qurator-spk/dinglehopper
1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-07-12 20:09:58 +02:00
Code Issues Releases Wiki Activity

🚧 dinglehopper: WIP data structure for extracted text

Browse source
This commit is contained in:
Gerber, Mike 2020-06-10 20:29:01 +02:00
parent 89852314dc
commit 534e042f9e
2 changed files with 16 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

15
extracted_text_test.py
View file

@ -1,17 +1,22 @@
from extracted_text import *
import unicodedata
import pytest
from extracted_text import ExtractedText, ExtractedTextSegment
def test_text():
test1 = ExtractedText([
ExtractedTextSegment('s0', 'foo'),
ExtractedTextSegment('s1', 'bar'),
ExtractedTextSegment(1, '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'))
def test_normalization_check():
with pytest.raises(ValueError, match=r'.*is not normalized.*'):
ExtractedTextSegment('foo', unicodedata.normalize('NFD', 'Schlyñ'))
assert ExtractedTextSegment('foo', unicodedata.normalize('NFC', 'Schlyñ'))