| 
									
										
										
										
											2021-02-12 13:18:04 +01:00
										 |  |  | #!/bin/bash | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | set -e  # Abort on error | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | # Configuration | 
					
						
							|  |  |  | export LOG_LEVEL=${LOG_LEVEL:-INFO}  # /etc/ocrd_logging.py uses this to set level for all OCR-D modules | 
					
						
							|  |  |  | export TEXTEQUIV_LEVEL=word | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | # Command line parameters | 
					
						
							|  |  |  | OPTS=`getopt -o I: --long input-file-grp:,skip-validation -- "$@"` | 
					
						
							|  |  |  | eval set -- "$OPTS" | 
					
						
							|  |  |  | INPUT_FILE_GRP=OCR-D-IMG | 
					
						
							|  |  |  | SKIP_VALIDATION=false | 
					
						
							|  |  |  | while true; do | 
					
						
							|  |  |  |   case "$1" in | 
					
						
							|  |  |  |     -I|--input-file-grp) INPUT_FILE_GRP=$2; shift 2;; | 
					
						
							|  |  |  |     --skip-validation) SKIP_VALIDATION=true; shift;; | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  |     --) shift; break;; | 
					
						
							|  |  |  |     *) break;; | 
					
						
							|  |  |  |   esac | 
					
						
							|  |  |  | done | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | # Set up logging | 
					
						
							|  |  |  | if [ "$LOG_LEVEL" = "DEBUG" -o "$LOG_LEVEL" = "TRACE" ]; then | 
					
						
							|  |  |  |   set -x | 
					
						
							|  |  |  | fi | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | do_validate() { | 
					
						
							|  |  |  |   # Validate the workspace | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  |   # Both ocrd_tesserocr + ocrd_calamari produce segment coordinates that are not strictly within their parent's | 
					
						
							|  |  |  |   # coordinates: | 
					
						
							|  |  |  |   # | 
					
						
							|  |  |  |   #     INCONSISTENCY in [...] coords [...] not within parent coords | 
					
						
							|  |  |  |   # | 
					
						
							|  |  |  |   # → --page-coordinate-consistency off | 
					
						
							|  |  |  |   # | 
					
						
							|  |  |  |   # ocrd_tesserocr sometimes produces segment text results that aren't concatenating as expected by the validator: | 
					
						
							|  |  |  |   # | 
					
						
							|  |  |  |   #     INCONSISTENCY in [...]: text results '[...]' != concatenated '[...]' | 
					
						
							|  |  |  |   # | 
					
						
							|  |  |  |   # → --page-strictness lax | 
					
						
							|  |  |  |   # | 
					
						
							|  |  |  |   validate_options=' | 
					
						
							|  |  |  |     --skip dimension | 
					
						
							|  |  |  |     --skip pixel_density | 
					
						
							|  |  |  |     --page-strictness lax | 
					
						
							|  |  |  |     --page-coordinate-consistency off' | 
					
						
							|  |  |  |   if [ "$SKIP_VALIDATION" = false ]; then | 
					
						
							|  |  |  |     ocrd workspace validate $validate_options | 
					
						
							|  |  |  |   fi | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | main() { | 
					
						
							|  |  |  |   do_validate | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  |   ocrd-sbb-binarize --overwrite -I $INPUT_FILE_GRP -O OCR-D-IMG-BIN -P model "/var/lib/sbb_binarization" | 
					
						
							|  |  |  |   do_validate | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  |   ocrd-sbb-textline-detector --overwrite -I OCR-D-IMG-BIN -O OCR-D-SEG-LINE -P model "/var/lib/textline_detection" | 
					
						
							|  |  |  |   do_validate | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2022-09-16 18:31:11 +02:00
										 |  |  |   ocrd-calamari-recognize --overwrite -I OCR-D-SEG-LINE -O OCR-D-OCR-CALAMARI -P checkpoint_dir "/var/lib/calamari-models/GT4HistOCR/2019-12-11T11_10+0100/" -P textequiv_level "$TEXTEQUIV_LEVEL" | 
					
						
							| 
									
										
										
										
											2021-02-12 13:18:04 +01:00
										 |  |  |   do_validate | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2021-02-15 16:15:59 +01:00
										 |  |  |   ocrd-fileformat-transform --overwrite -I OCR-D-OCR-CALAMARI -O OCR-D-OCR-CALAMARI-ALTO | 
					
						
							|  |  |  |   do_validate | 
					
						
							| 
									
										
										
										
											2021-02-12 13:18:04 +01:00
										 |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | if [ "$LOG_LEVEL" = "DEBUG" -o "$LOG_LEVEL" = "TRACE" ]; then | 
					
						
							|  |  |  |   pip list || true | 
					
						
							|  |  |  | fi | 
					
						
							|  |  |  | main | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | # vim:tw=120: |