🐛 Add my collection of OCR-D bug reproducers

ocrd-bugs/bug-lohenstein-ocrd-typegroups-classifier.sh

@@ -0,0 +1,13 @@
+#!/bin/bash -x
+cd `mktemp -d`
+wget https://ocr-d-repo.scc.kit.edu/api/v1/dataresources/8d8aa287-94ca-48e3-84a8-1ee602871550/data/lohenstein_agrippina_1665.ocrd.zip
+dtrx lohenstein_agrippina_1665.ocrd.zip
+cd lohenstein_agrippina_1665.ocrd/data
+ocrd_typegroups_classifier_parameters='
+  {
+    "network": "/home/mike/devel/OCR-D/monorepo/ocrd_typegroups_classifier/ocrd_typegroups_classifier/models/classifier.tgc",
+    "stride":143
+  }'
+ocrd-typegroups-classifier -l DEBUG \
+  -m mets.xml -I OCR-D-IMG -O OCR-D-FONTIDENT \
+  -p <(echo $ocrd_typegroups_classifier_parameters)

ocrd-bugs/bug-ocropy-segment-breakage.sh

@@ -0,0 +1,10 @@
+# zips all from https://ocr-d-repo.scc.kit.edu/api/v1/metastore/bagit
+for z in benner_herrnhuterey04_1748.ocrd.zip buerger_gedichte_1778.ocrd.zip estor_rechtsgelehrsamkeit02_1758.ocrd.zip lohenstein_agrippina_1665.ocrd.zip silesius_seelenlust01_1657.ocrd.zip; do
+  echo "== $z"
+  cd `mktemp -d`
+  cp /srv/data/OCR-D/$z .
+  dtrx $z
+  cd ${z//.zip}/data
+
+  ocrd-ocropy-segment -l DEBUG -m mets.xml -I OCR-D-IMG -O OCR-D-SEG-LINE 2>&1 | tail -n 1
+done

ocrd-bugs/bug-remote-image.sh

@@ -0,0 +1,7 @@
+#!/bin/sh
+set -x
+cd `mktemp -d`
+wget -q https://ocr-d-repo.scc.kit.edu/api/v1/dataresources/f15fb8c8-3842-4314-9a44-5e8b472d7bfc/data/buerger_gedichte_1778.ocrd.zip
+dtrx buerger_gedichte_1778.ocrd.zip
+cd buerger_gedichte_1778.ocrd/data
+ocrd workspace validate mets.xml

ocrd-bugs/bug-tesserocr-segment-line-no-description.sh

@@ -0,0 +1,2 @@
+#!/bin/bash -x
+ocrd-tesserocr-segment-line --help

ocrd-bugs/bug-tesserocr-segment-line-should-give-error.sh

@@ -0,0 +1,6 @@
+#!/bin/bash -x
+cd `mktemp -d`
+wget https://ocr-d-repo.scc.kit.edu/api/v1/dataresources/8d8aa287-94ca-48e3-84a8-1ee602871550/data/lohenstein_agrippina_1665.ocrd.zip
+dtrx lohenstein_agrippina_1665.ocrd.zip
+cd lohenstein_agrippina_1665.ocrd/data
+ocrd-tesserocr-segment-line -l DEBUG -m mets.xml -I DOES-NOT-EXIST -O OCR-D-SEG-REGION