refactor cli tests

src/eynollah/eynollah_ocr.py

@@ -59,7 +59,7 @@ class Eynollah_ocr:
         export_textline_images_and_text: bool=False,
         do_not_mask_with_textline_contour: bool=False,
         pref_of_dataset=None,
-        min_conf_value_of_textline_text : float=0.3,
+        min_conf_value_of_textline_text : Optional[float]=None,
         logger: Optional[Logger]=None,
     ):
         self.tr_ocr = tr_ocr
@@ -69,7 +69,7 @@ class Eynollah_ocr:
         self.do_not_mask_with_textline_contour = do_not_mask_with_textline_contour
         # prefix or dataset
         self.pref_of_dataset = pref_of_dataset
-        self.logger = logger if logger else getLogger('eynollah')
+        self.logger = logger if logger else getLogger('eynollah.ocr')
         self.model_zoo = EynollahModelZoo(basedir=dir_models)
         
         # TODO: Properly document what 'export_textline_images_and_text' is about
@@ -77,21 +77,15 @@ class Eynollah_ocr:
             self.logger.info("export_textline_images_and_text was set, so no actual models are loaded")
             return
 
-        self.min_conf_value_of_textline_text = min_conf_value_of_textline_text
+        self.min_conf_value_of_textline_text = min_conf_value_of_textline_text if min_conf_value_of_textline_text else 0.3
         self.b_s = 2 if batch_size is None and tr_ocr else 8 if batch_size is None else batch_size
 
         if tr_ocr:
-            self.model_zoo.load_model('trocr_processor', '')
+            self.model_zoo.load_model('trocr_processor')
-            if model_name:
+            self.model_zoo.load_model('ocr', 'tr', model_path_override=model_name)
-                self.model_zoo.load_model('ocr', 'tr', model_name)
-            else:
-                self.model_zoo.load_model('ocr', 'tr')
             self.model_zoo.get('ocr').to(self.device)
         else:
-            if model_name:
+            self.model_zoo.load_model('ocr', '', model_path_override=model_name)
-                self.model_zoo.load_model('ocr', '', model_name)
-            else:
-                self.model_zoo.load_model('ocr', '')
             self.model_zoo.load_model('num_to_char')
             self.end_character = len(self.model_zoo.load_model('characters')) + 2
 
@@ -206,10 +200,10 @@ class Eynollah_ocr:
                                             cropped_lines = []
                                             indexer_b_s = 0
                                             
-                                            pixel_values_merged = self.model_zoo.get('processor')(imgs, return_tensors="pt").pixel_values
+                                            pixel_values_merged = self.model_zoo.get('trocr_processor')(imgs, return_tensors="pt").pixel_values
                                             generated_ids_merged = self.model_zoo.get('ocr').generate(
                                                 pixel_values_merged.to(self.device))
-                                            generated_text_merged = self.model_zoo.get('processor').batch_decode(
+                                            generated_text_merged = self.model_zoo.get('trocr_processor').batch_decode(
                                                 generated_ids_merged, skip_special_tokens=True)
                                             
                                             extracted_texts = extracted_texts + generated_text_merged
@@ -229,10 +223,10 @@ class Eynollah_ocr:
                                                 cropped_lines = []
                                                 indexer_b_s = 0
                                                 
-                                                pixel_values_merged = self.model_zoo.get('processor')(imgs, return_tensors="pt").pixel_values
+                                                pixel_values_merged = self.model_zoo.get('trocr_processor')(imgs, return_tensors="pt").pixel_values
                                                 generated_ids_merged = self.model_zoo.get('ocr').generate(
                                                     pixel_values_merged.to(self.device))
-                                                generated_text_merged = self.model_zoo.get('processor').batch_decode(
+                                                generated_text_merged = self.model_zoo.get('trocr_processor').batch_decode(
                                                     generated_ids_merged, skip_special_tokens=True)
                                                 
                                                 extracted_texts = extracted_texts + generated_text_merged
@@ -249,10 +243,10 @@ class Eynollah_ocr:
                                                 cropped_lines = []
                                                 indexer_b_s = 0
                                                 
-                                                pixel_values_merged = self.model_zoo.get('processor')(imgs, return_tensors="pt").pixel_values
+                                                pixel_values_merged = self.model_zoo.get('trocr_processor')(imgs, return_tensors="pt").pixel_values
                                                 generated_ids_merged = self.model_zoo.get('ocr').generate(
                                                     pixel_values_merged.to(self.device))
-                                                generated_text_merged = self.model_zoo.get('processor').batch_decode(
+                                                generated_text_merged = self.model_zoo.get('trocr_processor').batch_decode(
                                                     generated_ids_merged, skip_special_tokens=True)
                                                 
                                                 extracted_texts = extracted_texts + generated_text_merged
@@ -267,10 +261,10 @@ class Eynollah_ocr:
                                                 cropped_lines = []
                                                 indexer_b_s = 0
                                                 
-                                                pixel_values_merged = self.model_zoo.get('processor')(imgs, return_tensors="pt").pixel_values
+                                                pixel_values_merged = self.model_zoo.get('trocr_processor')(imgs, return_tensors="pt").pixel_values
                                                 generated_ids_merged = self.model_zoo.get('ocr').generate(
                                                     pixel_values_merged.to(self.device))
-                                                generated_text_merged = self.model_zoo.get('processor').batch_decode(
+                                                generated_text_merged = self.model_zoo.get('trocr_processor').batch_decode(
                                                     generated_ids_merged, skip_special_tokens=True)
                                                 
                                                 extracted_texts = extracted_texts + generated_text_merged
@@ -284,9 +278,9 @@ class Eynollah_ocr:
                     cropped_lines = []
                     indexer_b_s = 0
                     
