WIP: reorganize OCR-D and start on ocrd-eynollah-ocr

pyproject.toml

@@ -41,8 +41,9 @@ classifiers = [
 [project.scripts]
 eynollah = "eynollah.cli:main"
 eynollah-training = "eynollah.training.cli:main"
-ocrd-eynollah-segment = "eynollah.ocrd_cli:main"
+ocrd-eynollah-segment = "eynollah.ocrd.ocrd_cli_layout:main"
-ocrd-sbb-binarize = "eynollah.ocrd_cli_binarization:main"
+ocrd-sbb-binarize = "eynollah.ocrd.ocrd_cli_binarize:main"
+ocrd-eynollah-ocr = "eynollah.ocrd.ocrd_cli_ocr:main"
 
 [project.urls]
 Homepage = "https://github.com/qurator-spk/eynollah"

src/eynollah/ocrd/ocrd_cli_binarize.py

@@ -0,0 +1,9 @@
+from click import command
+from ocrd.decorators import ocrd_cli_options, ocrd_cli_wrap_processor
+
+from .processor_binarize import SbbBinarizeProcessor
+
+@command()
+@ocrd_cli_options
+def main(*args, **kwargs):
+    return ocrd_cli_wrap_processor(SbbBinarizeProcessor, *args, **kwargs)

src/eynollah/ocrd/ocrd_cli_layout.py

@@ -1,11 +1,9 @@
-from .processor import EynollahProcessor
 from click import command
 from ocrd.decorators import ocrd_cli_options, ocrd_cli_wrap_processor
 
+from .processor_layout import EynollahProcessor
+
 @command()
 @ocrd_cli_options
 def main(*args, **kwargs):
     return ocrd_cli_wrap_processor(EynollahProcessor, *args, **kwargs)
-
-if __name__ == '__main__':
-    main()

src/eynollah/ocrd/processor_binarize.py

@@ -1,29 +1,15 @@
 from functools import cached_property
 from typing import Optional
 
-from PIL import Image
 from frozendict import frozendict
-import numpy as np
-import cv2
-from click import command
 
 from ocrd import Processor, OcrdPageResult, OcrdPageResultImage
 from ocrd_models.ocrd_page import OcrdPage, AlternativeImageType
-from ocrd.decorators import ocrd_cli_options, ocrd_cli_wrap_processor
 
 from eynollah.model_zoo.model_zoo import EynollahModelZoo
 
-from .sbb_binarize import SbbBinarizer
+from ..sbb_binarize import SbbBinarizer
-
+from ..utils.pil_cv2 import cv2pil, pil2cv
-
-def cv2pil(img):
-    return Image.fromarray(img.astype('uint8'))
-
-def pil2cv(img):
-    # from ocrd/workspace.py
-    color_conversion = cv2.COLOR_GRAY2BGR if img.mode in ('1', 'L') else  cv2.COLOR_RGB2BGR
-    pil_as_np_array = np.array(img).astype('uint8') if img.mode == '1' else np.array(img)
-    return cv2.cvtColor(pil_as_np_array, color_conversion)
 
 class SbbBinarizeProcessor(Processor):
     # already employs GPU (without singleton process atm)
@@ -103,12 +89,7 @@ class SbbBinarizeProcessor(Processor):
                 line_image_bin = cv2pil(self.binarizer.run(image=pil2cv(line_image), use_patches=True))
                 # update PAGE (reference the image file):
                 line_image_ref = AlternativeImageType(comments=line_xywh['features'] + ',binarized')
-                line.add_AlternativeImage(region_image_ref)
+                line.add_AlternativeImage(line_image_ref)
                 result.images.append(OcrdPageResultImage(line_image_bin, line.id + '.IMG-BIN', line_image_ref))
 
         return result
-
-@command()
-@ocrd_cli_options
-def main(*args, **kwargs):
-    return ocrd_cli_wrap_processor(SbbBinarizeProcessor, *args, **kwargs)

src/eynollah/ocrd/processor_layout.py

@@ -3,9 +3,9 @@ from typing import Optional
 from ocrd_models import OcrdPage
 from ocrd import OcrdPageResultImage, Processor, OcrdPageResult
 
-from eynollah.model_zoo.model_zoo import EynollahModelZoo
+from ..model_zoo.model_zoo import EynollahModelZoo
-
+from ..eynollah import Eynollah
-from .eynollah import Eynollah, EynollahXmlWriter
+from ..writer import EynollahXmlWriter
 
 class EynollahProcessor(Processor):
     # already employs background CPU multiprocessing per page

src/eynollah/ocrd/processor_ocr.py

@@ -0,0 +1,24 @@
+
+from functools import cached_property
+from frozendict import frozendict
+from ocrd import Processor
+
+from ..model_zoo.model_zoo import EynollahModelZoo
+
+
+class EynollahOcrProcessor(Processor):
+    # already employs GPU (without singleton process atm)
+    max_workers = 1
+
+    @cached_property
+    def executable(self):
+        return 'ocrd-eynollah-ocr'
+
+    def setup(self):
+        """
+        Set up the model prior to processing.
+        """
+        # resolve relative path via OCR-D ResourceManager
+        assert isinstance(self.parameter, frozendict)
+        model_zoo = EynollahModelZoo(basedir=self.parameter['model'])
+        raise NotImplementedError()