diff --git a/ocr b/ocr index b54d8d9..4e70c4d 100755 --- a/ocr +++ b/ocr @@ -145,7 +145,7 @@ class OCRWorkflow(WorkflowRunner): tesseract_job_number = 0 for job in self.jobs: # This list is empty if you don't wait for ocropus_nlbin_jobs to complete - for file in filter(lambda x: self.skipBinarization or x.endswith(".bin.png"), os.listdir(os.path.join(job["output_dir"], "tmp", "tiff_files" if self.skipBinarization else "ocropus-nlbin")): + for file in filter(lambda x: self.skipBinarization or x.endswith(".bin.png"), os.listdir(os.path.join(job["output_dir"], "tmp", "tiff_files" if self.skipBinarization else "ocropus-nlbin"))): tesseract_job_number += 1 cmd = 'tesseract "%s" "%s" -l "%s" hocr pdf txt' % ( os.path.join(job["output_dir"], "tmp", "tiff_files" if self.skipBinarization else "ocropus-nlbin", file),