Sanitize the access_header.

The access_header can contain a lot of nonsense, like whitespace around
or additional \n's or \r's.  We used to sanitize that, but then
regressed in e95413d151c3f0d9476063c8520dd477342ed235 where the
"tokenize by any of \n\r" was by mistake replaced with "tokenize by
string '\n\r'".

Unfortunately the unit test didn't uncover that, and the further
refactorings of the related code have hidden that even more.

Change-Id: Ie2bf950d0426292770b599e40ee2401101162ff2
Reviewed-on: https://gerrit.libreoffice.org/c/online/+/96638
Tested-by: Jenkins
Tested-by: Jenkins CollaboraOffice <jenkinscollaboraoffice@gmail.com>
Reviewed-by: Andras Timar <andras.timar@collabora.com>

1 files changed, 63 insertions, 0 deletions

diff --git a/test/WhiteBoxTests.cpp b/test/WhiteBoxTests.cpp
index bb2f57e4c..a2e676198 100644
--- a/test/WhiteBoxTests.cpp
+++ b/test/WhiteBoxTests.cpp
@@ -33,6 +33,7 @@ class WhiteBoxTests : public CPPUNIT_NS::TestFixture
     CPPUNIT_TEST(testSplitting);
     CPPUNIT_TEST(testMessageAbbreviation);
     CPPUNIT_TEST(testTokenizer);
+    CPPUNIT_TEST(testTokenizerTokenizeAnyOf);
     CPPUNIT_TEST(testReplace);
     CPPUNIT_TEST(testRegexListMatcher);
     CPPUNIT_TEST(testRegexListMatcher_Init);
@@ -54,6 +55,7 @@ class WhiteBoxTests : public CPPUNIT_NS::TestFixture
     void testSplitting();
     void testMessageAbbreviation();
     void testTokenizer();
+    void testTokenizerTokenizeAnyOf();
     void testReplace();
     void testRegexListMatcher();
     void testRegexListMatcher_Init();
@@ -426,6 +428,67 @@ void WhiteBoxTests::testTokenizer()
     LOK_ASSERT_EQUAL(static_cast<size_t>(0), ints.size());
 }
 
+void WhiteBoxTests::testTokenizerTokenizeAnyOf()
+{
+    StringVector tokens;
+    const char delimiters[] = "\n\r"; // any of these delimits; and we trim whitespace
+
+    tokens = Util::tokenizeAnyOf("", delimiters);
+    LOK_ASSERT_EQUAL(static_cast<size_t>(0), tokens.size());
+
+    tokens = Util::tokenizeAnyOf("  ", delimiters);
+    LOK_ASSERT_EQUAL(static_cast<size_t>(0), tokens.size());
+
+    tokens = Util::tokenizeAnyOf("A", delimiters);
+    LOK_ASSERT_EQUAL(static_cast<size_t>(1), tokens.size());
+    LOK_ASSERT_EQUAL(std::string("A"), tokens[0]);
+
+    tokens = Util::tokenizeAnyOf("  A", delimiters);
+    LOK_ASSERT_EQUAL(static_cast<size_t>(1), tokens.size());
+    LOK_ASSERT_EQUAL(std::string("A"), tokens[0]);
+
+    tokens = Util::tokenizeAnyOf("A  ", delimiters);
+    LOK_ASSERT_EQUAL(static_cast<size_t>(1), tokens.size());
+    LOK_ASSERT_EQUAL(std::string("A"), tokens[0]);
+
+    tokens = Util::tokenizeAnyOf(" A ", delimiters);
+    LOK_ASSERT_EQUAL(static_cast<size_t>(1), tokens.size());
+    LOK_ASSERT_EQUAL(std::string("A"), tokens[0]);
+
+    tokens = Util::tokenizeAnyOf(" A  Z ", delimiters);
+    LOK_ASSERT_EQUAL(static_cast<size_t>(1), tokens.size());
+    LOK_ASSERT_EQUAL(std::string("A  Z"), tokens[0]);
+
+    tokens = Util::tokenizeAnyOf("\n", delimiters);
+    LOK_ASSERT_EQUAL(static_cast<size_t>(0), tokens.size());
+
+    tokens = Util::tokenizeAnyOf("\n\r\r\n", delimiters);
+    LOK_ASSERT_EQUAL(static_cast<size_t>(0), tokens.size());
+
+    tokens = Util::tokenizeAnyOf(" A  \nZ ", delimiters);
+    LOK_ASSERT_EQUAL(static_cast<size_t>(2), tokens.size());
+    LOK_ASSERT_EQUAL(std::string("A"), tokens[0]);
+    LOK_ASSERT_EQUAL(std::string("Z"), tokens[1]);
+
+    tokens = Util::tokenizeAnyOf(" A  Z\n ", delimiters);
+    LOK_ASSERT_EQUAL(static_cast<size_t>(1), tokens.size());
+    LOK_ASSERT_EQUAL(std::string("A  Z"), tokens[0]);
+
+    tokens = Util::tokenizeAnyOf(" A  Z  \n\r\r\n ", delimiters);
+    LOK_ASSERT_EQUAL(static_cast<size_t>(1), tokens.size());
+    LOK_ASSERT_EQUAL(std::string("A  Z"), tokens[0]);
+
+    tokens = Util::tokenizeAnyOf(" A  \n\r\r\n  \r  \n  Z  \n ", delimiters);
+    LOK_ASSERT_EQUAL(static_cast<size_t>(2), tokens.size());
+    LOK_ASSERT_EQUAL(std::string("A"), tokens[0]);
+    LOK_ASSERT_EQUAL(std::string("Z"), tokens[1]);
+
+    tokens = Util::tokenizeAnyOf("  \r A  \n  \r  \n  Z  \n ", delimiters);
+    LOK_ASSERT_EQUAL(static_cast<size_t>(2), tokens.size());
+    LOK_ASSERT_EQUAL(std::string("A"), tokens[0]);
+    LOK_ASSERT_EQUAL(std::string("Z"), tokens[1]);
+}
+
 void WhiteBoxTests::testReplace()
 {
     LOK_ASSERT_EQUAL(std::string("zesz one zwo flee"), Util::replace("test one two flee", "t", "z"));