Adapt qmake's raw-string parser to avoid confusion by macros

A macro name ending in R might expand to a string; if this precedes a
string constant, we're juxtaposing the strings.  My first parser for
raw strings would mistake it for a raw string instead, ignoring the
part of the identifier before R.  Re-worked the exploration of what
came before the string to catch these cases, too.

The backwards parsing would also allow any messy jumble of [RLUu8]* as
prefix for the string; but in fact R must (if present) be last in the
prefix and *it* can have at most one prefix, [LUu] or u8.  Anything
else is an identifier that happens to precede the string.  Reworked
the parsing to allow only one prefix and not treat R specially unless
it's immediately (modulo BSNL) before the string's open-quotes.

Add link to the cppreference page about string literals, on which the
grammar now parsed is based.

Added a test for the issue this addresses.
Verified that this fails on 5.6, dev and 5.9 without the fix.
Expanded the existing test to cover R-with-prefix cases.

Task-number: QTBUG-55633
Change-Id: I541486c2ec909cfb42050907c84bee83ead4a2f4
Reviewed-by: Oswald Buddenhagen <oswald.buddenhagen@qt.io>

1 files changed, 100 insertions, 1 deletions

diff --git a/tests/auto/tools/qmake/testdata/rawString/main.cpp b/tests/auto/tools/qmake/testdata/rawString/main.cpp
index 53a28f7bc0..bc557f39f8 100644
--- a/tests/auto/tools/qmake/testdata/rawString/main.cpp
+++ b/tests/auto/tools/qmake/testdata/rawString/main.cpp
@@ -26,8 +26,107 @@
 **
 ****************************************************************************/
 
+// macro names that *aren't* string-literal-prefixes:
+#define Ru8 "rue-it"
+#define RL "real life"
+#define Ru "are you ?"
+#define RU "Are You ?"
+#define LLR "double-hockey-sticks"
+#define LUR "Tricky"
+#define LuR "tricky"
+#define Lu8R "l'uber"
+#define UUR "Double-Yew"
+#define ULR "Eweler"
+#define UuR "You ... you-are"
+#define Uu8R "You ... you *ate* our ..."
+#define uuR "water"
+#define uLR "eweler"
+#define uUR "double-Your"
+#define uu8R "totally uber"
+#define u8u8R "rubber-you"
+#define u8LR "Uber left-to-right"
+#define u8UR "Uber Upper-Right"
+#define u8uR "Uber upper-right"
+#define Ru8R "bouncy"
+#define RLR "Marching"
+#define RuR "Rossum's general-purpose workers"
+#define RUR "Rossum's Universal Robots"
+
+static const char monstrosity[] =
+    Ru8"Ru8("
+    RL"RL("
+    Ru"Ru("
+    RU"RU("
+    LLR"LLR("
+    LUR"LUR("
+    LuR"LuR("
+    Lu8R"Lu8R("
+    UUR"UUR("
+    ULR"ULR("
+    UuR"UuR("
+    Uu8R"Uu8R("
+    uuR"uuR("
+    uLR"uLR("
+    uUR"uUR("
+    uu8R"uu8R("
+    u8u8R"u8u8R("
+    u8LR"u8LR("
+    u8UR"u8UR("
+    u8uR"u8uR("
+    Ru8R"Ru8R("
+    RLR"RLR("
+    RuR"RuR("
+    RUR"RUR("
+    "Finally, some content";
+
+#include <moc_object2.cpp>
+
+static const char closure[] =
+    ")RUR"
+    ")RuR"
+    ")RLR"
+    ")Ru8R"
+    ")u8uR"
+    ")u8UR"
+    ")u8LR"
+    ")u8u8R"
+    ")uu8R"
+    ")uUR"
+    ")uLR"
+    ")uuR"
+    ")Uu8R"
+    ")UuR"
+    ")ULR"
+    ")UUR"
+    ")Lu8R"
+    ")LuR"
+    ")LUR"
+    ")LLR"
+    ")RU"
+    ")Ru"
+    ")RL"
+    ")Ru8";
+// If moc got confused, the confusion should now be over
+
+// Real raw strings, not actually leaving us inside any comments:
 static const char raw[] = R"blah(lorem " ipsum /*)blah"\
 ;
+static const wchar_t wider[] = LR"blah(lorem " ipsum /*)blah"\
+;
+static const char32_t UCS4[] = UR"blah(lorem " ipsum /*)blah"\
+;
+static const char16_t UCS2[] = uR"blah(lorem " ipsum /*)blah"\
+;
+static const char utf8[] = u8R"blah(lorem " ipsum /*)blah"\
+;
 #include <moc_object1.cpp>
 
-int main () { return 0; }
+/* Avoid unused variable warnings by silly uses of arrays: */
+#define final(x) x[sizeof(x) - 1] // 0, of course
+int main () {
+    return final(raw)
+    * (final(wider) - final(UCS4))
+    * (final(UCS2) - final(utf8))
+    * (final(monstrosity) - final(closure));
+}
+#undef final