[libcxx] Fix the ctype is (pointer version) function for Windows

Previously, this test snippet would report incorrect information:

    F::mask m;
    std::wstring in(L"\u00DA"); // LATIN CAPITAL LETTER U WITH ACUTE
    f.is(in.data(), in.data() + 1, &m);
    // m & F::lower would be set

The single-character version of the `is` function wasn't
affected by this issue though.

Define `_LIBCPP_CTYPE_MASK_IS_COMPOSITE_ALPHA` for Windows,
as the `alpha` / `_ALPHA` constant is a mask consisting of
multiple bits set, which avoids setting `alpha` whenver any
of the bits is set, in the `do_is` implementation.

On Windows, with the "C" locale, wchars are classified according
to their Unicode interpretation, just as in the en_US.UTF-8 locale on
all platforms.

Due to the differing classification of some characters, the
`scan_is` and `scan_not` tests are quite annoying to fix, thus just
ifdef out some of the tests for the "C" locale there - the code gets
tested with the more standard en_US.UTF-8 locale anyway.

Differential Revision: https://reviews.llvm.org/D120796

Author: mstorsjo

libcxx/include/__locale

@@ -454,6 +454,7 @@ public:
     static const mask blank  = _BLANK;
     static const mask __regex_word = 0x4000; // 0x8000 and 0x0100 and 0x00ff are used
 # define _LIBCPP_CTYPE_MASK_IS_COMPOSITE_PRINT
+# define _LIBCPP_CTYPE_MASK_IS_COMPOSITE_ALPHA
 #elif defined(__APPLE__) || defined(__FreeBSD__) || defined(__EMSCRIPTEN__) || defined(__NetBSD__)
 # ifdef __APPLE__
     typedef __uint32_t mask;

libcxx/test/std/localization/locale.categories/category.ctype/locale.ctype.byname/is_1.pass.cpp

@@ -13,7 +13,6 @@
 // bool is(mask m, charT c) const;
 
 // REQUIRES: locale.en_US.UTF-8
-// XFAIL: LIBCXX-WINDOWS-FIXME
 // XFAIL: libcpp-has-no-wide-characters
 
 #include <locale>
@@ -107,8 +106,15 @@ int main(int, char**)
             assert(f.is(F::graph, L'.'));
             assert(!f.is(F::graph,  L'\x07'));
 
+#if defined(_WIN32)
+            // On Windows, these wchars are classified according to their
+            // Unicode interpretation even in the "C" locale.
+            assert(f.is(F::alpha, L'\x00DA'));
+            assert(f.is(F::upper, L'\x00DA'));
+#else
             assert(!f.is(F::alpha, L'\x00DA'));
             assert(!f.is(F::upper, L'\x00DA'));
+#endif
         }
     }
 

libcxx/test/std/localization/locale.categories/category.ctype/locale.ctype.byname/is_many.pass.cpp

@@ -13,7 +13,6 @@
 // const charT* do_is(const charT* low, const charT* high, mask* vec) const;
 
 // REQUIRES: locale.en_US.UTF-8
-// XFAIL: LIBCXX-WINDOWS-FIXME
 // XFAIL: libcpp-has-no-wide-characters
 
 #include <locale>
@@ -149,17 +148,27 @@ int main(int, char**)
 
             // L'\x00DA'
             assert(!(m[0] & F::space));
-            assert(!(m[0] & F::print));
             assert(!(m[0] & F::cntrl));
-            assert(!(m[0] & F::upper));
             assert(!(m[0] & F::lower));
-            assert(!(m[0] & F::alpha));
             assert(!(m[0] & F::digit));
             assert(!(m[0] & F::punct));
             assert(!(m[0] & F::xdigit));
             assert(!(m[0] & F::blank));
+#if defined(_WIN32)
+            // On Windows, these wchars are classified according to their
+            // Unicode interpretation even in the "C" locale.
+            assert( (m[0] & F::alpha));
+            assert( (m[0] & F::upper));
+            assert( (m[0] & F::print));
+            assert( (m[0] & F::alnum));
+            assert( (m[0] & F::graph));
+#else
+            assert(!(m[0] & F::alpha));
+            assert(!(m[0] & F::upper));
+            assert(!(m[0] & F::print));
             assert(!(m[0] & F::alnum));
             assert(!(m[0] & F::graph));
+#endif
 
             // L' '
             assert( (m[1] & F::space));

libcxx/test/std/localization/locale.categories/category.ctype/locale.ctype.byname/scan_is.pass.cpp

@@ -13,7 +13,6 @@
 // const charT* scan_is(mask m, const charT* low, const charT* high) const;
 
