Refactor CLI for consistent logging and late imports

src/eynollah/cli.py

@@ -1,15 +1,34 @@
-import sys
+from dataclasses import dataclass
-import click
 import logging
-from ocrd_utils import initLogging, getLevelName, getLogger
+import sys
-from eynollah.eynollah import Eynollah, Eynollah_ocr
+from typing import Union
-from eynollah.sbb_binarize import SbbBinarizer
+
-from eynollah.image_enhancer import Enhancer
+import click
-from eynollah.mb_ro_on_layout import machine_based_reading_order_on_layout
+
+
+@dataclass
+class EynollahCliContext():
+    log_level : Union[str, None] = 'INFO'
 
 @click.group()
-def main():
+@click.option(
-    pass
+    "--log_level",
+    "-l",
+    type=click.Choice(['OFF', 'DEBUG', 'INFO', 'WARN', 'ERROR']),
+    help="Override log level globally to this",
+)
+@click.pass_context
+def main(ctx, log_level):
+    """
+    eynollah - Document Layout Analysis, Image Enhancement, OCR
+    """
+    ctx.obj = EynollahCliContext(log_level=log_level)
+    console_handler = logging.StreamHandler(sys.stdout)
+    console_handler.setLevel(logging.NOTSET)
+    formatter = logging.Formatter('%(asctime)s.%(msecs)03d %(levelname)s %(name)s - %(message)s', datefmt='%H:%M:%S')
+    console_handler.setFormatter(formatter)
+    logging.getLogger('eynollah').addHandler(console_handler)
+    logging.getLogger('eynollah').setLevel(ctx.obj.log_level or logging.INFO)
 
 @main.command()
 @click.option(
@@ -38,18 +57,13 @@ def main():
     type=click.Path(exists=True, file_okay=False),
     required=True,
 )
-@click.option(
+def machine_based_reading_order(input, dir_in, out, model):
-    "--log_level",
+    """
-    "-l",
+    Generate ReadingOrder with a ML model
-    type=click.Choice(['OFF', 'DEBUG', 'INFO', 'WARN', 'ERROR']),
+    """
-    help="Override log level globally to this",
+    from .mb_ro_on_layout import machine_based_reading_order_on_layout
-)
-
-def machine_based_reading_order(input, dir_in, out, model, log_level):
     assert bool(input) != bool(dir_in), "Either -i (single input) or -di (directory) must be provided, but not both."
     orderer = machine_based_reading_order_on_layout(model)
-    if log_level:
-        orderer.logger.setLevel(getLevelName(log_level))
 
     orderer.run(xml_filename=input,
                 dir_in=dir_in,
@@ -79,17 +93,13 @@ def machine_based_reading_order(input, dir_in, out, model, log_level):
     type=click.Path(file_okay=True, dir_okay=True),
     required=True,
 )
-@click.option(
+def binarization(patches, model_dir, input_image, dir_in, output):
-    "--log_level",
+    """
-    "-l",
+    Binarize images with a ML model
-    type=click.Choice(['OFF', 'DEBUG', 'INFO', 'WARN', 'ERROR']),
+    """
-    help="Override log level globally to this",
-)
-def binarization(patches, model_dir, input_image, dir_in, output, log_level):
     assert bool(input_image) != bool(dir_in), "Either -i (single input) or -di (directory) must be provided, but not both."
+    from .sbb_binarize import SbbBinarizer
     binarizer = SbbBinarizer(model_dir)
-    if log_level:
-        binarizer.log.setLevel(getLevelName(log_level))
     binarizer.run(image_path=input_image, use_patches=patches, output=output, dir_in=dir_in)
 