-                    pixel_values_merged = self.model_zoo.get('processor')(imgs, return_tensors="pt").pixel_values
+                    pixel_values_merged = self.model_zoo.get('trocr_processor')(imgs, return_tensors="pt").pixel_values
                     generated_ids_merged = self.model_zoo.get('ocr').generate(pixel_values_merged.to(self.device))
-                    generated_text_merged = self.model_zoo.get('processor').batch_decode(generated_ids_merged, skip_special_tokens=True)
+                    generated_text_merged = self.model_zoo.get('trocr_processor').batch_decode(generated_ids_merged, skip_special_tokens=True)
                     
                     extracted_texts = extracted_texts + generated_text_merged
                     
@@ -301,10 +295,10 @@ class Eynollah_ocr:
                         ####n_start = i*self.b_s
                         ####n_end = (i+1)*self.b_s
                         ####imgs = cropped_lines[n_start:n_end]
-                    ####pixel_values_merged = self.model_zoo.get('processor')(imgs, return_tensors="pt").pixel_values
+                    ####pixel_values_merged = self.model_zoo.get('trocr_processor')(imgs, return_tensors="pt").pixel_values
                     ####generated_ids_merged = self.model_ocr.generate(
                     ####    pixel_values_merged.to(self.device))
-                    ####generated_text_merged = self.model_zoo.get('processor').batch_decode(
+                    ####generated_text_merged = self.model_zoo.get('trocr_processor').batch_decode(
                     ####    generated_ids_merged, skip_special_tokens=True)
                     
                     ####extracted_texts = extracted_texts + generated_text_merged

src/eynollah/image_enhancer.py

@@ -50,7 +50,7 @@ class Enhancer:
         else:
             self.num_col_lower = num_col_lower
             
-        self.logger = logger if logger else getLogger('enhancement')
+        self.logger = logger if logger else getLogger('eynollah.enhance')
         self.model_zoo = EynollahModelZoo(basedir=dir_models)
         for v in ['binarization', 'enhancement', 'col_classifier', 'page']:
             self.model_zoo.load_model(v)
@@ -142,7 +142,7 @@ class Enhancer:
                     index_y_d = img_h - img_height_model
 
                 img_patch = img[np.newaxis, index_y_d:index_y_u, index_x_d:index_x_u, :]
-                label_p_pred = self.model_zoo.get('enhancement', Model).predict(img_patch, verbose=0)
+                label_p_pred = self.model_zoo.get('enhancement', Model).predict(img_patch, verbose='0')
                 seg = label_p_pred[0, :, :, :] * 255
 
                 if i == 0 and j == 0:
@@ -667,7 +667,7 @@ class Enhancer:
         t0 = time.time()
         img_res, is_image_enhanced, num_col_classifier, num_column_is_classified = self.run_enhancement(light_version=False)
         
-        return img_res
+        return img_res, is_image_enhanced
         
         
     def run(self,
@@ -705,9 +705,18 @@ class Enhancer:
                     self.logger.warning("will skip input for existing output file '%s'", self.output_filename)
                     continue
 
-            image_enhanced = self.run_single()
+            did_resize = False
+            image_enhanced, did_enhance = self.run_single()
             if self.save_org_scale:
                 image_enhanced = resize_image(image_enhanced, self.h_org, self.w_org)
+                did_resize = True
+
+            self.logger.info(
+                "Image %s was %senhanced%s.",
+                img_filename,
+                '' if did_enhance else 'not ',
+                'and resized' if did_resize else ''
+            )
             
             cv2.imwrite(self.output_filename, image_enhanced)
             

src/eynollah/model_zoo/model_zoo.py

@@ -84,10 +84,13 @@ class EynollahModelZoo:
         self,
         model_category: str,
         model_variant: str = '',
+        model_path_override: Optional[str] = None,
     ) -> AnyModel:
         """
         Load any model
         """
+        if model_path_override:
+            self.override_models((model_category, model_variant, model_path_override))
         model_path = self.model_path(model_category, model_variant)
         if model_path.suffix == '.h5' and Path(model_path.stem).exists():
             # prefer SavedModel over HDF5 format if it exists
@@ -183,5 +186,5 @@ class EynollahModelZoo:
         Ensure that a loaded models is not referenced by ``self._loaded`` anymore
         """
         if hasattr(self, '_loaded') and getattr(self, '_loaded'):
-            for needle in self._loaded.keys():
+            for needle in list(self._loaded.keys()):
                 del self._loaded[needle]

src/eynollah/sbb_binarize.py

@@ -322,8 +322,7 @@ class SbbBinarizer:
                 image = cv2.imread(image_path)
             img_last = 0
             for n, (model_file, model) in enumerate(self.models.items()):
-                self.log.info('Predicting with model %s [%s/%s]' % (model_file, n + 1, len(self.models.keys())))
+                self.log.info('Predicting %s with model %s [%s/%s]', image_path if image_path else '[image]', model_file, n + 1, len(self.models.keys()))
-
                 res = self.predict(model, image, use_patches)
 
                 img_fin = np.zeros((res.shape[0], res.shape[1], 3))
@@ -348,11 +347,11 @@ class SbbBinarizer:
             ls_imgs = list(filter(is_image_filename, os.listdir(dir_in)))
             for image_name in ls_imgs:
                 image_stem = image_name.split('.')[0]
-                print(image_name,'image_name')
+                # print(image_name,'image_name')
                 image = cv2.imread(os.path.join(dir_in,image_name) )
                 img_last = 0
                 for n, (model_file, model) in enumerate(self.models.items()):
-                    self.log.info('Predicting with model %s [%s/%s]' % (model_file, n + 1, len(self.models.keys())))
+                    self.log.info('Predicting %s with model %s [%s/%s]', image_name, model_file, n + 1, len(self.models.keys()))
 
                     res = self.predict(model, image, use_patches)
 

