ocrd-workspace-from-images

#!/bin/bash
# Create an OCR-D workspace from images
#
#   ocrd-workspace-from-images *.png
#
# In order to produce a workspace that validates, this script makes best effort
# to generate random IDs and to create the necessary structures like the
# physical page sequence.

workspace_dir=`mktemp -d "workspace-XXXXX"`
workspace_id=`basename $workspace_dir`

ocrd workspace -d $workspace_dir init
ocrd workspace -d $workspace_dir set-id $workspace_id

make_file_id_from_filename() {
  filename="$1"
  file_id="$filename"
  file_id=`echo $file_id | sed 's#(.png|.tif|.jpe?g)$##i'`
  file_id=`echo $file_id | sed 's#[^A-Za-z0-9_-]#_#g'`

  echo "$file_id"
}

mkdir $workspace_dir/OCR-D-IMG
page_count=0
for img_orig in "$@"; do
  page_count=$(($page_count + 1))
  img="$workspace_dir/OCR-D-IMG/`basename $img_orig`"
  cp -L "$img_orig" "$img"
  file_id=`make_file_id_from_filename "$img"`
  mime_type=`file -b --mime-type "$img"`
  page_id=`printf "P%05d" $page_count`
  ocrd workspace -d $workspace_dir add -G OCR-D-IMG "$img" --file-id $file_id --page-id $page_id --mimetype $mime_type
done

ocrd workspace -d $workspace_dir validate
echo $workspace_dir