(job.name)),  # noqa
+                    'file': os.path.join(
+                        relative_output_dir,
+                        '{}.pdf'.format(job.name)
+                    ),
                     'mimetype': 'application/pdf'
                 }
             )
-        with open(os.path.join(self.output_dir, 'output_records.json'), 'w') as f:  # noqa
-            json.dump(output_files, f, indent=4)
+        with open(os.path.join(self.output_dir, 'outputs.json'), 'w') as f:
+            json.dump(outputs, f, indent=4)
 
 
 def parse_args():
     parser = ArgumentParser(description='Pipeline for merging images')
     parser.add_argument(
-        '-i', '--input-dir', help='Input directory', required=True)
+        '-i', '--input-dir',
+        help='Input directory',
+        required=True
+    )
     parser.add_argument(
-        '-o', '--output-dir', help='Output directory', required=True)
+        '-o', '--output-dir',
+        help='Output directory',
+        required=True
+    )
     parser.add_argument(
-        '--log-dir', help='Logging directory (Default: --output-dir)')
+        '--log-dir',
+        help='Logging directory (Default: --output-dir)'
+    )
     parser.add_argument(
         '--mem-mb',
-        help='Amount of system memory to be used (Default: min(--n-cores * 256, available system memory))',  # noqa
+        help='Amount of system memory to be used '
+             '(Default: min(--n-cores * 256, available system memory))',
         type=int
     )
     parser.add_argument(
         '--n-cores',
-        default=min(2, multiprocessing.cpu_count()),
-        help='Number of CPU threads to be used (Default: min(2, CPU count))',
+        default=1,
+        help='Number of CPU threads to be used',
         type=int
     )
     parser.add_argument(
@@ -162,7 +179,10 @@ def main():
     main_workflow = MainWorkflow(args.input_dir, args.output_dir)
     main_workflow.collect_jobs()
     retval = main_workflow.run(
-        dataDirRoot=args.log_dir, memMb=args.mem_mb, nCores=args.n_cores)  # noqa
+        dataDirRoot=args.log_dir,
+        memMb=args.mem_mb,
+        nCores=args.n_cores
+    )
     sys.exit(retval)