From 64496874c46485bf7fddc86cde655990d656f1ba Mon Sep 17 00:00:00 2001
From: PhilipMay <philip@may.la>
Date: Sat, 23 Sep 2023 16:48:25 +0200
Subject: [PATCH] fix bug SoMaJo link extraction bug #94

---
 pyproject.toml       | 2 +-
 tests/test_somajo.py | 1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index 49f349f..f6c8fd3 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -61,7 +61,7 @@ scikit-learn = {version = "*", optional = true}
 fasttext-wheel = {version = "*", optional = true}
 optuna = {version = "*", optional = true}
 matplotlib = {version = "*", optional = true}
-SoMaJo = {version = "*", optional = true}
+SoMaJo = {version = ">=2.3.1", optional = true}
 torch = {version = "!=2.0.1", optional = true}  # version 2.0.1 has poetry issues
 transformers = {version = "*", optional = true}
 tiktoken = {version = "*", optional = true}
diff --git a/tests/test_somajo.py b/tests/test_somajo.py
index 3c36b20..1250f27 100644
--- a/tests/test_somajo.py
+++ b/tests/test_somajo.py
@@ -176,7 +176,6 @@ def test_UrlSwapper__no_reverse_swap_urls():
 
 
 # see https://github.com/telekom/mltb2/issues/94
-@pytest.mark.xfail
 def test_UrlSwapper__markdown_bug():
     token_extractor = TokenExtractor("de_CMC")
     url_swapper = UrlSwapper(token_extractor)