From 19ac9e89990eaee5977b2ee1df387ef32df4f4f9 Mon Sep 17 00:00:00 2001
From: Patrick Jentsch <p.jentsch@uni-bielefeld.de>
Date: Wed, 6 Mar 2019 18:31:18 +0100
Subject: [PATCH] Remove path from text id.

---
 spacy_nlp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/spacy_nlp b/spacy_nlp
index 8e52ac8..6d895a5 100755
--- a/spacy_nlp
+++ b/spacy_nlp
@@ -42,7 +42,7 @@ with open(args.input) as input_file:
 
 # Create and open the output file
 output_file = open(args.output, "w+")
-output_file.write('<?xml version="1.0" encoding="UTF-8"?>\n<corpus>\n<text id="' + args.input.rsplit(".", 1)[0] + '">\n')
+output_file.write('<?xml version="1.0" encoding="UTF-8"?>\n<corpus>\n<text id="' + os.path.basename(args.input).rsplit(".", 1)[0] + '">\n')
 for text in texts:
     # Run spacy nlp over the text (partial string if above 1 million chars)
     doc = nlp(text)