 
@@ -144,24 +154,18 @@ def binarization(patches, model_dir, input_image, dir_in, output, log_level):
     is_flag=True,
     help="if this parameter set to true, this tool will save the enhanced image in org scale.",
 )
-@click.option(
+def enhancement(image, out, overwrite, dir_in, model, num_col_upper, num_col_lower, save_org_scale):
-    "--log_level",
+    """
-    "-l",
+    Enhance image
-    type=click.Choice(['OFF', 'DEBUG', 'INFO', 'WARN', 'ERROR']),
+    """
-    help="Override log level globally to this",
-)
-
-def enhancement(image, out, overwrite, dir_in, model, num_col_upper, num_col_lower, save_org_scale,  log_level):
     assert bool(image) != bool(dir_in), "Either -i (single input) or -di (directory) must be provided, but not both."
-    initLogging()
+    from .image_enhancer import Enhancer
     enhancer = Enhancer(
         model,
         num_col_upper=num_col_upper,
         num_col_lower=num_col_lower,
         save_org_scale=save_org_scale,
     )
-    if log_level:
-        enhancer.logger.setLevel(getLevelName(log_level))
     enhancer.run(overwrite=overwrite,
                  dir_in=dir_in,
                  image_filename=image,
@@ -366,30 +370,10 @@ def enhancement(image, out, overwrite, dir_in, model, num_col_upper, num_col_low
     is_flag=True,
     help="if this parameter set to true, this tool will ignore layout detection and reading order. It means that textline detection will be done within printspace and contours of textline will be written in xml output file.",
 )
-# TODO move to top-level CLI context
+def layout(image, out, overwrite, dir_in, model, model_version, save_images, save_layout, save_deskewed, save_all, extract_only_images, save_page, enable_plotting, allow_enhancement, curved_line, textline_light, full_layout, tables, right2left, input_binary, allow_scaling, headers_off, light_version, reading_order_machine_based, do_ocr, transformer_ocr, batch_size_ocr, num_col_upper, num_col_lower, threshold_art_class_textline, threshold_art_class_layout, skip_layout_and_reading_order, ignore_page_extraction):
-@click.option(
+    """
-    "--log_level",
+    Detect Layout (with optional image enhancement and reading order detection)
-    "-l",
+    """
-    type=click.Choice(['OFF', 'DEBUG', 'INFO', 'WARN', 'ERROR']),
-    help="Override 'eynollah' log level globally to this",
-)
-# 
-@click.option(
-    "--setup-logging",
-    is_flag=True,
-    help="Setup a basic console logger",
-)
-
-def layout(image, out, overwrite, dir_in, model, model_version, save_images, save_layout, save_deskewed, save_all, extract_only_images, save_page, enable_plotting, allow_enhancement, curved_line, textline_light, full_layout, tables, right2left, input_binary, allow_scaling, headers_off, light_version, reading_order_machine_based, do_ocr, transformer_ocr, batch_size_ocr, num_col_upper, num_col_lower, threshold_art_class_textline, threshold_art_class_layout, skip_layout_and_reading_order, ignore_page_extraction, log_level, setup_logging):
-    if setup_logging:
-        console_handler = logging.StreamHandler(sys.stdout)
-        console_handler.setLevel(logging.INFO)
-        formatter = logging.Formatter('%(message)s')
-        console_handler.setFormatter(formatter)
-        getLogger('eynollah').addHandler(console_handler)
-        getLogger('eynollah').setLevel(logging.INFO)
-    else:
-        initLogging()
     assert enable_plotting or not save_layout, "Plotting with -sl also requires -ep"
     assert enable_plotting or not save_deskewed, "Plotting with -sd also requires -ep"
     assert enable_plotting or not save_all, "Plotting with -sa also requires -ep"
@@ -409,6 +393,7 @@ def layout(image, out, overwrite, dir_in, model, model_version, save_images, sav
     assert not extract_only_images or not right2left, "Image extraction -eoi can not be set alongside right2left -r2l"
     assert not extract_only_images or not headers_off, "Image extraction -eoi can not be set alongside headers_off -ho"
     assert bool(image) != bool(dir_in), "Either -i (single input) or -di (directory) must be provided, but not both."
+    from .eynollah import Eynollah
     eynollah = Eynollah(
         model,
         model_versions=model_version,
@@ -435,8 +420,6 @@ def layout(image, out, overwrite, dir_in, model, model_version, save_images, sav
         threshold_art_class_textline=threshold_art_class_textline,
         threshold_art_class_layout=threshold_art_class_layout,
     )
-    if log_level:
-        eynollah.logger.setLevel(getLevelName(log_level))
     eynollah.run(overwrite=overwrite,
                  image_filename=image,
                  dir_in=dir_in,
@@ -537,16 +520,11 @@ def layout(image, out, overwrite, dir_in, model, model_version, save_images, sav
     "-min_conf",
     help="minimum OCR confidence value. Text lines with a confidence value lower than this threshold will not be included in the output XML file.",
 )
-@click.option(
-    "--log_level",
-    "-l",
-    type=click.Choice(['OFF', 'DEBUG', 'INFO', 'WARN', 'ERROR']),
-    help="Override log level globally to this",
-)
 