tests/cli_tests/conftest.py

@@ -0,0 +1,36 @@
+from typing import List
+from click import Command
+import pytest
+import logging
+
+from click.testing import CliRunner, Result
+
+@pytest.fixture
+def run_eynollah_ok_and_check_logs(
+    pytestconfig,
+    caplog,
+    model_dir,
+    eynollah_log_filter,
+):
+    """
+    Generates a Click Runner for `cli`, injects model_path and logging level
+    to `args`, runs the command and checks whether the logs generated contain
+    every fragment in `expected_logs`
+    """
+
+    def _run_click_ok_logs(cli: Command, args: List[str], expected_logs: List[str]) -> Result:
+        args = ['-m', model_dir] + args
+        if pytestconfig.getoption('verbose') > 0:
+            args.extend(['-l', 'DEBUG'])
+        caplog.set_level(logging.INFO)
+        runner = CliRunner()
+        with caplog.filtering(eynollah_log_filter):
+            result = runner.invoke(cli, args, catch_exceptions=False)
+        assert result.exit_code == 0, result.stdout
+        if expected_logs:
+            logmsgs = [logrec.message for logrec in caplog.records]
+            assert any(logmsg.startswith(needle) for needle in expected_logs for logmsg in logmsgs), f'{expected_logs} not in {logmsgs}'
+        return result
+
+    return _run_click_ok_logs
+

tests/cli_tests/test_binarization.py

@@ -0,0 +1,58 @@
+import pytest
+from PIL import Image
+from eynollah.cli import (
+    binarization as binarization_cli,
+)
+from ocrd_modelfactory import page_from_file
+from ocrd_models.constants import NAMESPACES as NS
+
+@pytest.mark.parametrize(
+    "options",
+    [
+            [], # defaults
+            ["--no-patches"],
+    ], ids=str)
+def test_run_eynollah_binarization_filename(
+    tmp_path,
+    run_eynollah_ok_and_check_logs,
+    tests_dir,
+    options,
+):
+    infile = tests_dir.joinpath('resources/kant_aufklaerung_1784_0020.tif')
+    outfile = tmp_path.joinpath('kant_aufklaerung_1784_0020.png')
+    run_eynollah_ok_and_check_logs(
+        binarization_cli,
+        [
+            '-i', str(infile),
+            '-o', str(outfile),
+        ] + options,
+        [
+            'Predicting'
+        ]
+    )
+    assert outfile.exists()
+    with Image.open(infile) as original_img:
+        original_size = original_img.size
+    with Image.open(outfile) as binarized_img:
+        binarized_size = binarized_img.size
+    assert original_size == binarized_size
+
+def test_run_eynollah_binarization_directory(
+    tmp_path,
+    run_eynollah_ok_and_check_logs,
+    resources_dir,
+    image_resources,
+):
+    outdir = tmp_path
+    run_eynollah_ok_and_check_logs(
+        binarization_cli,
+        [
+            '-di', str(resources_dir),
+            '-o', str(outdir),
+        ],
+        [
+            f'Predicting {image_resources[0].name}',
+            f'Predicting {image_resources[1].name}',
+        ]
+    )
+    assert len(list(outdir.iterdir())) == 2

tests/cli_tests/test_enhance.py

@@ -0,0 +1,57 @@
+import pytest
+from PIL import Image
+from eynollah.cli import (
+    enhancement as enhancement_cli,
+)
+from ocrd_modelfactory import page_from_file
+from ocrd_models.constants import NAMESPACES as NS
+
+@pytest.mark.parametrize(
+    "options",
+    [
+            [], # defaults
+            ["-sos"],
+    ], ids=str)
+def test_run_eynollah_enhancement_filename(
+    tmp_path,
+    resources_dir,
+    run_eynollah_ok_and_check_logs,
+    options,
+):
+    infile = resources_dir / 'kant_aufklaerung_1784_0020.tif'
+    outfile = tmp_path.joinpath('kant_aufklaerung_1784_0020.png')
+    run_eynollah_ok_and_check_logs(
+        enhancement_cli,
+        [
+            '-i', str(infile),
+            '-o', str(outfile.parent),
+        ] + options,
+        [
+            'Image was enhanced',
+        ]
+    )
+    with Image.open(infile) as original_img:
+        original_size = original_img.size
+    with Image.open(outfile) as enhanced_img:
+        enhanced_size = enhanced_img.size
+    assert (original_size == enhanced_size) == ("-sos" in options)
+
+def test_run_eynollah_enhancement_directory(
+    tmp_path,
+    resources_dir,
+    image_resources,
+    run_eynollah_ok_and_check_logs,
+):
+    outdir = tmp_path
+    run_eynollah_ok_and_check_logs(
+        enhancement_cli,
+        [
+            '-di', str(resources_dir),
+            '-o', str(outdir),
+        ],
+        [
+            f'Image {image_resources[0]} was enhanced',
+            f'Image {image_resources[1]} was enhanced',
+        ]
+    )
+    assert len(list(outdir.iterdir())) == 2