 // REQUIRES: locale.en_US.UTF-8
-// XFAIL: LIBCXX-WINDOWS-FIXME
 // XFAIL: libcpp-has-no-wide-characters
 
 #include <locale>
@@ -57,17 +56,23 @@ int main(int, char**)
             const std::wstring in(L"\x00DA A\x07.a1");
             std::vector<F::mask> m(in.size());
             assert(f.scan_is(F::space, in.data(), in.data() + in.size()) - in.data() == 1);
-            assert(f.scan_is(F::print, in.data(), in.data() + in.size()) - in.data() == 1);
             assert(f.scan_is(F::cntrl, in.data(), in.data() + in.size()) - in.data() == 3);
-            assert(f.scan_is(F::upper, in.data(), in.data() + in.size()) - in.data() == 2);
             assert(f.scan_is(F::lower, in.data(), in.data() + in.size()) - in.data() == 5);
-            assert(f.scan_is(F::alpha, in.data(), in.data() + in.size()) - in.data() == 2);
             assert(f.scan_is(F::digit, in.data(), in.data() + in.size()) - in.data() == 6);
             assert(f.scan_is(F::punct, in.data(), in.data() + in.size()) - in.data() == 4);
             assert(f.scan_is(F::xdigit, in.data(), in.data() + in.size()) - in.data() == 2);
             assert(f.scan_is(F::blank, in.data(), in.data() + in.size()) - in.data() == 1);
+#if !defined(_WIN32)
+            // On Windows, these wchars are classified according to their
+            // Unicode interpretation even in the "C" locale, where
+            // the scan_is function returns the same as above for the
+            // en_US.UTF-8 locale.
+            assert(f.scan_is(F::print, in.data(), in.data() + in.size()) - in.data() == 1);
+            assert(f.scan_is(F::upper, in.data(), in.data() + in.size()) - in.data() == 2);
+            assert(f.scan_is(F::alpha, in.data(), in.data() + in.size()) - in.data() == 2);
             assert(f.scan_is(F::alnum, in.data(), in.data() + in.size()) - in.data() == 2);
             assert(f.scan_is(F::graph, in.data(), in.data() + in.size()) - in.data() == 2);
+#endif
         }
     }
 

libcxx/test/std/localization/locale.categories/category.ctype/locale.ctype.byname/scan_not.pass.cpp

@@ -13,7 +13,6 @@
 // const charT* scan_not(mask m, const charT* low, const charT* high) const;
 
 // REQUIRES: locale.en_US.UTF-8
-// XFAIL: LIBCXX-WINDOWS-FIXME
 // XFAIL: libcpp-has-no-wide-characters
 
 #include <locale>
@@ -57,17 +56,23 @@ int main(int, char**)
             const std::wstring in(L"\x00DA A\x07.a1");
             std::vector<F::mask> m(in.size());
             assert(f.scan_not(F::space, in.data(), in.data() + in.size()) - in.data() == 0);
-            assert(f.scan_not(F::print, in.data(), in.data() + in.size()) - in.data() == 0);
             assert(f.scan_not(F::cntrl, in.data(), in.data() + in.size()) - in.data() == 0);
-            assert(f.scan_not(F::upper, in.data(), in.data() + in.size()) - in.data() == 0);
             assert(f.scan_not(F::lower, in.data(), in.data() + in.size()) - in.data() == 0);
-            assert(f.scan_not(F::alpha, in.data(), in.data() + in.size()) - in.data() == 0);
             assert(f.scan_not(F::digit, in.data(), in.data() + in.size()) - in.data() == 0);
             assert(f.scan_not(F::punct, in.data(), in.data() + in.size()) - in.data() == 0);
             assert(f.scan_not(F::xdigit, in.data(), in.data() + in.size()) - in.data() == 0);
             assert(f.scan_not(F::blank, in.data(), in.data() + in.size()) - in.data() == 0);
+#if !defined(_WIN32)
+            // On Windows, these wchars are classified according to their
+            // Unicode interpretation even in the "C" locale, where
+            // the scan_is function returns the same as above for the
+            // en_US.UTF-8 locale.
+            assert(f.scan_not(F::print, in.data(), in.data() + in.size()) - in.data() == 0);
+            assert(f.scan_not(F::upper, in.data(), in.data() + in.size()) - in.data() == 0);
+            assert(f.scan_not(F::alpha, in.data(), in.data() + in.size()) - in.data() == 0);
             assert(f.scan_not(F::alnum, in.data(), in.data() + in.size()) - in.data() == 0);
             assert(f.scan_not(F::graph, in.data(), in.data() + in.size()) - in.data() == 0);
+#endif
         }
     }