Linting and type hint imports

kraken/align.py

@@ -29,16 +29,18 @@
 from bidi.algorithm import get_display
 
 from dataclasses import dataclass
-from typing import Optional, Literal
+from typing import Optional, Literal, TYPE_CHECKING
 
 from kraken import rpred
 from kraken.containers import Segmentation, BaselineOCRRecord
-from kraken.lib.models import TorchSeqRecognizer
+
+if TYPE_CHECKING:
+    from kraken.lib.models import TorchSeqRecognizer
 
 logger = logging.getLogger('kraken')
 
 
-def forced_align(doc: Segmentation, model: TorchSeqRecognizer, base_dir: Optional[Literal['L', 'R']] = None) -> Segmentation:
+def forced_align(doc: Segmentation, model: 'TorchSeqRecognizer', base_dir: Optional[Literal['L', 'R']] = None) -> Segmentation:
     """
     Performs a forced character alignment of text with recognition model
     output activations.

kraken/binarization.py

@@ -23,27 +23,32 @@
 import logging
 import numpy as np
 
-from PIL import Image
 from kraken.lib.util import pil2array, array2pil, is_bitonal, get_im_str
 from scipy.ndimage import affine_transform, percentile_filter, gaussian_filter, binary_dilation
 from scipy.ndimage import zoom as _zoom
 
+from typing import TYPE_CHECKING
+
 from kraken.lib.exceptions import KrakenInputException
 
+if TYPE_CHECKING:
+    from PIL import Image
+
+
 __all__ = ['nlbin']
 
 logger = logging.getLogger(__name__)
 
 
-def nlbin(im: Image.Image,
+def nlbin(im: 'Image.Image',
           threshold: float = 0.5,
           zoom: float = 0.5,
           escale: float = 1.0,
           border: float = 0.1,
           perc: int = 80,
           range: int = 20,
           low: int = 5,
-          high: int = 90) -> Image.Image:
+          high: int = 90) -> 'Image.Image':
     """
     Performs binarization using non-linear processing.
 

kraken/containers.py

@@ -22,13 +22,16 @@
 import numpy as np
 import bidi.algorithm as bd
 
-from os import PathLike
-from typing import Literal, List, Dict, Union, Optional, Tuple, Any
+from typing import Literal, List, Dict, Union, Optional, Tuple, Any, TYPE_CHECKING
 from dataclasses import dataclass, asdict
 from abc import ABC, abstractmethod
 
 from kraken.lib.segmentation import compute_polygon_section
 
+if TYPE_CHECKING:
+    from os import PathLike
+
+
 __all__ = ['BaselineLine',
            'BBoxLine',
            'Segmentation',
@@ -85,7 +88,7 @@ class BaselineLine:
     text: Optional[str] = None
     base_dir: Optional[Literal['L', 'R']] = None
     type: str = 'baselines'
-    imagename: Optional[Union[str, PathLike]] = None
+    imagename: Optional[Union[str, 'PathLike']] = None
     tags: Optional[Dict[str, str]] = None
     split: Optional[Literal['train', 'validation', 'test']] = None
     regions: Optional[List[str]] = None
@@ -124,7 +127,7 @@ class BBoxLine:
     text: Optional[str] = None
     base_dir: Optional[Literal['L', 'R']] = None
     type: str = 'bbox'
-    imagename: Optional[Union[str, PathLike]] = None
+    imagename: Optional[Union[str, 'PathLike']] = None
     tags: Optional[Dict[str, str]] = None
     split: Optional[Literal['train', 'validation', 'test']] = None
     regions: Optional[List[str]] = None
@@ -145,7 +148,7 @@ class Region:
     """
     id: str
     boundary: List[Tuple[int, int]]
-    imagename: Optional[Union[str, PathLike]] = None
+    imagename: Optional[Union[str, 'PathLike']] = None
     tags: Optional[Dict[str, str]] = None
 
