✨ dinglehopper: Show a progressbar on --progress

README.md

@@ -45,6 +45,7 @@ Usage: dinglehopper [OPTIONS] GT OCR [REPORT_PREFIX]
 
 Options:
   --metrics / --no-metrics  Enable/disable metrics and green/red
+  --progress                Show progress bar
   --help                    Show this message and exit.
 ~~~
 

qurator/dinglehopper/cli.py

@@ -10,7 +10,7 @@ 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 extract
-
+from .config import Config
 
 def gen_diff_report(gt_in, ocr_in, css_prefix, joiner, none):
     gtx = ''
@@ -134,7 +134,8 @@ def process(gt, ocr, report_prefix, *, metrics=True):
 @click.argument('ocr', type=click.Path(exists=True))
 @click.argument('report_prefix', type=click.Path(), default='report')
 @click.option('--metrics/--no-metrics', default=True, help='Enable/disable metrics and green/red')
-def main(gt, ocr, report_prefix, metrics):
+@click.option('--progress', default=False, is_flag=True, help='Show progress bar')
+def main(gt, ocr, report_prefix, metrics, progress):
     """
     Compare the PAGE/ALTO/text document GT against the document OCR.
 
@@ -150,6 +151,7 @@ def main(gt, ocr, report_prefix, metrics):
     $REPORT_PREFIX defaults to "report". The reports include the character error
     rate (CER) and the word error rate (WER).
     """
+    Config.progress = progress
     process(gt, ocr, report_prefix, metrics=metrics)
 
 

qurator/dinglehopper/config.py

@@ -0,0 +1,2 @@
+class Config:
+    progress = False

qurator/dinglehopper/edit_distance.py

@@ -7,8 +7,10 @@ from typing import Sequence, Tuple
 import numpy as np
 from multimethod import multimethod
 from uniseg.graphemecluster import grapheme_clusters
+from tqdm import tqdm
 
 from .extracted_text import ExtractedText
+from .config import Config
 
 
 def levenshtein_matrix(seq1: Sequence, seq2: Sequence):
@@ -43,7 +45,7 @@ def _levenshtein_matrix(seq1: Tuple, seq2: Tuple):
         D[i, 0] = i
     for j in from_to(1, n):
         D[0, j] = j
-    for i in from_to(1, m):
+    for i in tqdm(from_to(1, m), disable=not Config.progress):
         for j in from_to(1, n):
             D[i, j] = min(
                 D[i - 1, j - 1] + 1 * (seq1[i - 1] != seq2[j - 1]),  # Same or Substitution

requirements.txt

@@ -8,3 +8,4 @@ MarkupSafe
 ocrd >= 2.13.1
 attrs
 multimethod == 1.3  # latest version to officially support Python 3.5
+tqdm