1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-07-03 23:49:57 +02:00
dinglehopper/extracted_text_test.py

17 lines
547 B
Python

from extracted_text import *
def test_text():
test1 = ExtractedText([
ExtractedTextSegment('s0', 'foo'),
ExtractedTextSegment('s1', 'bar'),
ExtractedTextSegment('s2', 'bazinga')
], ' ')
assert test1.text == 'foo bar bazinga'
assert test1.segment_id_for_pos(0) == 's0'
assert test1.segment_id_for_pos(3) is None
assert test1.segment_id_for_pos(10) == 's2'
# ExtractedTextSegment('foo', unicodedata.normalize('NFD', 'Schlyñ'))
ExtractedTextSegment('foo', unicodedata.normalize('NFC', 'Schlyñ'))