 
@@ -175,7 +178,7 @@ class Segmentation:
                      Each reading order is a list of line indices.
     """
     type: Literal['baselines', 'bbox']
-    imagename: Union[str, PathLike]
+    imagename: Union[str, 'PathLike']
     text_direction: Literal['horizontal-lr', 'horizontal-rl', 'vertical-lr', 'vertical-rl']
     script_detection: bool
     lines: List[Union[BaselineLine, BBoxLine]]

kraken/contrib/extract_lines.py

@@ -1,6 +1,7 @@
 #! /usr/bin/env python
 import click
 
+
 @click.command()
 @click.option('-f', '--format-type', type=click.Choice(['xml', 'alto', 'page', 'binary']), default='xml',
               help='Sets the input document format. In ALTO and PageXML mode all '

kraken/contrib/heatmap_overlay.py

@@ -4,6 +4,7 @@
 """
 import click
 
+
 @click.command()
 @click.option('-i', '--model', default=None, show_default=True, type=click.Path(exists=True),
               help='Baseline detection model to use.')

kraken/contrib/hyperparameters/tune_pretraining.py

@@ -51,6 +51,7 @@ def train_tune(config, training_data=None, epochs=100, spec=RECOGNITION_SPEC):
                          enable_progress_bar=False)
     trainer.fit(model, datamodule=data_module)
 
+
 @click.command()
 @click.option('-v', '--verbose', default=0, count=True)
 @click.option('-s', '--seed', default=42, type=click.INT,
@@ -83,5 +84,6 @@ def cli(verbose, seed, output, num_samples, epochs, spec, training_files, files)
 
     click.echo("Best hyperparameters found were: ", analysis.get_best_config(metric='accuracy', mode='max'))
 
+
 if __name__ == '__main__':
     cli()

kraken/contrib/hyperparameters/tune_training.py

@@ -11,7 +11,6 @@
 
 from kraken.lib.default_spec import RECOGNITION_PRETRAIN_HYPER_PARAMS, RECOGNITION_SPEC
 from kraken.lib.pretrain.model import PretrainDataModule, RecognitionPretrainModel
-from ray.tune.schedulers import ASHAScheduler
 
 import pytorch_lightning as pl
 

kraken/contrib/segmentation_overlay.py

@@ -11,6 +11,7 @@
 from itertools import cycle
 from collections import defaultdict
 
+
 cmap = cycle([(230, 25, 75, 127),
               (60, 180, 75, 127)])
 

kraken/ketos/transcription.py

@@ -202,7 +202,7 @@ def transcription(ctx, text_direction, scale, bw, maxcolseps,
             else:
                 with click.open_file(lines, 'r') as fp:
                     try:
-                        fp = cast(IO[Any], fp)
+                        fp = cast('IO[Any]', fp)
                         res = json.load(fp)
                     except ValueError as e:
                         raise click.UsageError('{} invalid segmentation: {}'.format(lines, str(e)))

kraken/kraken.py

@@ -86,7 +86,7 @@ def binarizer(threshold, zoom, escale, border, perc, range, low, high, input, ou
                                  low, high)
         if ctx.meta['last_process'] and ctx.meta['output_mode'] != 'native':
             with click.open_file(output, 'w', encoding='utf-8') as fp:
-                fp = cast(IO[Any], fp)
+                fp = cast('IO[Any]', fp)
                 logger.info('Serializing as {} into {}'.format(ctx.meta['output_mode'], output))
                 res.save(f'{output}.png')
                 from kraken import serialization
@@ -159,7 +159,7 @@ def segmenter(legacy, model, text_direction, scale, maxcolseps, black_colseps,
         ctx.exit(1)
     if ctx.meta['last_process'] and ctx.meta['output_mode'] != 'native':
         with click.open_file(output, 'w', encoding='utf-8') as fp:
-            fp = cast(IO[Any], fp)
+            fp = cast('IO[Any]', fp)
             logger.info('Serializing as {} into {}'.format(ctx.meta['output_mode'], output))
             from kraken import serialization
             fp.write(serialization.serialize_segmentation(res,
@@ -170,7 +170,7 @@ def segmenter(legacy, model, text_direction, scale, maxcolseps, black_colseps,
                                                           processing_steps=ctx.meta['steps']))
     else:
         with click.open_file(output, 'w') as fp:
-            fp = cast(IO[Any], fp)
+            fp = cast('IO[Any]', fp)
             json.dump(dataclasses.asdict(res), fp)
     message('\u2713', fg='green')
 