tests/cli_tests/test_layout.py

@@ -0,0 +1,109 @@
+import pytest
+from eynollah.cli import (
+    layout as layout_cli,
+)
+from ocrd_modelfactory import page_from_file
+from ocrd_models.constants import NAMESPACES as NS
+
+@pytest.mark.parametrize(
+    "options",
+    [
+            [], # defaults
+            #["--allow_scaling", "--curved-line"],
+            ["--allow_scaling", "--curved-line", "--full-layout"],
+            ["--allow_scaling", "--curved-line", "--full-layout", "--reading_order_machine_based"],
+            ["--allow_scaling", "--curved-line", "--full-layout", "--reading_order_machine_based",
+             "--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"],
+            #["--do_ocr", "--transformer_ocr", "--light_version", "--textline_light"],
+            ["--do_ocr", "--transformer_ocr", "--light_version", "--textline_light", "--full-layout"],
+            # --skip_layout_and_reading_order
+    ], ids=str)
+def test_run_eynollah_layout_filename(
+    tmp_path,
+    run_eynollah_ok_and_check_logs,
+    resources_dir,
+    options,
+):
+    outdir = tmp_path
+    infile = resources_dir / 'kant_aufklaerung_1784_0020.tif'
+    outfile = tmp_path / 'kant_aufklaerung_1784_0020.xml'
+    run_eynollah_ok_and_check_logs(
+        layout_cli,
+        [
+        '-i', str(infile),
+        '-o', str(outfile.parent),
+        ] + options,
+        [
+            str(infile)
+        ]
+    )
+    assert outfile.exists()
+    tree = page_from_file(str(outfile)).etree
+    regions = tree.xpath("//page:TextRegion", namespaces=NS)
+    assert len(regions) >= 2, "result is inaccurate"
+    regions = tree.xpath("//page:SeparatorRegion", namespaces=NS)
+    assert len(regions) >= 2, "result is inaccurate"
+    lines = tree.xpath("//page:TextLine", namespaces=NS)
+    assert len(lines) == 31, "result is inaccurate" # 29 paragraph lines, 1 page and 1 catch-word line
+
+@pytest.mark.parametrize(
+    "options",
+    [
+            ["--tables"],
+            ["--tables", "--full-layout"],
+            ["--tables", "--full-layout", "--textline_light", "--light_version"],
+    ], ids=str)
+def test_run_eynollah_layout_filename2(
+    tmp_path,
+    resources_dir,
+    run_eynollah_ok_and_check_logs,
+    options,
+):
+    infile = resources_dir / 'euler_rechenkunst01_1738_0025.tif'
+    outfile = tmp_path / 'euler_rechenkunst01_1738_0025.xml'
+    run_eynollah_ok_and_check_logs(
+        layout_cli,
+        [
+            '-i', str(infile),
+            '-o', str(outfile.parent),
+        ] + options,
+        [
+            infile
+        ]
+    )
+    assert outfile.exists()
+    tree = page_from_file(str(outfile)).etree
+    regions = tree.xpath("//page:TextRegion", namespaces=NS)
+    assert len(regions) >= 2, "result is inaccurate"
+    regions = tree.xpath("//page:TableRegion", namespaces=NS)
+    # model/decoding is not very precise, so (depending on mode) we can get fractures/splits/FP
+    assert len(regions) >= 1, "result is inaccurate"
+    regions = tree.xpath("//page:SeparatorRegion", namespaces=NS)
+    assert len(regions) >= 2, "result is inaccurate"
+    lines = tree.xpath("//page:TextLine", namespaces=NS)
+    assert len(lines) >= 2, "result is inaccurate" # mostly table (if detected correctly), but 1 page and 1 catch-word line
+
+def test_run_eynollah_layout_directory(
+    tmp_path,
+    resources_dir,
+    run_eynollah_ok_and_check_logs,
+):
+    outdir = tmp_path
+    run_eynollah_ok_and_check_logs(
+        layout_cli,
+        [
+        '-di', str(resources_dir),
+        '-o', str(outdir),
+        ],
+        [
+            'Job done in',
+            'All jobs done in',
+        ]
+    )
+    assert len(list(outdir.iterdir())) == 2

tests/cli_tests/test_mbreorder.py

@@ -0,0 +1,53 @@
+from ocrd_modelfactory import page_from_file
+from ocrd_models.constants import NAMESPACES as NS
+
+from eynollah.cli import (
+    machine_based_reading_order as mbreorder_cli,
+)
+
+
+def test_run_eynollah_mbreorder_filename(
+    tmp_path,
+    resources_dir,
+    run_eynollah_ok_and_check_logs,
+):
+    infile = resources_dir / 'kant_aufklaerung_1784_0020.xml'
+    outfile = tmp_path.joinpath('kant_aufklaerung_1784_0020.xml')
+    run_eynollah_ok_and_check_logs(
+        mbreorder_cli,
+        [
+            '-i', str(infile),
+            '-o', str(outfile.parent),
+        ],
+        [
+            # FIXME: mbreorder has no logging!
+        ]
+    )
+    assert outfile.exists()
+    #in_tree = page_from_file(str(infile)).etree
+    #in_order = in_tree.xpath("//page:OrderedGroup//@regionRef", namespaces=NS)
+    out_tree = page_from_file(str(outfile)).etree
+    out_order = out_tree.xpath("//page:OrderedGroup//@regionRef", namespaces=NS)
+    #assert len(out_order) >= 2, "result is inaccurate"
+    #assert in_order != out_order
+    assert out_order == ['r_1_1', 'r_2_1', 'r_2_2', 'r_2_3']
+
+def test_run_eynollah_mbreorder_directory(
+    tmp_path,
+    resources_dir,
+    run_eynollah_ok_and_check_logs,
+):
+    outfile = tmp_path.joinpath('kant_aufklaerung_1784_0020.xml')
+    outdir = tmp_path
+    run_eynollah_ok_and_check_logs(
+        mbreorder_cli,
+        [
+            '-di', str(resources_dir),
+            '-o', str(outdir),
+        ],
+        [
+            # FIXME: mbreorder has no logging!
+        ]
+    )
+    assert len(list(outdir.iterdir())) == 2
+

