diff --git a/tools/test_corpus.txt b/tools/test_corpus.txt
new file mode 100644
index 0000000..6ab389f
--- /dev/null
+++ b/tools/test_corpus.txt
@@ -0,0 +1,11 @@
+test sentence
+this is a test sentence
+test sentence
+test sentence 321
+test sentence 3123
+3213 12.01.1998
+  this   ,,.,    is []';'] A ,,./ test ,,../; SENTENCE
+this is a <a href="http://example.com" target="_blank">test</a> sentence
+zażółć gęślą jaźń 32
+ZAŻÓŁĆ GĘŚLĄ JAŹŃ 54
+unique sentence