-def ocr(image, dir_in, dir_in_bin, dir_xmls, out, dir_out_image_text, overwrite, model, model_name, tr_ocr, export_textline_images_and_text, do_not_mask_with_textline_contour, batch_size, dataset_abbrevation, min_conf_value_of_textline_text, log_level):
+def ocr(image, dir_in, dir_in_bin, dir_xmls, out, dir_out_image_text, overwrite, model, model_name, tr_ocr, export_textline_images_and_text, do_not_mask_with_textline_contour, batch_size, dataset_abbrevation, min_conf_value_of_textline_text):
-    initLogging()
+    """
-        
+    Recognize text with a CNN/RNN or transformer ML model.
+    """
     assert bool(model) != bool(model_name), "Either -m (model directory) or --model_name (specific model name) must be provided."
     assert not export_textline_images_and_text or not tr_ocr, "Exporting textline and text  -etit can not be set alongside transformer ocr -tr_ocr"
     assert not export_textline_images_and_text or not model, "Exporting textline and text  -etit can not be set alongside model -m"
@@ -554,6 +532,7 @@ def ocr(image, dir_in, dir_in_bin, dir_xmls, out, dir_out_image_text, overwrite,
     assert not export_textline_images_and_text or not dir_in_bin, "Exporting textline and text  -etit can not be set alongside directory of bin images -dib"
     assert not export_textline_images_and_text or not dir_out_image_text, "Exporting textline and text  -etit can not be set alongside directory of images with predicted text -doit"
     assert bool(image) != bool(dir_in), "Either -i (single image) or -di (directory) must be provided, but not both."
+    from .eynollah import Eynollah_ocr
     eynollah_ocr = Eynollah_ocr(
         dir_models=model,
         model_name=model_name,
@@ -562,10 +541,7 @@ def ocr(image, dir_in, dir_in_bin, dir_xmls, out, dir_out_image_text, overwrite,
         do_not_mask_with_textline_contour=do_not_mask_with_textline_contour,
         batch_size=batch_size,
         pref_of_dataset=dataset_abbrevation,
-        min_conf_value_of_textline_text=min_conf_value_of_textline_text,
+        min_conf_value_of_textline_text=min_conf_value_of_textline_text)
-    )
-    if log_level:
-        eynollah_ocr.logger.setLevel(getLevelName(log_level))
     eynollah_ocr.run(overwrite=overwrite,
                      dir_in=dir_in,
                      dir_in_bin=dir_in_bin,

src/eynollah/eynollah.py

@@ -7,6 +7,7 @@ document layout analysis (segmentation) with output in PAGE-XML
 """
 
 # cannot use importlib.resources until we move to 3.9+ forimportlib.resources.files
+import logging
 import sys
 if sys.version_info < (3, 10):
     import importlib_resources
@@ -19,8 +20,7 @@ import math
 import os
 import sys
 import time
-from typing import Dict, List, Optional, Tuple
+from typing import List, Optional, Tuple
-import atexit
 import warnings
 from functools import partial
 from pathlib import Path
@@ -39,7 +39,7 @@ from scipy.ndimage import gaussian_filter1d
 from numba import cuda
 from skimage.morphology import skeletonize
 from ocrd import OcrdPage
-from ocrd_utils import getLogger, tf_disable_interactive_logs
+from ocrd_utils import tf_disable_interactive_logs
 import statistics
 
 try:
@@ -60,8 +60,6 @@ tf_disable_interactive_logs()
 import tensorflow as tf
 from tensorflow.python.keras import backend as K
 from tensorflow.keras.models import load_model
-tf.get_logger().setLevel("ERROR")
-warnings.filterwarnings("ignore")
 # use tf1 compatibility for keras backend
 from tensorflow.compat.v1.keras.backend import set_session
 from tensorflow.keras import layers
@@ -230,8 +228,9 @@ class Eynollah:
         threshold_art_class_layout: Optional[float] = None,
         threshold_art_class_textline: Optional[float] = None,
         skip_layout_and_reading_order : bool = False,
+        logger : Optional[logging.Logger] = None,
     ):
-        self.logger = getLogger('eynollah')
+        self.logger = logger or logging.getLogger('eynollah')
         self.plotter = None
 
