🚧 dinglehopper: WIP data structure for extracted text

extracted_text.py

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

extracted_text_test.py

@@ -13,7 +13,5 @@ def test_text():
     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'))