tests/cli_tests/test_ocr.py

@@ -0,0 +1,67 @@
+import pytest
+from eynollah.cli import (
+    ocr as ocr_cli,
+)
+from ocrd_modelfactory import page_from_file
+from ocrd_models.constants import NAMESPACES as NS
+
+@pytest.mark.parametrize(
+    "options",
+    [
+        [], # defaults
+        ["-doit", #str(outrenderfile.parent)],
+         ],
+        ["-trocr"],
+    ], ids=str)
+def test_run_eynollah_ocr_filename(
+    tmp_path,
+    run_eynollah_ok_and_check_logs,
+    resources_dir,
+    options,
+):
+    infile = resources_dir / 'kant_aufklaerung_1784_0020.tif'
+    outfile = tmp_path.joinpath('kant_aufklaerung_1784_0020.xml')
+    outrenderfile = tmp_path / 'render' / 'kant_aufklaerung_1784_0020.png'
+    outrenderfile.parent.mkdir()
+    if "-doit" in options:
+        options.insert(options.index("-doit") + 1, str(outrenderfile.parent))
+    run_eynollah_ok_and_check_logs(
+        ocr_cli,
+        [
+            '-i', str(infile),
+            '-dx', str(infile.parent),
+            '-o', str(outfile.parent),
+        ] + options,
+        [
+            # FIXME: ocr has no logging!
+        ]
+    )
+    assert outfile.exists()
+    if "-doit" in options:
+        assert outrenderfile.exists()
+    #in_tree = page_from_file(str(infile)).etree
+    #in_order = in_tree.xpath("//page:OrderedGroup//@regionRef", namespaces=NS)
+    out_tree = page_from_file(str(outfile)).etree
+    out_texts = out_tree.xpath("//page:TextLine/page:TextEquiv[last()]/page:Unicode/text()", namespaces=NS)
+    assert len(out_texts) >= 2, ("result is inaccurate", out_texts)
+    assert sum(map(len, out_texts)) > 100, ("result is inaccurate", out_texts)
+
+def test_run_eynollah_ocr_directory(
+    tmp_path,
+    run_eynollah_ok_and_check_logs,
+    resources_dir,
+):
+    outdir = tmp_path
+    run_eynollah_ok_and_check_logs(
+        ocr_cli,
+        [
+            '-di', str(resources_dir),
+            '-dx', str(resources_dir),
+            '-o', str(outdir),
+        ],
+        [
+            # FIXME: ocr has no logging!
+        ]
+    )
+    assert len(list(outdir.iterdir())) == 2
+

tests/cli_tests/test_run.py

@@ -0,0 +1,10 @@
+import pytest
+from PIL import Image
+from eynollah.cli import (
+    layout as layout_cli,
+    binarization as binarization_cli,
+    enhancement as enhancement_cli,
+)
+from ocrd_modelfactory import page_from_file
+from ocrd_models.constants import NAMESPACES as NS
+

tests/conftest.py

@@ -0,0 +1,25 @@
+from glob import glob
+import os
+import pytest
+from pathlib import Path
+
+
+@pytest.fixture()
+def tests_dir():
+    return Path(__file__).parent.resolve()
+
+@pytest.fixture()
+def model_dir(tests_dir):
+    return os.environ.get('EYNOLLAH_MODELS_DIR', str(tests_dir.joinpath('..').resolve()))
+
+@pytest.fixture()
+def resources_dir(tests_dir):
+    return tests_dir / 'resources'
+
+@pytest.fixture()
+def image_resources(resources_dir):
+    return [Path(x) for x in glob(str(resources_dir / '*.tif'))]
+
+@pytest.fixture()
+def eynollah_log_filter():
+    return lambda logrec: logrec.name.startswith('eynollah')

