🧹 Remove old build scripts/docs

master
Gerber, Mike 12 months ago
parent 9d2ebd9cec
commit 0166e44e37

@ -3,7 +3,6 @@ How to add a processor
* Add model download to `build` (if necessary)
* Add a Dockerfile
* Add commands to `wrapper/qurator/ocrd_galley/cli.py`
* Add to `.drone.star`
Releasing
---------

27
build

@ -22,33 +22,6 @@ echo "$sub_images"
echo
DATA_SUBDIR=data
get_from_annex() {
annex_get 'calamari-models/GT4HistOCR/2019-07-22T15_49+0200/*.ckpt*'
annex_get 'calamari-models/GT4HistOCR/2019-12-11T11_10+0100/*.ckpt*'
annex_get 'calamari-models/GT4HistOCR/2019-12-18T17_24+0100*/*.ckpt*'
annex_get 'mirror/github.com/Calamari-OCR/calamari_models/gt4histocr/*.ckpt*'
annex_get 'tesseract-models/GT4HistOCR/*.traineddata'
annex_get 'textline_detection/*.h5'
annex_get 'mirror/github.com/tesseract-ocr/tessdata_best/archive/4.0.0-repacked.tar.gz'
annex_get 'sbb_binarization/2021-03-09/*.h5'
annex_get 'eynollah/*.h5'
}
get_from_web() {
download_to 'https://qurator-data.de/calamari-models/GT4HistOCR/model.tar.xz' 'calamari-models/GT4HistOCR/2019-07-22T15_49+0200'
download_to 'https://qurator-data.de/calamari-models/GT4HistOCR/2019-12-11T11_10+0100/model.tar.xz' 'calamari-models/GT4HistOCR/2019-12-11T11_10+0100'
download_to 'https://qurator-data.de/tesseract-models/GT4HistOCR/models.tar' 'tesseract-models/GT4HistOCR'
download_to 'https://qurator-data.de/sbb_textline_detector/models.tar.gz' 'textline_detection'
download_to --strip-components 1 'https://qurator-data.de/sbb_binarization/2021-03-09/models.tar.gz' 'sbb_binarization/2021-03-09'
download_to --no-unpack 'https://qurator-data.de/mirror/github.com/tesseract-ocr/tessdata_best/archive/4.0.0-repacked.tar.gz' 'mirror/github.com/tesseract-ocr/tessdata_best/archive/4.0.0-repacked.tar.gz'
download_to --strip-components 1 'https://qurator-data.de/eynollah/models_eynollah.tar.gz' 'eynollah'
}
. $self_dir/qurator_data_lib.sh
#handle_data
# Update base images if we build a core image
if echo "$sub_images" | grep -q core; then
docker pull ubuntu:18.04

@ -1,18 +0,0 @@
#!/bin/bash -x
set -e
self=`realpath $0`
self_dir=`dirname "$self"`
DATA_SUBDIR=data
get_from_web() {
download_to 'https://qurator-data.de/calamari-models/GT4HistOCR/model.tar.xz' 'calamari-models/GT4HistOCR/2019-07-22T15_49+0200'
download_to 'https://qurator-data.de/calamari-models/GT4HistOCR/2019-12-11T11_10+0100/model.tar.xz' 'calamari-models/GT4HistOCR/2019-12-11T11_10+0100'
download_to 'https://qurator-data.de/tesseract-models/GT4HistOCR/models.tar' 'tesseract-models/GT4HistOCR'
download_to 'https://qurator-data.de/sbb_textline_detector/models.tar.gz' 'textline_detection'
download_to --strip-components 1 'https://qurator-data.de/sbb_binarization/2021-03-09/models.tar.gz' 'sbb_binarization/2021-03-09'
download_to --no-unpack 'https://qurator-data.de/mirror/github.com/tesseract-ocr/tessdata_best/archive/4.0.0-repacked.tar.gz' 'mirror/github.com/tesseract-ocr/tessdata_best/archive/4.0.0-repacked.tar.gz'
download_to --strip-components 1 'https://qurator-data.de/eynollah/models_eynollah.tar.gz' 'eynollah'
}
. $self_dir/qurator_data_lib.sh
handle_data
Loading…
Cancel
Save