fix bug SoMaJo link extraction bug #94

telekom · Sep 23, 2023 · 6449687 · 6449687
1 parent 2546eff
commit 6449687
Show file tree

Hide file tree

Showing 2 changed files with 1 addition and 2 deletions.
diff --git 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
@@ -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)