Strip more known bad characters before parsing

Removes all the non-printable characters excluded from the XML [characters specification][1]. [1]: https://www.w3.org/TR/xml/#charsets
WinRb · Dec 5, 2016 · f8e0aa6 · f8e0aa6
1 parent 6d17df3
commit f8e0aa6
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/lib/ews/soap/parsers/ews_parser.rb b/lib/ews/soap/parsers/ews_parser.rb
@@ -28,7 +28,7 @@ def initialize(soap_resp)
 
     def parse(opts = {})
       opts[:response_class] ||= EwsSoapResponse
-      @soap_resp.gsub!(/&#x1A;/, '')
+      @soap_resp.gsub!(/&#x([0-8bcef]|1[0-9a-f]);/i, '')
       sax_parser.parse(@soap_resp)
       opts[:response_class].new @sax_doc.struct
     end

diff --git a/spec/soap_data/dodgy_ews_response.xml b/spec/soap_data/dodgy_ews_response.xml
@@ -15,7 +15,7 @@
               <t:ItemClass>IPM.Appointment</t:ItemClass>
               <t:Subject>Invalid character</t:Subject>
               <t:Sensitivity>Normal</t:Sensitivity>
-              <t:Body BodyType="Text"> Invalid character: &#x1A;</t:Body>
+              <t:Body BodyType="Text">Invalid characters: &#x0; &#x1; &#x2; &#x3; &#x4; &#x5; &#x6; &#x7; &#x8; &#xb; &#xc; &#xe; &#xf; &#x10; &#x11; &#x12; &#x13; &#x14; &#x15; &#x16; &#x17; &#x18; &#x19; &#x1A; &#x1B; &#x1C; &#x1D; &#x1E; &#x1F; </t:Body>
               <t:DateTimeReceived>2016-01-01T00:00:00Z</t:DateTimeReceived>
               <t:Size>42</t:Size>
               <t:Importance>Normal</t:Importance>