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>

4 files changed, 190 insertions, 9 deletions

diff --git a/qmake/generators/makefiledeps.cpp b/qmake/generators/makefiledeps.cpp
index 3140b045a1..c68eeb13d6 100644
--- a/qmake/generators/makefiledeps.cpp
+++ b/qmake/generators/makefiledeps.cpp
@@ -422,25 +422,53 @@ static bool matchWhileUnsplitting(const char *buffer, int buffer_len, int start,
 /* Advance from an opening quote at buffer[offset] to the matching close quote. */
 static int scanPastString(char *buffer, int buffer_len, int offset, int *lines)
 {
+    // http://en.cppreference.com/w/cpp/language/string_literal
     // It might be a C++11 raw string.
     bool israw = false;
     if (buffer[offset] == '"' && offset > 0) {
         int explore = offset - 1;
-        while (explore > 0 && buffer[explore] != 'R') {
-            if (buffer[explore] == '8' || buffer[explore] == 'u' || buffer[explore] == 'U') {
-                explore--;
-            } else if (explore > 1 && qmake_endOfLine(buffer[explore])
-                       && buffer[explore - 1] == '\\') {
+        bool prefix = false; // One of L, U, u or u8 may appear before R
+        bool saw8 = false; // Partial scan of u8
+        while (explore >= 0) {
+            // Cope with backslash-newline interruptions of the prefix:
+            if (explore > 0
+                && qmake_endOfLine(buffer[explore])
+                && buffer[explore - 1] == '\\') {
                 explore -= 2;
-            } else if (explore > 2 && buffer[explore] == '\n'
+            } else if (explore > 1
+                       && buffer[explore] == '\n'
                        && buffer[explore - 1] == '\r'
                        && buffer[explore - 2] == '\\') {
                 explore -= 3;
+                // Remaining cases can only decrement explore by one at a time:
+            } else if (saw8 && buffer[explore] == 'u') {
+                explore--;
+                saw8 = false;
+                prefix = true;
+            } else if (saw8 || prefix) {
+                break;
+            } else if (explore > 1 && buffer[explore] == '8') {
+                explore--;
+                saw8 = true;
+            } else if (buffer[explore] == 'L'
+                       || buffer[explore] == 'U'
+                       || buffer[explore] == 'u') {
+                explore--;
+                prefix = true;
+            } else if (buffer[explore] == 'R') {
+                if (israw)
+                    break;
+                explore--;
+                israw = true;
             } else {
                 break;
             }
         }
-        israw = (buffer[explore] == 'R');
+        // Check the R (with possible prefix) isn't just part of an identifier:
+        if (israw && explore >= 0
+            && (isalnum(buffer[explore]) || buffer[explore] == '_')) {
+            israw = false;
+        }
     }
 
     if (israw) {
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
diff --git a/tests/auto/tools/qmake/testdata/rawString/object2.h b/tests/auto/tools/qmake/testdata/rawString/object2.h
new file mode 100644
index 0000000000..2ab77cd3bd
--- /dev/null
+++ b/tests/auto/tools/qmake/testdata/rawString/object2.h
@@ -0,0 +1,54 @@
+/****************************************************************************
+**
+** Copyright (C) 2015 The Qt Company Ltd.
+** Contact: http://www.qt.io/licensing/
+**
+** This file is part of the test suite of the Qt Toolkit.
+**
+** $QT_BEGIN_LICENSE:LGPL21$
+** Commercial License Usage
+** Licensees holding valid commercial Qt licenses may use this file in
+** accordance with the commercial license agreement provided with the
+** Software or, alternatively, in accordance with the terms contained in
+** a written agreement between you and The Qt Company. For licensing terms
+** and conditions see http://www.qt.io/terms-conditions. For further
+** information use the contact form at http://www.qt.io/contact-us.
+**
+** GNU Lesser General Public License Usage
+** Alternatively, this file may be used under the terms of the GNU Lesser
+** General Public License version 2.1 or version 3 as published by the Free
+** Software Foundation and appearing in the file LICENSE.LGPLv21 and
+** LICENSE.LGPLv3 included in the packaging of this file. Please review the
+** following information to ensure the GNU Lesser General Public License
+** requirements will be met: https://www.gnu.org/licenses/lgpl.html and
+** http://www.gnu.org/licenses/old-licenses/lgpl-2.1.html.
+**
+** As a special exception, The Qt Company gives you certain additional
+** rights. These rights are described in The Qt Company LGPL Exception
+** version 1.1, included in the file LGPL_EXCEPTION.txt in this package.
+**
+** $QT_END_LICENSE$
+**
+****************************************************************************/
+#ifndef TEST_QMAKE_RAWSTRING_OBJECT2_H
+#define TEST_QMAKE_RAWSTRING_OBJECT2_H
+
+#define Lu8UR "land"
+inline char opener(int i) {
+    const char text[] = Lu8UR"blah( not a raw string; just juxtaposed";
+    return text[i];
+}
+
+#include <QObject>
+
+class Object2 : public QObject
+{
+    Q_OBJECT
+};
+
+inline char closer(int i) {
+    const char text[] = "pretend to close it, all the same )blah";
+    return text[i];
+}
+
+#endif // TEST_QMAKE_RAWSTRING_OBJECT2_H
diff --git a/tests/auto/tools/qmake/testdata/rawString/rawString.pro b/tests/auto/tools/qmake/testdata/rawString/rawString.pro
index d2d8132ceb..19c81dfe97 100644
--- a/tests/auto/tools/qmake/testdata/rawString/rawString.pro
+++ b/tests/auto/tools/qmake/testdata/rawString/rawString.pro
@@ -1,4 +1,4 @@
 DESTDIR = ./
 
-HEADERS += object1.h
+HEADERS += object1.h object2.h
 SOURCES += main.cpp