🎨 Sort imports (auto-fixed by ruff)

src/dinglehopper/__init__.py

@@ -1,5 +1,5 @@
-from .ocr_files import *
-from .extracted_text import *
+from .align import *
 from .character_error_rate import *
+from .extracted_text import *
+from .ocr_files import *
 from .word_error_rate import *
-from .align import *

src/dinglehopper/align.py

@@ -1,6 +1,7 @@
-from .edit_distance import *
 from rapidfuzz.distance import Levenshtein
 
+from .edit_distance import *
+
 
 def align(t1, t2):
     """Align text."""

src/dinglehopper/cli.py

@@ -4,15 +4,15 @@ from collections import Counter
 import click
 from jinja2 import Environment, FileSystemLoader
 from markupsafe import escape
-from uniseg.graphemecluster import grapheme_clusters
 from ocrd_utils import initLogging
+from uniseg.graphemecluster import grapheme_clusters
 
-from dinglehopper.character_error_rate import character_error_rate_n
-from dinglehopper.word_error_rate import word_error_rate_n, words_normalized
 from dinglehopper.align import seq_align
+from dinglehopper.character_error_rate import character_error_rate_n
+from dinglehopper.config import Config
 from dinglehopper.extracted_text import ExtractedText
 from dinglehopper.ocr_files import extract
-from dinglehopper.config import Config
+from dinglehopper.word_error_rate import word_error_rate_n, words_normalized
 
 
 def gen_diff_report(gt_in, ocr_in, css_prefix, joiner, none, differences=False):

src/dinglehopper/cli_extract.py

@@ -1,9 +1,7 @@
-import os
 
 import click
 from ocrd_utils import initLogging
 
-from .extracted_text import ExtractedText
 from .ocr_files import extract
 
 

src/dinglehopper/cli_line_dirs.py

@@ -1,20 +1,14 @@
-import os
-import sys
 import itertools
+import os
 
 import click
 from jinja2 import Environment, FileSystemLoader
-from markupsafe import escape
-from uniseg.graphemecluster import grapheme_clusters
 from ocrd_utils import initLogging
 
 from .character_error_rate import character_error_rate_n
-from .word_error_rate import word_error_rate_n, words_normalized
-from .align import seq_align
-from .extracted_text import ExtractedText
-from .ocr_files import plain_extract
-from .config import Config
 from .cli import gen_diff_report, json_float
+from .ocr_files import plain_extract
+from .word_error_rate import word_error_rate_n, words_normalized
 
 
 def all_equal(iterable):

src/dinglehopper/cli_summarize.py

@@ -2,8 +2,8 @@ import json
 import os
 
 import click
-from ocrd_utils import initLogging
 from jinja2 import Environment, FileSystemLoader
+from ocrd_utils import initLogging
 
 from dinglehopper.cli import json_float
 

src/dinglehopper/edit_distance.py

@@ -1,17 +1,12 @@
 from __future__ import division, print_function
 
 import unicodedata
-from functools import partial, lru_cache
-from typing import Sequence, Tuple
 
-import numpy as np
 from multimethod import multimethod
-from uniseg.graphemecluster import grapheme_clusters
-from tqdm import tqdm
 from rapidfuzz.distance import Levenshtein
+from uniseg.graphemecluster import grapheme_clusters
 
 from .extracted_text import ExtractedText
-from .config import Config
 
 
 @multimethod

src/dinglehopper/ocr_files.py

@@ -3,11 +3,10 @@ from __future__ import division, print_function
 import os
 import sys
 from typing import Iterator
-from warnings import warn
 
+import chardet
 from lxml import etree as ET
 from lxml.etree import XMLSyntaxError
-import chardet
 
 from .extracted_text import ExtractedText, normalize_sbb
 

src/dinglehopper/ocrd_cli.py

@@ -4,7 +4,7 @@ import os
 import click
 from ocrd import Processor
 from ocrd.decorators import ocrd_cli_options, ocrd_cli_wrap_processor
-from ocrd_utils import getLogger, make_file_id, assert_file_grp_cardinality
+from ocrd_utils import assert_file_grp_cardinality, getLogger, make_file_id
 from pkg_resources import resource_string
 
 from .cli import process as cli_process

src/dinglehopper/tests/extracted_text_test.py

@@ -6,7 +6,7 @@ import pytest
 from lxml import etree as ET
 from uniseg.graphemecluster import grapheme_clusters
 
