Fix enumeration in readme

README.md

@@ -14,10 +14,10 @@ This software implements a heavily parallelized pipeline to recognize text in PD
 
 1. Install Docker and Python 3.
 2. Clone this repository: `git clone https://gitlab.ub.uni-bielefeld.de/sfb1288inf/ocr.git`
-2. Build the Docker image: `docker build -t gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/ocr:v0.1.0 ocr`
+3. Build the Docker image: `docker build -t gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/ocr:v0.1.0 ocr`
-2. Add the wrapper script (`wrapper/ocr` relative to this README file) to your `${PATH}`.
+4. Add the wrapper script (`wrapper/ocr` relative to this README file) to your `${PATH}`.
-3. Create working directories for the pipeline: `mkdir -p /<my_data_location>/{input,models,output}`.
+5. Create working directories for the pipeline: `mkdir -p /<my_data_location>/{input,models,output}`.
-4. Place your Tesseract OCR model(s) inside `/<my_data_location>/models`.
+6. Place your Tesseract OCR model(s) inside `/<my_data_location>/models`.
 
 ## Use the Pipeline
 

ocr

@@ -385,7 +385,6 @@ class MainWorkflow(WorkflowRunner):
         self.input_dir = input_dir
         self.lang = lang
         self.output_dir = output_dir
-        self.output_files = []
         self.binarize = binarize
         self.jobs = []
 
@@ -528,33 +527,34 @@ class MainWorkflow(WorkflowRunner):
             create_txt_tasks.append(task)
 
         self.waitForTasks()
+        output_files = []
         for job in self.jobs:
             # Remove temporary directory
             os.rmdir(job.tmp_dir)
             # Track output files
             relative_output_dir = os.path.relpath(job.output_dir, start=self.output_dir)  # noqa
-            self.output_files.append(
+            output_files.append(
                 {
                     'description': 'Post correction package (.png and .hocr).',
                     'file': os.path.join(relative_output_dir, '{}.poco.zip'.format(job.name)),  # noqa
                     'mimetype': 'application/zip'
                 }
             )
-            self.output_files.append(
+            output_files.append(
                 {
                     'description': 'PDF file with text layer.',
                     'file': os.path.join(relative_output_dir, '{}.pdf'.format(job.name)),  # noqa
                     'mimetype': 'application/pdf'
                 }
             )
-            self.output_files.append(
+            output_files.append(
                 {
                     'description': 'Plain text file.',
                     'file': os.path.join(relative_output_dir, '{}.txt'.format(job.name)),  # noqa
                     'mimetype': 'text/plain'
                 }
             )
-            self.output_files.append(
+            output_files.append(
                 {
                     'description': 'TEI compliant XML file.',
                     'file': os.path.join(relative_output_dir, '{}.tei.xml'.format(job.name)),  # noqa
@@ -562,7 +562,7 @@ class MainWorkflow(WorkflowRunner):
                 }
             )
         with open(os.path.join(self.output_dir, 'output_records.json'), 'w') as f:  # noqa
-            json.dump(self.output_files, f, indent=4)
+            json.dump(output_files, f, indent=4)
 
 
 def parse_args():