tests/test_run.py

@@ -1,229 +0,0 @@
-from os import environ
-from pathlib import Path
-import pytest
-import logging
-from PIL import Image
-from eynollah.cli import (
-    layout as layout_cli,
-    binarization as binarization_cli,
-    enhancement as enhancement_cli,
-    machine_based_reading_order as mbreorder_cli,
-    ocr as ocr_cli,
-)
-from click.testing import CliRunner
-from ocrd_modelfactory import page_from_file
-from ocrd_models.constants import NAMESPACES as NS
-
-testdir = Path(__file__).parent.resolve()
-
-MODELS_DIR = environ.get('EYNOLLAH_MODELS_DIR', str(testdir.joinpath('..').resolve()))
-
-def only_eynollah(logrec):
-		return logrec.name.startswith('eynollah')
-
-@pytest.mark.parametrize(
-    "options",
-    [
-            [], # defaults
-            ["--no-patches"],
-    ], ids=str)
-def test_run_eynollah_binarization_filename(tmp_path, pytestconfig, caplog, options):
-    infile = testdir.joinpath('resources/kant_aufklaerung_1784_0020.tif')
-    outfile = tmp_path.joinpath('kant_aufklaerung_1784_0020.png')
-    args = [
-        '-m', MODELS_DIR,
-        '-i', str(infile),
-        '-o', str(outfile),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.INFO)
-    runner = CliRunner()
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(binarization_cli, args + options, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    assert any(True for logmsg in logmsgs if logmsg.startswith('Predicting'))
-    assert outfile.exists()
-    with Image.open(infile) as original_img:
-        original_size = original_img.size
-    with Image.open(outfile) as binarized_img:
-        binarized_size = binarized_img.size
-    assert original_size == binarized_size
-
-def test_run_eynollah_binarization_directory(tmp_path, pytestconfig, caplog):
-    indir = testdir.joinpath('resources')
-    outdir = tmp_path
-    args = [
-        '-m', MODELS_DIR,
-        '-di', str(indir),
-        '-o', str(outdir),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.INFO)
-    runner = CliRunner()
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(binarization_cli, args, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    assert len([logmsg for logmsg in logmsgs if logmsg.startswith('Predicting')]) == 2
-    assert len(list(outdir.iterdir())) == 2
-
-@pytest.mark.parametrize(
-    "options",
-    [
-            [], # defaults
-            ["-sos"],
-    ], ids=str)
-def test_run_eynollah_enhancement_filename(tmp_path, pytestconfig, caplog, options):
-    infile = testdir.joinpath('resources/kant_aufklaerung_1784_0020.tif')
-    outfile = tmp_path.joinpath('kant_aufklaerung_1784_0020.png')
-    args = [
-        '-m', MODELS_DIR,
-        '-i', str(infile),
-        '-o', str(outfile.parent),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.INFO)
-    runner = CliRunner()
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(enhancement_cli, args + options, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    assert any(True for logmsg in logmsgs if logmsg.startswith('Image was enhanced')), logmsgs
-    assert outfile.exists()
-    with Image.open(infile) as original_img:
-        original_size = original_img.size
-    with Image.open(outfile) as enhanced_img:
-        enhanced_size = enhanced_img.size
-    assert (original_size == enhanced_size) == ("-sos" in options)
-
-def test_run_eynollah_enhancement_directory(tmp_path, pytestconfig, caplog):
-    indir = testdir.joinpath('resources')
-    outdir = tmp_path
-    args = [
-        '-m', MODELS_DIR,
-        '-di', str(indir),
-        '-o', str(outdir),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.INFO)
-    runner = CliRunner()
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(enhancement_cli, args, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    assert len([logmsg for logmsg in logmsgs if logmsg.startswith('Image was enhanced')]) == 2
-    assert len(list(outdir.iterdir())) == 2
-
-def test_run_eynollah_mbreorder_filename(tmp_path, pytestconfig, caplog):
-    infile = testdir.joinpath('resources/kant_aufklaerung_1784_0020.xml')
-    outfile = tmp_path.joinpath('kant_aufklaerung_1784_0020.xml')
-    args = [
-        '-m', MODELS_DIR,
-        '-i', str(infile),
-        '-o', str(outfile.parent),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.INFO)
-    runner = CliRunner()
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(mbreorder_cli, args, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    # FIXME: mbreorder has no logging!
-    #assert any(True for logmsg in logmsgs if logmsg.startswith('???')), logmsgs
-    assert outfile.exists()
-    #in_tree = page_from_file(str(infile)).etree
-    #in_order = in_tree.xpath("//page:OrderedGroup//@regionRef", namespaces=NS)
-    out_tree = page_from_file(str(outfile)).etree
-    out_order = out_tree.xpath("//page:OrderedGroup//@regionRef", namespaces=NS)
-    #assert len(out_order) >= 2, "result is inaccurate"
-    #assert in_order != out_order
-    assert out_order == ['r_1_1', 'r_2_1', 'r_2_2', 'r_2_3']
-
-def test_run_eynollah_mbreorder_directory(tmp_path, pytestconfig, caplog):
-    indir = testdir.joinpath('resources')
-    outdir = tmp_path
-    args = [
-        '-m', MODELS_DIR,
-        '-di', str(indir),
-        '-o', str(outdir),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.INFO)
-    runner = CliRunner()
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(mbreorder_cli, args, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    # FIXME: mbreorder has no logging!
-    #assert len([logmsg for logmsg in logmsgs if logmsg.startswith('???')]) == 2
-    assert len(list(outdir.iterdir())) == 2
-
-@pytest.mark.parametrize(
-    "options",
-    [
-        [], # defaults
-        ["-doit", #str(outrenderfile.parent)],
-         ],
-        ["-trocr"],
-    ], ids=str)
-def test_run_eynollah_ocr_filename(tmp_path, pytestconfig, caplog, options):
-    infile = testdir.joinpath('resources/kant_aufklaerung_1784_0020.tif')
-    outfile = tmp_path.joinpath('kant_aufklaerung_1784_0020.xml')
-    outrenderfile = tmp_path.joinpath('render').joinpath('kant_aufklaerung_1784_0020.png')
-    outrenderfile.parent.mkdir()
-    args = [
-        '-m', MODELS_DIR,
-        '-i', str(infile),
-        '-dx', str(infile.parent),
-        '-o', str(outfile.parent),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.DEBUG)
-    runner = CliRunner()
-    if "-doit" in options:
-        options.insert(options.index("-doit") + 1, str(outrenderfile.parent))
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(ocr_cli, args + options, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    # FIXME: ocr has no logging!
-    #assert any(True for logmsg in logmsgs if logmsg.startswith('???')), logmsgs
-    assert outfile.exists()
-    if "-doit" in options:
-        assert outrenderfile.exists()
-    #in_tree = page_from_file(str(infile)).etree
-    #in_order = in_tree.xpath("//page:OrderedGroup//@regionRef", namespaces=NS)
-    out_tree = page_from_file(str(outfile)).etree
-    out_texts = out_tree.xpath("//page:TextLine/page:TextEquiv[last()]/page:Unicode/text()", namespaces=NS)
-    assert len(out_texts) >= 2, ("result is inaccurate", out_texts)
-    assert sum(map(len, out_texts)) > 100, ("result is inaccurate", out_texts)
-
-def test_run_eynollah_ocr_directory(tmp_path, pytestconfig, caplog):
-    indir = testdir.joinpath('resources')
-    outdir = tmp_path
-    args = [
-        '-m', MODELS_DIR,
-        '-di', str(indir),
-        '-dx', str(indir),
-        '-o', str(outdir),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.INFO)
-    runner = CliRunner()
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(ocr_cli, args, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    # FIXME: ocr has no logging!
-    #assert any(True for logmsg in logmsgs if logmsg.startswith('???')), logmsgs
-    assert len(list(outdir.iterdir())) == 2

