Fix invalid regex for U+10000-U+10FFFF range

This fixes a bad unicode range in the INVALID_XML10_CHARS regex which caused valid XML unicode character to be escaped.
felixbuenemann · Oct 30, 2017 · 229ab50 · 229ab50
1 parent 763904c
commit 229ab50
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 1 deletion.
diff --git a/lib/xlsxtream/xml.rb b/lib/xlsxtream/xml.rb
@@ -16,7 +16,7 @@ module XML
 
     # http://www.w3.org/TR/REC-xml/#NT-Char:
     # Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]
-    INVALID_XML10_CHARS = /[^\x09\x0A\x0D\x20-\uD7FF\uE000-\uFFFD\u10000-\u10FFFF]/.freeze
+    INVALID_XML10_CHARS = /[^\x09\x0A\x0D\x20-\uD7FF\uE000-\uFFFD\u{10000}-\u{10FFFF}]/.freeze
 
     # ST_Xstring escaping
     ESCAPE_CHAR = lambda { |c| '_x%04X_'.freeze % c.ord }.freeze

diff --git a/test/xlsxtream/xml_test.rb b/test/xlsxtream/xml_test.rb
@@ -35,5 +35,11 @@ def test_escape_value_invalid_xml_chars
       expected = 'The _x0007_ rings_x0000__xFFFE__xFFFF_'
       assert_equal expected, XML.escape_value(unsafe_value)
     end
+
+    def test_escape_value_valid_xml_chars
+      safe_value = "\u{10000}\u{10FFFF}"
+      expected = safe_value
+      assert_equal expected, XML.escape_value(safe_value)
+    end
   end
 end