         if skip_layout_and_reading_order:
@@ -4888,14 +4887,13 @@ class Eynollah_ocr:
         do_not_mask_with_textline_contour=False,
         pref_of_dataset=None,
         min_conf_value_of_textline_text : Optional[float]=None,
-        logger=None,
     ):
         self.model_name = model_name
         self.tr_ocr = tr_ocr
         self.export_textline_images_and_text = export_textline_images_and_text
         self.do_not_mask_with_textline_contour = do_not_mask_with_textline_contour
         self.pref_of_dataset = pref_of_dataset
-        self.logger = logger if logger else getLogger('eynollah')
+        self.logger = logging.getLogger('eynollah')
         
         if not export_textline_images_and_text:
             if min_conf_value_of_textline_text:

src/eynollah/image_enhancer.py

@@ -2,7 +2,7 @@
 Image enhancer. The output can be written as same scale of input or in new predicted scale.
 """
 
-from logging import Logger
+import logging
 import os
 import time
 from typing import Optional
@@ -11,7 +11,6 @@ import gc
 
 import cv2
 import numpy as np
-from ocrd_utils import getLogger, tf_disable_interactive_logs
 import tensorflow as tf
 from skimage.morphology import skeletonize
 from tensorflow.keras.models import load_model
@@ -35,7 +34,6 @@ class Enhancer:
         num_col_upper : Optional[int] = None,
         num_col_lower : Optional[int] = None,
         save_org_scale : bool = False,
-        logger : Optional[Logger] = None,
     ):
         self.input_binary = False
         self.light_version = False
@@ -49,7 +47,7 @@ class Enhancer:
         else:
             self.num_col_lower = num_col_lower
             
-        self.logger = logger if logger else getLogger('enhancement')
+        self.logger = logging.getLogger('eynollah.enhancement')
         self.dir_models = dir_models
         self.model_dir_of_binarization = dir_models + "/eynollah-binarization_20210425"
         self.model_dir_of_enhancement = dir_models + "/eynollah-enhancement_20210425"

src/eynollah/mb_ro_on_layout.py

@@ -1,8 +1,8 @@
 """
-Image enhancer. The output can be written as same scale of input or in new predicted scale.
+Machine learning based reading order detection
 """
 
-from logging import Logger
+import logging 
 import os
 import time
 from typing import Optional
@@ -11,7 +11,6 @@ import xml.etree.ElementTree as ET
 
 import cv2
 import numpy as np
-from ocrd_utils import getLogger
 import statistics
 import tensorflow as tf
 from tensorflow.keras.models import load_model
@@ -33,9 +32,9 @@ class machine_based_reading_order_on_layout:
     def __init__(
         self,
         dir_models : str,
-        logger : Optional[Logger] = None,
+        logger : Optional[logging.Logger] = None,
     ):
-        self.logger = logger if logger else getLogger('mbreorder')
+        self.logger = logger or logging.getLogger('eynollah.mbreorder')
         self.dir_models = dir_models
         self.model_reading_order_dir = dir_models + "/model_eynollah_reading_order_20250824"
         

src/eynollah/ocrd_cli_binarization.py

@@ -34,6 +34,7 @@ class SbbBinarizeProcessor(Processor):
         Set up the model prior to processing.
         """
         # resolve relative path via OCR-D ResourceManager
+        assert isinstance(self.parameter, dict)
         model_path = self.resolve_resource(self.parameter['model'])
         self.binarizer = SbbBinarizer(model_dir=model_path, logger=self.logger)
 

src/eynollah/processor.py

@@ -32,8 +32,8 @@ class EynollahProcessor(Processor):
             allow_scaling=self.parameter['allow_scaling'],
             headers_off=self.parameter['headers_off'],
             tables=self.parameter['tables'],
+            logger=self.logger
         )
-        self.eynollah.logger = self.logger
         self.eynollah.plotter = None
 
     def shutdown(self):

src/eynollah/sbb_binarize.py

@@ -2,19 +2,16 @@
 Tool to load model and binarize a given image.
 """
 
