qurator-spk/dinglehopper
1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-06-07 19:05:13 +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 19:40:57 +02:00
parent ac1e1ec79a
commit 4e9b0aeef1
2 changed files with 19 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

16
extracted_text.py
View file

@ -43,19 +43,3 @@ class ExtractedTextSegment:
if normalize(value, self.normalization) != value:
raise ValueError('String "{}" is not normalized.'.format(value))
normalization = attr.ib(default=NORM_NFC)
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) == None
assert test1.segment_id_for_pos(10) == 's2'
# ExtractedTextSegment('foo', unicodedata.normalize('NFD', 'Schlyñ'))
ExtractedTextSegment('foo', unicodedata.normalize('NFC', 'Schlyñ'))

19
extracted_text_test.py Normal file
View file

@ -0,0 +1,19 @@
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'
# TODO handle grapheme cluster positions?
# ExtractedTextSegment('foo', unicodedata.normalize('NFD', 'Schlyñ'))
ExtractedTextSegment('foo', unicodedata.normalize('NFC', 'Schlyñ'))