-from .. import seq_align, ExtractedText
+from .. import ExtractedText, seq_align
 
 
 def test_text():

src/dinglehopper/tests/test_align.py

@@ -1,6 +1,7 @@
 import pytest
+
+from .. import align, distance, seq_align
 from .util import unzip
-from .. import align, seq_align, distance
 
 
 def test_left_empty():

src/dinglehopper/tests/test_integ_bigger_texts.py

@@ -4,9 +4,8 @@ import os
 
 import pytest
 from lxml import etree as ET
-from uniseg.graphemecluster import grapheme_clusters
 
-from .. import character_error_rate, page_text, alto_text
+from .. import alto_text, character_error_rate, page_text
 
 data_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "data")
 

src/dinglehopper/tests/test_integ_character_error_rate_ocr.py

@@ -6,7 +6,7 @@ import pytest
 from lxml import etree as ET
 from uniseg.graphemecluster import grapheme_clusters
 
-from .. import character_error_rate, page_text, alto_text
+from .. import alto_text, character_error_rate, page_text
 
 data_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "data")
 

src/dinglehopper/tests/test_integ_cli_dir.py

@@ -1,6 +1,8 @@
 import os
+
 import pytest
 from ocrd_utils import initLogging
+
 from dinglehopper.cli import process_dir
 
 data_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "data")

src/dinglehopper/tests/test_integ_cli_valid_json.py

@@ -1,9 +1,9 @@
 import json
 
 import pytest
-from .util import working_directory
 
 from ..cli import process
+from .util import working_directory
 
 
 @pytest.mark.integration

src/dinglehopper/tests/test_integ_differences.py

@@ -1,7 +1,9 @@
 import json
 import os
+
 import pytest
 from ocrd_utils import initLogging
+
 from dinglehopper.cli import process
 
 data_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "data")

src/dinglehopper/tests/test_integ_edit_distance_ocr.py

@@ -5,7 +5,7 @@ import os
 import pytest
 from lxml import etree as ET
 
-from .. import distance, page_text, alto_text
+from .. import alto_text, distance, page_text
 
 data_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "data")
 

src/dinglehopper/tests/test_integ_ocrd_cli.py

@@ -1,15 +1,14 @@
+import json
 import os
 import shutil
-import json
 import sys
 from pathlib import Path
 
 import pytest
 from click.testing import CliRunner
-from .util import working_directory
-
 
 from ..ocrd_cli import ocrd_dinglehopper
+from .util import working_directory
 
 data_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "data")
 

src/dinglehopper/tests/test_integ_summarize.py

@@ -1,8 +1,10 @@
 import json
 import os
+
 import pytest
-from .util import working_directory
+
 from .. import cli_summarize
+from .util import working_directory
 
 expected_cer_avg = (0.05 + 0.10) / 2
 expected_wer_avg = (0.15 + 0.20) / 2

src/dinglehopper/tests/test_integ_word_error_rate_ocr.py

@@ -5,7 +5,7 @@ import os
 import pytest
 from lxml import etree as ET
 
-from .. import word_error_rate, words, page_text, alto_text
+from .. import alto_text, page_text, word_error_rate, words
 
 data_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "data")
 

src/dinglehopper/tests/test_ocr_files.py

@@ -1,13 +1,11 @@
 import os
 import re
-
-import lxml.etree as ET
 import textwrap
 
-import pytest
+import lxml.etree as ET
 
-from .util import working_directory
 from .. import alto_namespace, alto_text, page_namespace, page_text, plain_text, text
+from .util import working_directory
 
 data_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "data")
 

src/dinglehopper/tests/util.py

@@ -1,8 +1,8 @@
+import os
 from itertools import zip_longest
 from typing import Iterable
 
 import colorama
-import os
 
 
 def diffprint(x, y):

src/dinglehopper/word_error_rate.py

@@ -1,14 +1,13 @@
 from __future__ import division
 
 import unicodedata
-from typing import Tuple, Iterable
-from multimethod import multimethod
+from typing import Iterable, Tuple
 
 import uniseg.wordbreak
-
+from multimethod import multimethod
 from rapidfuzz.distance import Levenshtein
-from . import ExtractedText
 
+from . import ExtractedText
 
 # Did we patch uniseg.wordbreak.word_break already?
 word_break_patched = False