From 5e43e09beb39dea98adf26c7286b6b1941f792f2 Mon Sep 17 00:00:00 2001
From: Patrick Jentsch <p.jentsch@uni-bielefeld.de>
Date: Mon, 15 Apr 2019 10:25:57 +0200
Subject: [PATCH] Update

---
 ocr | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/ocr b/ocr
index 0eaaf83..80f5b95 100755
--- a/ocr
+++ b/ocr
@@ -84,14 +84,17 @@ class OCRWorkflow(WorkflowRunner):
         create_output_directories_job_number = 0
         for job in self.jobs:
             create_output_directories_job_number += 1
-            cmd = 'mkdir -p "%s" "%s" "%s" "%s" "%s" "%s"' % (
-                os.path.join(job["output_dir"], "tmp", "binarized_png"),
+            cmd = 'mkdir -p "%s" "%s" "%s" "%s"' % (
                 os.path.join(job["output_dir"], "tmp", "hocr"),
-                os.path.join(job["output_dir"], "tmp", "normalized_png"),
                 os.path.join(job["output_dir"], "tmp", "pdf"),
                 os.path.join(job["output_dir"], "tmp", "tiff"),
                 os.path.join(job["output_dir"], "tmp", "txt")
             )
+            if not self.skipBinarization:
+                cmd += ' "%s" "%s"' % (
+                    os.path.join(job["output_dir"], "tmp", "binarized_png"),
+                    os.path.join(job["output_dir"], "tmp", "normalized_png"),
+                )
             create_output_directories_jobs.append(self.addTask(label="create_output_directories_job_-_%i" % (create_output_directories_job_number), command=cmd))
 
         ###
@@ -237,20 +240,23 @@ class OCRWorkflow(WorkflowRunner):
         if self.keepIntermediates:
             for job in self.jobs:
                 cleanup_job_counter += 1
-                cmd = 'mv "%s"/*.bin.png "%s" && mv "%s"/*.hocr "%s" && mv "%s"/*.nrm.png "%s" && mv "%s"/*.pdf "%s" && mv "%s"/*.tif "%s" && mv "%s"/*.txt "%s"' % (
-                    os.path.join(job["output_dir"], "tmp"),
-                    os.path.join(job["output_dir"], "tmp", "binarized_png"),
+                cmd = 'mv "%s"/*.hocr "%s" && mv "%s"/*.pdf "%s" && mv "%s"/*.tif "%s" && mv "%s"/*.txt "%s"' % (
                     os.path.join(job["output_dir"], "tmp"),
                     os.path.join(job["output_dir"], "tmp", "hocr"),
                     os.path.join(job["output_dir"], "tmp"),
-                    os.path.join(job["output_dir"], "tmp", "normalized_png"),
-                    os.path.join(job["output_dir"], "tmp"),
                     os.path.join(job["output_dir"], "tmp", "pdf"),
                     os.path.join(job["output_dir"], "tmp"),
                     os.path.join(job["output_dir"], "tmp", "tiff"),
                     os.path.join(job["output_dir"], "tmp"),
                     os.path.join(job["output_dir"], "tmp", "txt")
                 )
+            if not self.skipBinarization:
+                cmd += ' && mv "%s"/*.bin.png "%s" && mv "%s"/*.nrm.png "%s"' % (
+                    os.path.join(job["output_dir"], "tmp"),
+                    os.path.join(job["output_dir"], "tmp", "binarized_png"),
+                    os.path.join(job["output_dir"], "tmp"),
+                    os.path.join(job["output_dir"], "tmp", "normalized_png"),
+                )
                 cleanup_jobs.append(self.addTask(label="cleanup_job_-_%i" % (cleanup_job_counter), command=cmd, dependencies=hocr_to_tei_jobs + pdf_merge_jobs + txt_merge_jobs))
         else:
             for job in self.jobs: