pep 8 code style

.gitignore

@@ -1,6 +1,5 @@
 *.egg-info
 __pycache__
-sbb_newspapers_org_image/pylint.log
 models_eynollah*
 output.html
 /build

src/eynollah/cli.py

@@ -1,7 +1,7 @@
-import sys
 import click
+import sys
 from ocrd_utils import initLogging, setOverrideLogLevel
-from src.eynollah.eynollah import Eynollah
+from .eynollah import Eynollah
 
 
 @click.command()

src/eynollah/eynollah.py

@@ -1,40 +1,40 @@
 # pylint: disable=no-member,invalid-name,line-too-long,missing-function-docstring,missing-class-docstring,too-many-branches
 # pylint: disable=too-many-locals,wrong-import-position,too-many-lines,too-many-statements,chained-comparison,fixme,broad-except,c-extension-no-member
-# pylint: disable=too-many-public-methods,too-many-arguments,too-many-instance-attributes,too-many-public-methods,
+# pylint: disable=too-many-public-methods,too-many-arguments,too-many-instance-attributes,too-many-public-methods
 # pylint: disable=consider-using-enumerate
 """
 document layout analysis (segmentation) with output in PAGE-XML
 """
-
 import math
 import os
 import sys
 import time
 import warnings
-from pathlib import Path
 from multiprocessing import Process, Queue, cpu_count
-import gc
+from pathlib import Path
-from ocrd_utils import getLogger
 import cv2
 import numpy as np
-
-os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"
-stderr = sys.stderr
-sys.stderr = open(os.devnull, "w")
 import tensorflow as tf
-from tensorflow.python.keras import backend as K
+from ocrd_utils import getLogger
-from tensorflow.keras.models import load_model
-
-sys.stderr = stderr
-tf.get_logger().setLevel("ERROR")
-warnings.filterwarnings("ignore")
-from scipy.signal import find_peaks
-import matplotlib.pyplot as plt
 from scipy.ndimage import gaussian_filter1d
-# use tf1 compatibility for keras backend
+from scipy.signal import find_peaks
-from tensorflow.compat.v1.keras.backend import set_session
+from tensorflow.python.keras import backend as K
 from tensorflow.keras import layers
-
+from tensorflow.keras.models import load_model
+from .plot import EynollahPlotter
+from .utils import (
+    boosting_headers_by_longshot_region_segmentation,
+    crop_image_inside_box,
+    find_num_col,
+    otsu_copy_binary,
+    put_drop_out_from_only_drop_model,
+    putt_bb_of_drop_capitals_of_model_in_patches_in_layout,
+    check_any_text_region_in_model_one_is_main_or_header,
+    check_any_text_region_in_model_one_is_main_or_header_light,
+    small_textlines_to_parent_adherence2,
+    order_of_regions,
+    find_number_of_columns_in_document,
+    return_boxes_of_images_by_order_of_reading_new)
 from .utils.contour import (
     filter_contours_area_of_image,
     filter_contours_area_of_image_tables,
@@ -50,6 +50,12 @@ from .utils.contour import (
     return_contours_of_interested_textline,
     return_parent_contours,
 )
+from .utils.drop_capitals import (
+    adhere_drop_capital_region_into_corresponding_textline,
+    filter_small_drop_capitals_from_no_patch_layout)
+from .utils.marginals import get_marginals
+from .utils.pil_cv2 import check_dpi, pil2cv
+from .utils.resize import resize_image
 from .utils.rotate import (
     rotate_image,
     rotation_not_90_func,
@@ -58,29 +64,16 @@ from .utils.separate_lines import (
     textline_contours_postprocessing,
     separate_lines_new2,
     return_deskew_slop)
-from .utils.drop_capitals import (
-    adhere_drop_capital_region_into_corresponding_textline,
-    filter_small_drop_capitals_from_no_patch_layout)
-from .utils.marginals import get_marginals
-from .utils.resize import resize_image
-from .utils import (
-    boosting_headers_by_longshot_region_segmentation,
-    crop_image_inside_box,
-    find_num_col,
-    otsu_copy_binary,
-    put_drop_out_from_only_drop_model,
-    putt_bb_of_drop_capitals_of_model_in_patches_in_layout,
-    check_any_text_region_in_model_one_is_main_or_header,
-    check_any_text_region_in_model_one_is_main_or_header_light,
-    small_textlines_to_parent_adherence2,
-    order_of_regions,
-    find_number_of_columns_in_document,
-    return_boxes_of_images_by_order_of_reading_new)
-from .utils.pil_cv2 import check_dpi, pil2cv
 from .utils.xml import order_and_id_of_texts
-from .plot import EynollahPlotter
 from .writer import EynollahXmlWriter
 
