From 23535998f7532942d481f3729682969e19c228b6 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Mon, 6 Oct 2025 21:27:21 +0200
Subject: [PATCH] tests: symlink OCR models into layout model directory

(so layout with OCR options works with our split model packages)
---
 Makefile          | 19 +++++++++++--------
 tests/test_run.py |  3 ++-
 2 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/Makefile b/Makefile
index 357aa47..5d190b2 100644
--- a/Makefile
+++ b/Makefile
@@ -90,26 +90,29 @@ deps-test: $(OCR_MODELNAME)
 endif
 deps-test: $(BIN_MODELNAME) $(SEG_MODELNAME)
 	$(PIP) install -r requirements-test.txt
+ifeq (OCR,$(findstring OCR, $(EXTRAS)))
+	ln -s $(OCR_MODELNAME)/* $(SEG_MODELNAME)/
+endif
 
 smoke-test: TMPDIR != mktemp -d
 smoke-test: tests/resources/kant_aufklaerung_1784_0020.tif
 	# layout analysis:
-	eynollah layout -i $< -o $(TMPDIR) -m $(CURDIR)/models_layout_v0_5_0
+	eynollah layout -i $< -o $(TMPDIR) -m $(CURDIR)/$(SEG_MODELNAME)
 	fgrep -q http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15 $(TMPDIR)/$(basename $(<F)).xml
 	fgrep -c -e TextRegion -e ImageRegion -e SeparatorRegion $(TMPDIR)/$(basename $(<F)).xml
 	# layout, directory mode (skip one, add one):
-	eynollah layout -di $(<D) -o $(TMPDIR) -m $(CURDIR)/models_layout_v0_5_0
+	eynollah layout -di $(<D) -o $(TMPDIR) -m $(CURDIR)/$(SEG_MODELNAME)
 	test -s $(TMPDIR)/euler_rechenkunst01_1738_0025.xml
 	# mbreorder, directory mode (overwrite):
-	eynollah machine-based-reading-order -di $(<D) -o $(TMPDIR) -m $(CURDIR)/models_layout_v0_5_0
+	eynollah machine-based-reading-order -di $(<D) -o $(TMPDIR) -m $(CURDIR)/$(SEG_MODELNAME)
 	fgrep -q http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15 $(TMPDIR)/$(basename $(<F)).xml
 	fgrep -c -e RegionRefIndexed $(TMPDIR)/$(basename $(<F)).xml
 	# binarize:
-	eynollah binarization -m $(CURDIR)/default-2021-03-09 -i $< -o $(TMPDIR)/$(<F)
+	eynollah binarization -m $(CURDIR)/$(BIN_MODELNAME) -i $< -o $(TMPDIR)/$(<F)
 	test -s $(TMPDIR)/$(<F)
 	@set -x; test "$$(identify -format '%w %h' $<)" = "$$(identify -format '%w %h' $(TMPDIR)/$(<F))"
 	# enhance:
-	eynollah enhancement -m $(CURDIR)/models_layout_v0_5_0 -sos -i $< -o $(TMPDIR) -O
+	eynollah enhancement -m $(CURDIR)/$(SEG_MODELNAME) -sos -i $< -o $(TMPDIR) -O
 	test -s $(TMPDIR)/$(<F)
 	@set -x; test "$$(identify -format '%w %h' $<)" = "$$(identify -format '%w %h' $(TMPDIR)/$(<F))"
 	$(RM) -r $(TMPDIR)
@@ -120,12 +123,12 @@ ocrd-test: tests/resources/kant_aufklaerung_1784_0020.tif
 	cp $< $(TMPDIR)
 	ocrd workspace -d $(TMPDIR) init
 	ocrd workspace -d $(TMPDIR) add -G OCR-D-IMG -g PHYS_0020 -i OCR-D-IMG_0020 $(<F)
-	ocrd-eynollah-segment -w $(TMPDIR) -I OCR-D-IMG -O OCR-D-SEG -P models $(CURDIR)/models_layout_v0_5_0
+	ocrd-eynollah-segment -w $(TMPDIR) -I OCR-D-IMG -O OCR-D-SEG -P models $(CURDIR)/$(SEG_MODELNAME)
 	result=$$(ocrd workspace -d $(TMPDIR) find -G OCR-D-SEG); \
 	fgrep -q http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15 $(TMPDIR)/$$result && \
 	fgrep -c -e TextRegion -e ImageRegion -e SeparatorRegion $(TMPDIR)/$$result
-	ocrd-sbb-binarize -w $(TMPDIR) -I OCR-D-IMG -O OCR-D-BIN -P model $(CURDIR)/default-2021-03-09
-	ocrd-sbb-binarize -w $(TMPDIR) -I OCR-D-SEG -O OCR-D-SEG-BIN -P model $(CURDIR)/default-2021-03-09 -P operation_level region
+	ocrd-sbb-binarize -w $(TMPDIR) -I OCR-D-IMG -O OCR-D-BIN -P model $(CURDIR)/$(BIN_MODELNAME)
+	ocrd-sbb-binarize -w $(TMPDIR) -I OCR-D-SEG -O OCR-D-SEG-BIN -P model $(CURDIR)/$(BIN_MODELNAME) -P operation_level region
 	$(RM) -r $(TMPDIR)
 
 # Run unit tests
diff --git a/tests/test_run.py b/tests/test_run.py
index d69f021..98cee30 100644
--- a/tests/test_run.py
+++ b/tests/test_run.py
@@ -17,7 +17,7 @@ from ocrd_models.constants import NAMESPACES as NS
 testdir = Path(__file__).parent.resolve()
 
 MODELS_LAYOUT = environ.get('MODELS_LAYOUT', str(testdir.joinpath('..', 'models_layout_v0_5_0').resolve()))
-MODELS_OCR = environ.get('MODELS_OCR', str(testdir.joinpath('..', 'models_ocr_v0_5_0').resolve()))
+MODELS_OCR = environ.get('MODELS_OCR', str(testdir.joinpath('..', 'models_ocr_v0_5_1').resolve()))
 MODELS_BIN = environ.get('MODELS_BIN', str(testdir.joinpath('..', 'default-2021-03-09').resolve()))
 
 @pytest.mark.parametrize(
@@ -31,6 +31,7 @@ MODELS_BIN = environ.get('MODELS_BIN', str(testdir.joinpath('..', 'default-2021-
              "--textline_light", "--light_version"],
             # -ep ...
             # -eoi ...
+            # FIXME: find out whether OCR extra was installed, otherwise skip these
             ["--do_ocr"],
             ["--do_ocr", "--light_version", "--textline_light"],
             ["--do_ocr", "--transformer_ocr"],