tests/test_run_layout.py

@@ -1,330 +0,0 @@
-from os import environ
-from pathlib import Path
-import pytest
-import logging
-from PIL import Image
-from eynollah.cli import (
-    layout as layout_cli,
-    binarization as binarization_cli,
-    enhancement as enhancement_cli,
-    machine_based_reading_order as mbreorder_cli,
-    ocr as ocr_cli,
-)
-from click.testing import CliRunner
-from ocrd_modelfactory import page_from_file
-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_6_0').resolve()))
-
-def only_eynollah(logrec):
-		return logrec.name.startswith('eynollah')
-
-@pytest.mark.parametrize(
-    "options",
-    [
-            [], # defaults
-            #["--allow_scaling", "--curved-line"],
-            ["--allow_scaling", "--curved-line", "--full-layout"],
-            ["--allow_scaling", "--curved-line", "--full-layout", "--reading_order_machine_based"],
-            ["--allow_scaling", "--curved-line", "--full-layout", "--reading_order_machine_based",
-             "--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"],
-            #["--do_ocr", "--transformer_ocr", "--light_version", "--textline_light"],
-            ["--do_ocr", "--transformer_ocr", "--light_version", "--textline_light", "--full-layout"],
-            # --skip_layout_and_reading_order
-    ], ids=str)
-def test_run_eynollah_layout_filename(tmp_path, pytestconfig, caplog, options):
-    infile = testdir.joinpath('resources/kant_aufklaerung_1784_0020.tif')
-    outfile = tmp_path / 'kant_aufklaerung_1784_0020.xml'
-    args = [
-        '-m', MODELS_LAYOUT,
-        '-i', str(infile),
-        '-o', str(outfile.parent),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.INFO)
-    runner = CliRunner()
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(layout_cli, args + options, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    assert str(infile) in logmsgs
-    assert outfile.exists()
-    tree = page_from_file(str(outfile)).etree
-    regions = tree.xpath("//page:TextRegion", namespaces=NS)
-    assert len(regions) >= 2, "result is inaccurate"
-    regions = tree.xpath("//page:SeparatorRegion", namespaces=NS)
-    assert len(regions) >= 2, "result is inaccurate"
-    lines = tree.xpath("//page:TextLine", namespaces=NS)
-    assert len(lines) == 31, "result is inaccurate" # 29 paragraph lines, 1 page and 1 catch-word line
-
-@pytest.mark.parametrize(
-    "options",
-    [
-            ["--tables"],
-            ["--tables", "--full-layout"],
-            ["--tables", "--full-layout", "--textline_light", "--light_version"],
-    ], ids=str)
-def test_run_eynollah_layout_filename2(tmp_path, pytestconfig, caplog, options):
-    infile = testdir.joinpath('resources/euler_rechenkunst01_1738_0025.tif')
-    outfile = tmp_path / 'euler_rechenkunst01_1738_0025.xml'
-    args = [
-        '-m', MODELS_LAYOUT,
-        '-i', str(infile),
-        '-o', str(outfile.parent),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.INFO)
-    runner = CliRunner()
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(layout_cli, args + options, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    assert str(infile) in logmsgs
-    assert outfile.exists()
-    tree = page_from_file(str(outfile)).etree
-    regions = tree.xpath("//page:TextRegion", namespaces=NS)
-    assert len(regions) >= 2, "result is inaccurate"
-    regions = tree.xpath("//page:TableRegion", namespaces=NS)
-    # model/decoding is not very precise, so (depending on mode) we can get fractures/splits/FP
-    assert len(regions) >= 1, "result is inaccurate"
-    regions = tree.xpath("//page:SeparatorRegion", namespaces=NS)
-    assert len(regions) >= 2, "result is inaccurate"
-    lines = tree.xpath("//page:TextLine", namespaces=NS)
-    assert len(lines) >= 2, "result is inaccurate" # mostly table (if detected correctly), but 1 page and 1 catch-word line
-
-def test_run_eynollah_layout_directory(tmp_path, pytestconfig, caplog):
-    indir = testdir.joinpath('resources')
-    outdir = tmp_path
-    args = [
-        '-m', MODELS_LAYOUT,
-        '-di', str(indir),
-        '-o', str(outdir),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.INFO)
-    runner = CliRunner()
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(layout_cli, args, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    assert len([logmsg for logmsg in logmsgs if logmsg.startswith('Job done in')]) == 2
-    assert any(logmsg for logmsg in logmsgs if logmsg.startswith('All jobs done in'))
-    assert len(list(outdir.iterdir())) == 2
-
-@pytest.mark.parametrize(
-    "options",
-    [
-            [], # defaults
-            ["--no-patches"],
-    ], ids=str)
-def test_run_eynollah_binarization_filename(tmp_path, pytestconfig, caplog, options):
-    infile = testdir.joinpath('resources/kant_aufklaerung_1784_0020.tif')
-    outfile = tmp_path.joinpath('kant_aufklaerung_1784_0020.png')
-    args = [
-        '-m', MODELS_BIN,
-        '-i', str(infile),
-        '-o', str(outfile),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.INFO)
-    runner = CliRunner()
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(binarization_cli, args + options, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    assert any(True for logmsg in logmsgs if logmsg.startswith('Predicting'))
-    assert outfile.exists()
-    with Image.open(infile) as original_img:
-        original_size = original_img.size
-    with Image.open(outfile) as binarized_img:
-        binarized_size = binarized_img.size
-    assert original_size == binarized_size
-
-def test_run_eynollah_binarization_directory(tmp_path, pytestconfig, caplog):
-    indir = testdir.joinpath('resources')
-    outdir = tmp_path
-    args = [
-        '-m', MODELS_BIN,
-        '-di', str(indir),
-        '-o', str(outdir),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.INFO)
-    runner = CliRunner()
