Update tests for data extraction

tests/test_extract.py

@@ -185,7 +185,6 @@ def test_normalize_spaces(text, trimmed):
         ("\rcarriage_return", "carriage_return"),
         ("\r\ncarriage_return+linebreak", "carriage_return+linebreak"),
         ("\n\r\r\n\ncarriage_return+linebreak", "carriage_return+linebreak"),
-        ("no|linebreaks", "no|linebreaks"),
     ),
 )
 def test_normalize_linebreaks(text, trimmed):
@@ -396,10 +395,9 @@ def test_extract(
         VAL_DIR / "val-page_1-line_2.jpg",
         VAL_DIR / "val-page_1-line_3.jpg",
         output / "labels.json",
-        # Language resources
-        output / "language_model" / "corpus.txt",
-        output / "language_model" / "lexicon.txt",
-        output / "language_model" / "tokens.txt",
+        output / "language_corpus.txt",
+        output / "language_lexicon.txt",
+        output / "language_tokens.txt",
     ]
     assert sorted(filter(methodcaller("is_file"), output.rglob("*"))) == expected_paths