qurator-spk/dinglehopper
1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-07-03 07:29:59 +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 20:31:54 +02:00
parent 91371971eb
commit eca8cbc81e
2 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

4
extracted_text.py
View file

@ -4,14 +4,14 @@ import enum
# TODO handle grapheme cluster positions? # TODO handle grapheme cluster positions?
# TODO Use type annotations for attr.ib types when support for Python 3.5 is dropped
# TODO types are not validated (attr does not do this yet)
@attr.s(frozen=True) @attr.s(frozen=True)
class ExtractedText: class ExtractedText:
segments = attr.ib() segments = attr.ib()
joiner = attr.ib(type=str) joiner = attr.ib(type=str)
# XXX Use type annotations for attr types when support for Python 3.5 is dropped
# XXX Also I think these are not validated?
@property @property
def text(self): def text(self):

2
extracted_text_test.py
View file

@ -6,7 +6,7 @@ from extracted_text import ExtractedText, ExtractedTextSegment
def test_text(): def test_text():
test1 = ExtractedText([ test1 = ExtractedText([
ExtractedTextSegment('s0', 'foo'), ExtractedTextSegment('s0', 'foo'),
ExtractedTextSegment(1, 'bar'), ExtractedTextSegment('s1', 'bar'),
ExtractedTextSegment('s2', 'bazinga') ExtractedTextSegment('s2', 'bazinga')
], ' ') ], ' ')