From 9af2a5cb18a26f2b37e85d3201c13e56fc7b3f6b Mon Sep 17 00:00:00 2001
From: manonBlanco <blanco@teklia.com>
Date: Thu, 20 Jul 2023 11:17:20 +0200
Subject: [PATCH] Test with only start token AND separators

---
 tests/test_extract.py | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/tests/test_extract.py b/tests/test_extract.py
index e6f999ee..c20c4674 100644
--- a/tests/test_extract.py
+++ b/tests/test_extract.py
@@ -170,9 +170,12 @@ def test_reconstruct_text_joined_entities(entity_separators, text_before, text_a
     )
 
 
+@pytest.mark.parametrize("joined", (True, False))
 @pytest.mark.parametrize("text_before", ("", "text before "))
 @pytest.mark.parametrize("text_after", ("", " text after"))
-def test_reconstruct_text_only_start_token(text_before, text_after):
+def test_reconstruct_text_only_start_token(joined, text_before, text_after):
+    separator = " " if not joined else ""
+
     arkindex_extractor = ArkindexExtractor(entity_separators=[" ", "\n"])
     arkindex_extractor.tokens = {
         "P": EntityType(start="â“Ÿ"),
@@ -180,7 +183,7 @@ def test_reconstruct_text_only_start_token(text_before, text_after):
     }
     assert (
         arkindex_extractor.reconstruct_text(
-            text_before + "LouisXIV" + text_after,
+            text_before + "Louis" + separator + "XIV" + text_after,
             [
                 Entity(
                     offset=0 + len(text_before),
@@ -189,12 +192,12 @@ def test_reconstruct_text_only_start_token(text_before, text_after):
                     value="Louis",
                 ),
                 Entity(
-                    offset=5 + len(text_before),
+                    offset=5 + len(separator) + len(text_before),
                     length=3,
                     type="I",
                     value="XIV",
                 ),
             ],
         )
-        == "ⓟLouisⓘXIV"
+        == "ⓟLouis" + separator + "ⓘXIV"
     )
-- 
GitLab