From 89852314dc7cf57aa85574a613b008fee58d3226 Mon Sep 17 00:00:00 2001
From: "Gerber, Mike" <mike.gerber@sbb.spk-berlin.de>
Date: Wed, 10 Jun 2020 19:49:12 +0200
Subject: [PATCH] =?UTF-8?q?=F0=9F=9A=A7=20dinglehopper:=20WIP=20data=20str?=
 =?UTF-8?q?ucture=20for=20extracted=20text?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 extracted_text.py      | 3 +++
 extracted_text_test.py | 2 --
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/extracted_text.py b/extracted_text.py
index a76f402..69d836b 100644
--- a/extracted_text.py
+++ b/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()
diff --git a/extracted_text_test.py b/extracted_text_test.py
index 29fabfe..b302ca8 100644
--- a/extracted_text_test.py
+++ b/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'))