commit 53623e04349fa06a8951eda046c4170ca6657566
author Marc Kupietz <kupietz@ids-mannheim.de> Wed Apr 07 19:07:20 2021 +0200
committer Marc Kupietz <kupietz@ids-mannheim.de> Wed Apr 07 19:07:20 2021 +0200
tree e8784c743cec9f5d35c8d04f52d0d50e2b0e1f35
parent bc8bd3d86fb7bc465fc6e4241a9d86b267823958

Add --downcase/-d option to convert all token characters to lower case

Change-Id: I236cf61369faead4b9e4d955b7190b25f88d4a46

src/test/resources/entities.conllu

diff --git a/src/test/resources/entities.conllu b/src/test/resources/entities.conllu
new file mode 100644
index 0000000..fe4731d
--- /dev/null
+++ b/src/test/resources/entities.conllu
@@ -0,0 +1,15 @@
+# foundry = tree_tagger
+# filename = A00/JAN/00001/tree_tagger/morpho.xml  
+# text_id = A00_JAN.00001
+# start_offsets = 0 0 3 7 14 18 28 31 38 45 51 63
+# end_offsets = 64 2 6 13 17 27 30 37 44 50 63 64
+1	In	in	APPR	APPR	_	_	_	_	1.000000
+2	den	die	ART	ART	_	_	_	_	0.999974
+3	Farben	Farbe	NN	NN	_	_	_	_	1.000000
+4	der	die	ART	ART	_	_	_	_	0.999973
+5	Dämmerung	Dämmerung	NN	NN	_	_	_	_	1.000000
+6	'	--	NN	NN	_	_	_	_	1.0
+7	<	--	NN	NN	_	_	_	_	1.0
+8	>	--	NN	NN	_	_	_	_	1.0
+9	&	--	NN	NN	_	_	_	_	1.0
+10	"	--	NN	NN	_	_	_	_	1.0