@@ -208,7 +208,7 @@ def recognizer(model, pad, no_segmentation, bidi_reordering, tags_ignore, input,
     if not bounds and ctx.meta['base_image'] != input:
         with click.open_file(input, 'r') as fp:
             try:
-                fp = cast(IO[Any], fp)
+                fp = cast('IO[Any]', fp)
                 bounds = Segmentation(**json.load(fp))
             except ValueError as e:
                 raise click.UsageError(f'{input} invalid segmentation: {str(e)}')
@@ -244,7 +244,7 @@ def recognizer(model, pad, no_segmentation, bidi_reordering, tags_ignore, input,
 
     ctx = click.get_current_context()
     with click.open_file(output, 'w', encoding='utf-8') as fp:
-        fp = cast(IO[Any], fp)
+        fp = cast('IO[Any]', fp)
         message(f'Writing recognition results for {ctx.meta["orig_file"]}\t', nl=False)
         logger.info('Serializing as {} into {}'.format(ctx.meta['output_mode'], output))
         if ctx.meta['output_mode'] != 'native':

kraken/lib/arrow_dataset.py

@@ -26,15 +26,17 @@
 from PIL import Image, UnidentifiedImageError
 from functools import partial
 from collections import Counter
-from typing import Optional, List, Union, Callable, Tuple, Dict
+from typing import Optional, List, Union, Callable, Tuple, Dict, TYPE_CHECKING
 from multiprocessing import Pool
 from kraken.containers import Segmentation
 from kraken.lib import functional_im_transforms as F_t
 from kraken.lib.segmentation import extract_polygons
 from kraken.lib.xml import XMLPage
 from kraken.lib.util import is_bitonal, make_printable
 from kraken.lib.exceptions import KrakenInputException
-from os import PathLike
+
+if TYPE_CHECKING:
+    from os import PathLike
 
 import logging
 
@@ -89,7 +91,7 @@ def _extract_path_line(xml_record, skip_empty_lines: bool = True):
     return [line], im.mode
 
 
-def parse_path(path: Union[str, PathLike],
+def parse_path(path: Union[str, 'PathLike'],
                suffix: str = '.gt.txt',
                split=F_t.default_split,
                skip_empty_lines: bool = True):
@@ -101,8 +103,8 @@ def parse_path(path: Union[str, PathLike],
     return {'image': path, 'lines': [{'text': gt}]}
 
 
-def build_binary_dataset(files: Optional[List[Union[str, PathLike, Dict]]] = None,
-                         output_file: Union[str, PathLike] = None,
+def build_binary_dataset(files: Optional[List[Union[str, 'PathLike', Dict]]] = None,
+                         output_file: Union[str, 'PathLike'] = None,
                          format_type: str = 'xml',
                          num_workers: int = 0,
                          ignore_splits: bool = False,

kraken/lib/dataset/recognition.py

@@ -24,12 +24,11 @@
 import pyarrow as pa
 
 from PIL import Image
-from os import PathLike
 from functools import partial
 from torchvision import transforms
 from collections import Counter
 from torch.utils.data import Dataset
-from typing import List, Tuple, Callable, Optional, Any, Union, Literal
+from typing import List, Tuple, Callable, Optional, Any, Union, Literal, TYPE_CHECKING
 
 from kraken.containers import BaselineLine, BBoxLine, Segmentation
 from kraken.lib.util import is_bitonal
@@ -39,6 +38,9 @@
 