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(binarization_cli, args, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    assert len([logmsg for logmsg in logmsgs if logmsg.startswith('Predicting')]) == 2
-    assert len(list(outdir.iterdir())) == 2
-
-@pytest.mark.parametrize(
-    "options",
-    [
-            [], # defaults
-            ["-sos"],
-    ], ids=str)
-def test_run_eynollah_enhancement_filename(tmp_path, pytestconfig, caplog, options):
-    infile = testdir.joinpath('resources/kant_aufklaerung_1784_0020.tif')
-    outfile = tmp_path.joinpath('kant_aufklaerung_1784_0020.png')
-    args = [
-        '-m', MODELS_LAYOUT,
-        '-i', str(infile),
-        '-o', str(outfile.parent),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.INFO)
-    runner = CliRunner()
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(enhancement_cli, args + options, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    assert any(True for logmsg in logmsgs if logmsg.startswith('Image was enhanced')), logmsgs
-    assert outfile.exists()
-    with Image.open(infile) as original_img:
-        original_size = original_img.size
-    with Image.open(outfile) as enhanced_img:
-        enhanced_size = enhanced_img.size
-    assert (original_size == enhanced_size) == ("-sos" in options)
-
-def test_run_eynollah_enhancement_directory(tmp_path, pytestconfig, caplog):
-    indir = testdir.joinpath('resources')
-    outdir = tmp_path
-    args = [
-        '-m', MODELS_LAYOUT,
-        '-di', str(indir),
-        '-o', str(outdir),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.INFO)
-    runner = CliRunner()
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(enhancement_cli, args, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    assert len([logmsg for logmsg in logmsgs if logmsg.startswith('Image was enhanced')]) == 2
-    assert len(list(outdir.iterdir())) == 2
-
-def test_run_eynollah_mbreorder_filename(tmp_path, pytestconfig, caplog):
-    infile = testdir.joinpath('resources/kant_aufklaerung_1784_0020.xml')
-    outfile = tmp_path.joinpath('kant_aufklaerung_1784_0020.xml')
-    args = [
-        '-m', MODELS_LAYOUT,
-        '-i', str(infile),
-        '-o', str(outfile.parent),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.INFO)
-    runner = CliRunner()
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(mbreorder_cli, args, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    # FIXME: mbreorder has no logging!
-    #assert any(True for logmsg in logmsgs if logmsg.startswith('???')), logmsgs
-    assert outfile.exists()
-    #in_tree = page_from_file(str(infile)).etree
-    #in_order = in_tree.xpath("//page:OrderedGroup//@regionRef", namespaces=NS)
-    out_tree = page_from_file(str(outfile)).etree
-    out_order = out_tree.xpath("//page:OrderedGroup//@regionRef", namespaces=NS)
-    #assert len(out_order) >= 2, "result is inaccurate"
-    #assert in_order != out_order
-    assert out_order == ['r_1_1', 'r_2_1', 'r_2_2', 'r_2_3']
-
-def test_run_eynollah_mbreorder_directory(tmp_path, pytestconfig, caplog):
-    indir = testdir.joinpath('resources')
-    outdir = tmp_path
-    args = [
-        '-m', MODELS_LAYOUT,
-        '-di', str(indir),
-        '-o', str(outdir),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.INFO)
-    runner = CliRunner()
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(mbreorder_cli, args, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    # FIXME: mbreorder has no logging!
-    #assert len([logmsg for logmsg in logmsgs if logmsg.startswith('???')]) == 2
-    assert len(list(outdir.iterdir())) == 2
-
-@pytest.mark.parametrize(
-    "options",
-    [
-        [], # defaults
-        ["-doit", #str(outrenderfile.parent)],
-         ],
-        ["-trocr"],
-    ], ids=str)
-def test_run_eynollah_ocr_filename(tmp_path, pytestconfig, caplog, options):
-    infile = testdir.joinpath('resources/kant_aufklaerung_1784_0020.tif')
-    outfile = tmp_path.joinpath('kant_aufklaerung_1784_0020.xml')
-    outrenderfile = tmp_path.joinpath('render').joinpath('kant_aufklaerung_1784_0020.png')
-    outrenderfile.parent.mkdir()
-    args = [
-        '-m', MODELS_OCR,
-        '-i', str(infile),
-        '-dx', str(infile.parent),
-        '-o', str(outfile.parent),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.DEBUG)
-    runner = CliRunner()
-    if "-doit" in options:
-        options.insert(options.index("-doit") + 1, str(outrenderfile.parent))
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(ocr_cli, args + options, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    # FIXME: ocr has no logging!
-    #assert any(True for logmsg in logmsgs if logmsg.startswith('???')), logmsgs
-    assert outfile.exists()
-    if "-doit" in options:
-        assert outrenderfile.exists()
-    #in_tree = page_from_file(str(infile)).etree
-    #in_order = in_tree.xpath("//page:OrderedGroup//@regionRef", namespaces=NS)
-    out_tree = page_from_file(str(outfile)).etree
-    out_texts = out_tree.xpath("//page:TextLine/page:TextEquiv[last()]/page:Unicode/text()", namespaces=NS)
-    assert len(out_texts) >= 2, ("result is inaccurate", out_texts)
-    assert sum(map(len, out_texts)) > 100, ("result is inaccurate", out_texts)
-
-def test_run_eynollah_ocr_directory(tmp_path, pytestconfig, caplog):
-    indir = testdir.joinpath('resources')
-    outdir = tmp_path
-    args = [
-        '-m', MODELS_OCR,
-        '-di', str(indir),
-        '-dx', str(indir),
-        '-o', str(outdir),
-    ]
-    if pytestconfig.getoption('verbose') > 0:
-        args.extend(['-l', 'DEBUG'])
-    caplog.set_level(logging.INFO)
-    runner = CliRunner()
-    with caplog.filtering(only_eynollah):
-        result = runner.invoke(ocr_cli, args, catch_exceptions=False)
-    assert result.exit_code == 0, result.stdout
-    logmsgs = [logrec.message for logrec in caplog.records]
-    # FIXME: ocr has no logging!
-    #assert any(True for logmsg in logmsgs if logmsg.startswith('???')), logmsgs
-    assert len(list(outdir.iterdir())) == 2