qurator-spk/dinglehopper
1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-07-04 07:59:59 +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 19:49:12 +02:00
parent 93608ba697
commit 8e3a19d7e9
2 changed files with 3 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

3
extracted_text.py
View file

@ -2,6 +2,9 @@ import attr
import unicodedata import unicodedata
# TODO handle grapheme cluster positions?
@attr.s(frozen=True) @attr.s(frozen=True)
class ExtractedText: class ExtractedText:
segments = attr.ib() segments = attr.ib()

2
extracted_text_test.py
View file

@ -13,7 +13,5 @@ def test_text():
assert test1.segment_id_for_pos(3) is None assert test1.segment_id_for_pos(3) is None
assert test1.segment_id_for_pos(10) == 's2' assert test1.segment_id_for_pos(10) == 's2'
# TODO handle grapheme cluster positions?
# ExtractedTextSegment('foo', unicodedata.normalize('NFD', 'Schlyñ')) # ExtractedTextSegment('foo', unicodedata.normalize('NFD', 'Schlyñ'))
ExtractedTextSegment('foo', unicodedata.normalize('NFC', 'Schlyñ')) ExtractedTextSegment('foo', unicodedata.normalize('NFC', 'Schlyñ'))