+os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"
+tf.get_logger().setLevel("ERROR")
+warnings.filterwarnings("ignore")
+stderr = sys.stderr
+sys.stderr = open(os.devnull, "w")
+sys.stderr = stderr
+
 SLOPE_THRESHOLD = 0.13
 RATIO_OF_TWO_MODEL_THRESHOLD = 95.50  # 98.45:
 DPI_THRESHOLD = 298
@@ -244,7 +237,7 @@ class Eynollah:
             config = tf.compat.v1.ConfigProto()
             config.gpu_options.allow_growth = True
             session = tf.compat.v1.Session(config=config)
-            set_session(session)
+            K.set_session(session)
 
             self.model_page = self.our_load_model(self.model_page_dir)
             self.model_classifier = self.our_load_model(self.model_dir_of_col_classifier)
@@ -260,7 +253,7 @@ class Eynollah:
             config = tf.compat.v1.ConfigProto()
             config.gpu_options.allow_growth = True
             session = tf.compat.v1.Session(config=config)
-            set_session(session)
+            K.set_session(session)
 
             self.model_page = self.our_load_model(self.model_page_dir)
             self.model_classifier = self.our_load_model(self.model_dir_of_col_classifier)
@@ -276,7 +269,7 @@ class Eynollah:
             config = tf.compat.v1.ConfigProto()
             config.gpu_options.allow_growth = True
             session = tf.compat.v1.Session(config=config)
-            set_session(session)
+            K.set_session(session)
 
             self.model_page = self.our_load_model(self.model_page_dir)
             self.model_classifier = self.our_load_model(self.model_dir_of_col_classifier)
@@ -2566,6 +2559,7 @@ class Eynollah:
 
                 image_revised_last[int(boxes[i][2]):int(boxes[i][3]), int(boxes[i][0]):int(boxes[i][1]), :] = image_box[:, :, :]
         else:
+            image_revised_last = np.zeros((image_regions_eraly_p.shape[0], image_regions_eraly_p.shape[1], 3))
             for i in range(len(boxes)):
                 image_box = img_comm[int(boxes[i][2]):int(boxes[i][3]), int(boxes[i][0]):int(boxes[i][1]), :]
                 image_revised_last[int(boxes[i][2]):int(boxes[i][3]), int(boxes[i][0]):int(boxes[i][1]), :] = image_box[:, :, :]
@@ -3345,11 +3339,9 @@ class Eynollah:
                     else:
                         pass
                 if self.light_version:
-                    txt_con_org = get_textregion_contours_in_org_image_light(contours_only_text_parent, self.image,
+                    txt_con_org = get_textregion_contours_in_org_image_light(contours_only_text_parent, self.image, slope_first)
-                                                                             slope_first)
                 else:
-                    txt_con_org = get_textregion_contours_in_org_image(contours_only_text_parent, self.image,
+                    txt_con_org = get_textregion_contours_in_org_image(contours_only_text_parent, self.image, slope_first)
-                                                                       slope_first)
                 boxes_text, _ = get_text_region_boxes_by_given_contours(contours_only_text_parent)
                 boxes_marginals, _ = get_text_region_boxes_by_given_contours(polygons_of_marginals)
 

src/eynollah/ocrd_cli.py

@@ -1,6 +1,6 @@
-from .processor import EynollahProcessor
 from click import command
 from ocrd.decorators import ocrd_cli_options, ocrd_cli_wrap_processor
+from .processor import EynollahProcessor
 
