1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-06-09 11:50:00 +02:00

dinglehopper: Show a progressbar on --progress

This commit is contained in:
Gerber, Mike 2020-10-15 16:09:17 +02:00
parent 4951823a29
commit 5ed184c8c4
5 changed files with 11 additions and 3 deletions

View file

@ -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)

View file

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

View file

@ -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