-import sys
 from glob import glob
 import os
 import logging
+from typing import Optional
 
 import numpy as np
-from PIL import Image
 import cv2
-from ocrd_utils import tf_disable_interactive_logs
-tf_disable_interactive_logs()
 import tensorflow as tf
-from tensorflow.keras.models import load_model
+from keras.models import load_model
-from tensorflow.python.keras import backend as tensorflow_backend
+from keras import backend as tensorflow_backend
 
 from .utils import is_image_filename
 
@@ -23,9 +20,13 @@ def resize_image(img_in, input_height, input_width):
 
 class SbbBinarizer:
 
-    def __init__(self, model_dir, logger=None):
+    def __init__(
+        self,
+        model_dir,
+        logger: Optional[logging.Logger] = None,
+    ):
         self.model_dir = model_dir
-        self.log = logger if logger else logging.getLogger('SbbBinarizer')
+        self.logger = logger or logging.getLogger('eynollah.binarize')
 
         self.start_new_session()
 
@@ -325,7 +326,7 @@ class SbbBinarizer:
                 image = cv2.imread(image_path)
             img_last = 0
             for n, (model, model_file) in enumerate(zip(self.models, self.model_files)):
-                self.log.info('Predicting with model %s [%s/%s]' % (model_file, n + 1, len(self.model_files)))
+                self.logger.debug('Binarizing with model %s [%s/%s]' % (model_file, n + 1, len(self.model_files)))
 
                 res = self.predict(model, image, use_patches)
 
@@ -345,17 +346,19 @@ class SbbBinarizer:
             img_last[:, :][img_last[:, :] > 0] = 255
             img_last = (img_last[:, :] == 0) * 255
             if output:
+                self.logger.info('Writing binarized image to %s', output)
                 cv2.imwrite(output, img_last)
             return img_last
         else:
             ls_imgs = list(filter(is_image_filename, os.listdir(dir_in)))
-            for image_name in ls_imgs:
+            self.logger.info("Found %d image files to binarize in %s", len(ls_imgs), dir_in)
+            for i, image_name in enumerate(ls_imgs):
                 image_stem = image_name.split('.')[0]
-                print(image_name,'image_name')
+                self.logger.info('Binarizing [%3d/%d] %s', i + 1, len(ls_imgs), image_name)
                 image = cv2.imread(os.path.join(dir_in,image_name) )
                 img_last = 0
                 for n, (model, model_file) in enumerate(zip(self.models, self.model_files)):
-                    self.log.info('Predicting with model %s [%s/%s]' % (model_file, n + 1, len(self.model_files)))
+                    self.logger.debug('Predicting with model %s [%s/%s]' % (model_file, n + 1, len(self.model_files)))
 
                     res = self.predict(model, image, use_patches)
 
@@ -375,4 +378,6 @@ class SbbBinarizer:
                 img_last[:, :][img_last[:, :] > 0] = 255
                 img_last = (img_last[:, :] == 0) * 255
                 
-                cv2.imwrite(os.path.join(output, image_stem + '.png'), img_last)
+                output_filename = os.path.join(output, image_stem + '.png')
+                self.logger.info('Writing binarized image to %s', output_filename)
+                cv2.imwrite(output_filename, img_last)

src/eynollah/utils/__init__.py

@@ -19,7 +19,6 @@ from .contour import (contours_in_same_horizon,
                       find_new_features_of_contours,
                       return_contours_of_image,
                       return_parent_contours)
-
 def pairwise(iterable):
     # pairwise('ABCDEFG') → AB BC CD DE EF FG
 

src/eynollah/writer.py

@@ -2,11 +2,11 @@
 # pylint: disable=import-error
 from pathlib import Path
 import os.path
+import logging
 import xml.etree.ElementTree as ET
 from .utils.xml import create_page_xml, xml_reading_order
 from .utils.counter import EynollahIdCounter
 
-from ocrd_utils import getLogger
 from ocrd_models.ocrd_page import (
         BorderType,
         CoordsType,
@@ -24,7 +24,7 @@ import numpy as np
 class EynollahXmlWriter:
 
     def __init__(self, *, dir_out, image_filename, curved_line,textline_light, pcgts=None):
-        self.logger = getLogger('eynollah.writer')
+        self.logger = logging.getLogger('eynollah.writer')
         self.counter = EynollahIdCounter()
         self.dir_out = dir_out
         self.image_filename = image_filename