 
 @command()

src/eynollah/plot.py

@@ -1,10 +1,9 @@
-import matplotlib.pyplot as plt
+import cv2
 import matplotlib.patches as mpatches
+import matplotlib.pyplot as plt
 import numpy as np
 import os.path
-import cv2
 from scipy.ndimage import gaussian_filter1d
-
 from .utils import crop_image_inside_box
 from .utils.rotate import rotate_image_different
 from .utils.resize import resize_image

src/eynollah/processor.py

@@ -1,14 +1,7 @@
 from json import loads
-from pkg_resources import resource_string
-from tempfile import NamedTemporaryFile
-from pathlib import Path
 from os.path import join
-
-from PIL import Image
-
 from ocrd import Processor
-from ocrd_modelfactory import page_from_file, exif_from_filename
+from ocrd_modelfactory import page_from_file
-from ocrd_models import OcrdFile, OcrdExif
 from ocrd_models.ocrd_page import to_xml
 from ocrd_utils import (
     getLogger,
@@ -16,9 +9,8 @@ from ocrd_utils import (
     assert_file_grp_cardinality,
     make_file_id
 )
-
+from pkg_resources import resource_string
 from .eynollah import Eynollah
-from .utils.pil_cv2 import pil2cv
 
 OCRD_TOOL = loads(resource_string(__name__, 'ocrd-tool.json').decode('utf8'))
 

src/eynollah/utils/__init__.py

@@ -1,17 +1,18 @@
+import cv2
+import imutils
 import math
 import matplotlib.pyplot as plt
 import numpy as np
-from shapely import geometry
-import cv2
-import imutils
 from scipy.signal import find_peaks
 from scipy.ndimage import gaussian_filter1d
-
+from shapely import geometry
 from .is_nan import isNaN
-from .contour import (contours_in_same_horizon,
+from .contour import (
+    contours_in_same_horizon,
     find_new_features_of_contours,
     return_contours_of_image,
-                      return_parent_contours)
+    return_parent_contours
+)
 
 
 def return_x_start_end_mothers_childs_and_type_of_reading_order(x_min_hor_some, x_max_hor_some, cy_hor_some, peak_points, cy_hor_diff):
@@ -1646,8 +1647,7 @@ def find_number_of_columns_in_document(region_pre_p, num_col_classifier, tables,
         # regions_without_separators_tile=cv2.erode(regions_without_separators_tile,kernel,iterations = 3)
 
         try:
-            num_col, peaks_neg_fin = find_num_col(regions_without_separators_tile, num_col_classifier, tables,
+            num_col, peaks_neg_fin = find_num_col(regions_without_separators_tile, num_col_classifier, tables, multiplier=7.0)
-                                                  multiplier=7.0)
         except:
             num_col = 0
             peaks_neg_fin = []

src/eynollah/utils/contour.py

@@ -73,8 +73,8 @@ def filter_contours_area_of_image_tables(image, contours, hierarchy, max_area, m
         # print(np.prod(thresh.shape[:2]))
         # Check that polygon has area greater than minimal area
         # print(hierarchy[0][jv][3],hierarchy )
-        if area >= min_area * np.prod(image.shape[:2]) and area <= max_area * np.prod(
+        if area >= min_area * np.prod(image.shape[:2]) and area <= max_area * np.prod(image.shape[:2]):
-                image.shape[:2]):  # and hierarchy[0][jv][3]==-1 :
+            # and hierarchy[0][jv][3]==-1 :
             # print(c[0][0][1])
             found_polygons_early.append(np.array([[point] for point in polygon.exterior.coords], dtype=np.int32))
     return found_polygons_early

src/eynollah/utils/drop_capitals.py

@@ -1,5 +1,6 @@
-import numpy as np
 import cv2
+import numpy as np
+
 from .contour import (
     find_new_features_of_contours,
     return_contours_of_image,

src/eynollah/utils/marginals.py

@@ -1,8 +1,7 @@
-import numpy as np
 import cv2
+import numpy as np
 from scipy.signal import find_peaks
 from scipy.ndimage import gaussian_filter1d
-
 from .contour import find_new_features_of_contours, return_contours_of_interested_region
 from .resize import resize_image
 from .rotate import rotate_image

src/eynollah/utils/pil_cv2.py

@@ -1,9 +1,13 @@
-from PIL import Image
+from cv2 import (
+    COLOR_GRAY2BGR,
+    COLOR_RGB2BGR,
+    COLOR_BGR2RGB,
+    cvtColor,
+    imread
+)
 import numpy as np
+from PIL import Image
 from ocrd_models import OcrdExif
-from cv2 import COLOR_GRAY2BGR, COLOR_RGB2BGR, COLOR_BGR2RGB, cvtColor, imread
-
-# from sbb_binarization
 
