From 38c02f38e6cde28150202bdfad5ed7e87b24e9bf Mon Sep 17 00:00:00 2001
From: David Rouquet <david.rouquet@tetras-libre.fr>
Date: Thu, 11 Jun 2020 10:42:26 +0200
Subject: [PATCH] Ignore commit when parsing a document Closes #4

---
 scripts/unlizeXml.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/scripts/unlizeXml.py b/scripts/unlizeXml.py
index e3af7af..c05a361 100755
--- a/scripts/unlizeXml.py
+++ b/scripts/unlizeXml.py
@@ -1,6 +1,6 @@
 #!/bin/env python3
 
-from lxml import etree
+from lxml import etree, objectify
 import requests
 import click
 import tempfile
@@ -125,7 +125,8 @@ def unl2dot(text, path):
               help='Path of the unltools jar')
 def unlizeXml(input, output, lang, dry_run, svg, unltools_path):
 
-    doc = etree.parse(input)
+    parser = etree.XMLParser(remove_comments=True)
+    doc = objectify.parse(input, parser=parser)
     remove_namespace(doc)
     tags = ['title', 'text_body', 'term', 'meaning']
     for t in tags:
-- 
GitLab