 from kraken.lib import functional_im_transforms as F_t
 
+if TYPE_CHECKING:
+    from os import PathLike
+
 __all__ = ['DefaultAugmenter',
            'ArrowIPCRecognitionDataset',
            'PolygonGTDataset',
@@ -137,7 +139,7 @@ def __init__(self,
 
         self.im_mode = self.transforms.mode
 
-    def add(self, file: Union[str, PathLike]) -> None:
+    def add(self, file: Union[str, 'PathLike']) -> None:
         """
         Adds an Arrow IPC file to the dataset.
 

kraken/lib/dataset/ro.py

@@ -19,14 +19,16 @@
 import numpy as np
 
 from math import factorial
-from os import PathLike
 from torch.utils.data import Dataset
-from typing import Dict, Sequence, Union, Literal, Optional
+from typing import Dict, Sequence, Union, Literal, Optional, TYPE_CHECKING
 
 from kraken.lib.xml import XMLPage
 
 from kraken.lib.exceptions import KrakenInputException
 
+if TYPE_CHECKING:
+    from os import PathLike
+
 __all__ = ['PairWiseROSet', 'PageWiseROSet']
 
 import logging
@@ -40,7 +42,7 @@ class PairWiseROSet(Dataset):
 
     Returns random pairs of lines from the same page.
     """
-    def __init__(self, files: Sequence[Union[PathLike, str]] = None,
+    def __init__(self, files: Sequence[Union['PathLike', str]] = None,
                  mode: Optional[Literal['alto', 'page', 'xml']] = 'xml',
                  level: Literal['regions', 'baselines'] = 'baselines',
                  ro_id: Optional[str] = None,
@@ -142,7 +144,7 @@ class PageWiseROSet(Dataset):
 
     Returns all lines from the same page.
     """
-    def __init__(self, files: Sequence[Union[PathLike, str]] = None,
+    def __init__(self, files: Sequence[Union['PathLike', str]] = None,
                  mode: Optional[Literal['alto', 'page', 'xml']] = 'xml',
                  level: Literal['regions', 'baselines'] = 'baselines',
                  ro_id: Optional[str] = None,

kraken/lib/dataset/segmentation.py

@@ -27,12 +27,13 @@
 from torchvision import transforms
 from collections import defaultdict
 from torch.utils.data import Dataset
-from typing import Dict, Tuple, Sequence, Callable, Any, Union, Literal, Optional
+from typing import Dict, Tuple, Sequence, Callable, Any, Union, Literal, Optional, TYPE_CHECKING
 
 from skimage.draw import polygon
 
-from kraken.containers import Segmentation
-from kraken.lib.xml import XMLPage
+if TYPE_CHECKING:
+    from kraken.containers import Segmentation
+    from kraken.lib.xml import XMLPage
 
 
 __all__ = ['BaselineSet']
@@ -124,7 +125,7 @@ def __init__(self,
         self.transforms = im_transforms
         self.seg_type = None
 
-    def add(self, doc: Union[Segmentation, XMLPage]):
+    def add(self, doc: Union['Segmentation', 'XMLPage']):
         """
         Adds a page to the dataset.
 

kraken/lib/functional_im_transforms.py

@@ -21,16 +21,18 @@
 import unicodedata
 import bidi.algorithm as bd
 
-from os import PathLike
 from pathlib import Path
-from PIL import Image
 from PIL.Image import Resampling
 
-from typing import Tuple, Optional, Callable, Any, Union
+from typing import Tuple, Optional, Callable, Any, Union, TYPE_CHECKING
 
 from kraken.binarization import nlbin
 from kraken.lib.lineest import dewarp, CenterNormalizer
 
+if TYPE_CHECKING:
+    from os import PathLike
+    from PIL import Image
+
 
 def pil_to_mode(im: Image.Image, mode: str) -> Image.Image:
     return im.convert(mode)