From 5f20f9be40f7af84ac3d628a10b36dbf18bb05b0 Mon Sep 17 00:00:00 2001
From: Patrick Jentsch <p.jentsch@uni-bielefeld.de>
Date: Mon, 27 Jan 2020 15:59:32 +0100
Subject: [PATCH] Remove id xml attribute from output file

---
 spacy_nlp | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

diff --git a/spacy_nlp b/spacy_nlp
index 57904d5..e5d086d 100755
--- a/spacy_nlp
+++ b/spacy_nlp
@@ -40,11 +40,9 @@ with open(args.i) as input_file:
 # Create and open the output file
 output_file = open(args.o, 'w+')
 
-output_file.write(
-    '<?xml version="1.0" encoding="UTF-8"?>\n'
-    '<corpus>\n'
-    '<text id="{}">\n'.format(os.path.basename(args.i).rsplit(".", 1)[0])
-)
+output_file.write('<?xml version="1.0" encoding="UTF-8"?>\n'
+                  '<corpus>\n'
+                  '<text>\n')
 for text in texts:
     # Run spacy nlp over the text (partial string if above 1 million chars)
     doc = nlp(text)
@@ -66,9 +64,7 @@ for text in texts:
                 )
             )
         output_file.write('</s>\n')
-output_file.write(
-    '</text>\n'
-    '</corpus>'
-)
+output_file.write('</text>\n'
+                  '</corpus>')
 
 output_file.close()