Do not write out invalid characters to XML file

For special characters such as: <, >, or ', write them out to the file
as: &#[decimal ASCII value];

Character     Written to    Appears in Jenkins
to encode     XML file      test result viewer
=========     ==========    ==================
  <            &lt;             <
  >            &gt;             >
  '            &apos;           '
  &            &amp;            &
  "            &quot;           "

For characters which are listed as RestrictedChar in
http://www.w3.org/TR/xml11/#charsets , these characters are completely
invalid XML, and cannot even be escaped.

Character     Written to    Appears in Jenkins
to encode     XML file      test result viewer
=========     ==========    ==================
  0x08         &amp;#8;          &#8;
  0x1F         &amp;#31;         &#31;

This will at least generate a valid XML file, but let us see where these
restricted characters would appear in the output.

Fixes #136

NEWS

@@ -57,6 +57,10 @@ STILL UNDER DEVELOPMENT; NOT RELEASED YET.
   GDB 6.1.1 (circa 2004) does not have the -ex flag so we need to
   generate a temporary GDB script and feed it to GDB with -x instead.
 
+* Issue 136: Fixed the XML escaping in the JUnit output so that
+  non-printable characters are properly handled when they appear in the
+  process's stdout or stderr.
+
 * Issue 141: Improved reporting of errors triggered by sqlite3.  In
   particular, all error messages are now tagged with their corresponding
   database filename and, if they are API-level errors, the name of the

utils/text/operations.cpp

@@ -38,6 +38,9 @@ namespace text = utils::text;
 
 /// Replaces XML special characters from an input string.
 ///
+/// The list of XML special characters is specified here:
+///     http://www.w3.org/TR/xml11/#charsets
+///
 /// \param in The input to quote.
 ///
 /// \return A quoted string without any XML special characters.
@@ -46,25 +49,34 @@ text::escape_xml(const std::string& in)
 {
     std::ostringstream quoted;
 
-    const char* delims = "\"&<>'";  // Keep in sync with 'switch' below.
-    std::string::size_type start_pos = 0;
-    std::string::size_type last_pos = in.find_first_of(delims);
-    while (last_pos != std::string::npos) {
-        quoted << in.substr(start_pos, last_pos - start_pos);
-        switch (in[last_pos]) {
-        case '"':  quoted << "&quot;"; break;
-        case '&':  quoted << "&amp;"; break;
-        case '<':  quoted << "&lt;"; break;
-        case '>':  quoted << "&gt;"; break;
-        case '\'': quoted << "&apos;"; break;
-        default:   UNREACHABLE;
+    for (std::string::const_iterator it = in.begin();
+         it != in.end(); ++it) {
+        unsigned char c = (unsigned char)*it;
+        if (c == '"') {
+            quoted << "&quot;";
+        } else if (c == '&') {
+            quoted << "&amp;";
+        } else if (c == '<') {
+            quoted << "&lt;";
+        } else if (c == '>') {
+            quoted << "&gt;";
+        } else if (c == '\'') {
+            quoted << "&apos;";
+        } else if ((c >= 0x01 && c <= 0x08) ||
+                   (c >= 0x0B && c <= 0x0C) ||
+                   (c >= 0x0E && c <= 0x1F) ||
+                   (c >= 0x7F && c <= 0x84) ||
+                   (c >= 0x86 && c <= 0x9F)) {
+            // for RestrictedChar characters, escape them
+            // as '&amp;#[decimal ASCII value];'
+            // so that in the XML file we will see the escaped
+            // character.
+            quoted << "&amp;#" << static_cast< std::string::size_type >(*it)
+                   << ";";
+        } else {
+            quoted << *it;
         }
-        start_pos = last_pos + 1;
-        last_pos = in.find_first_of(delims, start_pos);
     }
-    if (start_pos < in.length())
-        quoted << in.substr(start_pos);
-
     return quoted.str();
 }
 

utils/text/operations_test.cpp

@@ -77,6 +77,7 @@ ATF_TEST_CASE_BODY(escape_xml__no_escaping)
 {
     ATF_REQUIRE_EQ("a", text::escape_xml("a"));
     ATF_REQUIRE_EQ("Some text!", text::escape_xml("Some text!"));
+    ATF_REQUIRE_EQ("\n\t\r", text::escape_xml("\n\t\r"));
 }
 
 
@@ -90,6 +91,8 @@ ATF_TEST_CASE_BODY(escape_xml__some_escaping)
 
     ATF_REQUIRE_EQ("&quot;&amp;&lt;&gt;&apos;", text::escape_xml("\"&<>'"));
     ATF_REQUIRE_EQ("&amp;&amp;&amp;", text::escape_xml("&&&"));
+    ATF_REQUIRE_EQ("&amp;#8;&amp;#11;", text::escape_xml("\b\v"));
+    ATF_REQUIRE_EQ("\t&amp;#127;BAR&amp;", text::escape_xml("\t\x7f""BAR&"));
 }