 
 def cv2pil(img):

src/eynollah/utils/rotate.py

@@ -1,7 +1,6 @@
-import math
-
-import imutils
 import cv2
+import imutils
+import math
 
 
 def rotatedRectWithMaxArea(w, h, angle):

src/eynollah/utils/separate_lines.py

@@ -1,21 +1,18 @@
-import numpy as np
 import cv2
-from scipy.signal import find_peaks
+import numpy as np
 from scipy.ndimage import gaussian_filter1d
-import os
+from scipy.signal import find_peaks
-
+from . import (
-from .rotate import rotate_image
+    find_num_col_deskew,
+    isNaN,
+)
 from .contour import (
     return_parent_contours,
     filter_contours_area_of_image_tables,
     return_contours_of_image,
     filter_contours_area_of_image
 )
-from .is_nan import isNaN
+from .rotate import rotate_image
-from . import (
-    find_num_col_deskew,
-    isNaN,
-)
 
 
 def dedup_separate_lines(img_patch, contour_text_interest, thetha, axis):
@@ -477,7 +474,6 @@ def separate_lines(img_patch, contour_text_interest, thetha, x_help, y_help):
                                         [int(x_max), int(y_max)],
                                         [int(x_min), int(y_max)]]))
 
-
     elif len(peaks) == 2:
         dis_to_next = np.abs(peaks[1] - peaks[0])
         for jj in range(len(peaks)):

src/eynollah/utils/xml.py

@@ -1,9 +1,7 @@
 # pylint: disable=too-many-locals,wrong-import-position,too-many-lines,too-many-statements,chained-comparison,fixme,broad-except,c-extension-no-member
 # pylint: disable=invalid-name
-from .counter import EynollahIdCounter
 import numpy as np
 from datetime import datetime
-
 from ocrd_models.ocrd_page import (
     CoordsType,
     GlyphType,
@@ -26,8 +24,9 @@ from ocrd_models.ocrd_page import (
     UnorderedGroupIndexedType,
     UnorderedGroupType,
     WordType,
-
+    to_xml
-    to_xml)
+)
+from .counter import EynollahIdCounter
 
 
 def create_page_xml(imageFilename, height, width):

src/eynollah/writer.py

@@ -1,12 +1,8 @@
 # pylint: disable=too-many-locals,wrong-import-position,too-many-lines,too-many-statements,chained-comparison,fixme,broad-except,c-extension-no-member
 # pylint: disable=import-error
-from pathlib import Path
+import numpy as np
 import os.path
-
+from pathlib import Path
-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,
@@ -18,7 +14,9 @@ from ocrd_models.ocrd_page import (
     SeparatorRegionType,
     to_xml
 )
-import numpy as np
+from ocrd_utils import getLogger
+from .utils.xml import create_page_xml, xml_reading_order
+from .utils.counter import EynollahIdCounter
 
 
 class EynollahXmlWriter():

tests/base.py

@@ -1,12 +1,8 @@
 # pylint: disable=unused-import
-
-from os.path import dirname, realpath
-from os import chdir
 import sys
-import logging
+from os import chdir
-import io
+from os.path import dirname, realpath
-import collections
+from unittest import TestCase as VanillaTestCase, main as unittests_main
-from unittest import TestCase as VanillaTestCase, skip, main as unittests_main
 import pytest
 from ocrd_utils import disableLogging, initLogging
 

tests/test_dpi.py

@@ -1,7 +1,7 @@
 import cv2
 from pathlib import Path
-from src.eynollah.utils.pil_cv2 import check_dpi
 from tests.base import main
+from src.eynollah.utils.pil_cv2 import check_dpi
 
 
 def test_dpi():

tests/test_xml.py

@@ -1,6 +1,6 @@
 from pytest import main
-from src.eynollah.utils.xml import create_page_xml
 from ocrd_models.ocrd_page import to_xml
+from src.eynollah.utils.xml import create_page_xml
 
 PAGE_2019 = 'http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15'