assume UTF8 encoding when reading javadocs HTML

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1356824 13f79535-47bb-0310-9956-ffa450edef68
2012-07-03 16:48:07 +00:00 · 2012-07-03 16:48:07 +00:00 · b4080ca7e5
parent dae7f3e56a
commit b4080ca7e5
1 changed files with 1 additions and 1 deletions
--- a/dev-tools/scripts/checkJavadocLinks.py
+++ b/dev-tools/scripts/checkJavadocLinks.py
@ -128,7 +128,7 @@ def checkAll(dirName):
        # deprecated-list.html can fail to escape generics types
        fullPath = os.path.join(root, f)
        #print '  %s' % fullPath
-        allFiles[fullPath] = parse(fullPath, open('%s/%s' % (root, f)).read())
+        allFiles[fullPath] = parse(fullPath, open('%s/%s' % (root, f), encoding='UTF-8').read())

  # ... then verify:
  print()