Add string_set buildfile value type

This exposes the std::set<std::string> type to buildfiles.

New functions:

  $size(<string-set>)

Subscript returns true if the value is present and false otherwise (so
it is mapped to std::set::contains()). For example:

set = [string_set] a b c

if ($set[b])
  ...

Note that append (+=) and prepend (=+) have the same semantics
(std::set::insert()). For example:

set = [string_set] a b
set += c b              # a b c
set =+ d b              # a b c d

Example of iteration:

set = [string_set] a b c
for k: $set
  ...

9 files changed, 348 insertions, 3 deletions

diff --git a/libbuild2/functions-string.cxx b/libbuild2/functions-string.cxx
index b332efa..367923f 100644
--- a/libbuild2/functions-string.cxx
+++ b/libbuild2/functions-string.cxx
@@ -119,14 +119,16 @@ namespace build2
     };
 
     // $size(<strings>)
+    // $size(<string-set>)
     // $size(<string-map>)
     // $size(<string>)
     //
-    // First two forms: return the number of elements in the sequence.
+    // First three forms: return the number of elements in the sequence.
     //
-    // Third form: return the number of characters (bytes) in the string.
+    // Fourth form: return the number of characters (bytes) in the string.
     //
     f["size"] += [] (strings v)             {return v.size ();};
+    f["size"] += [] (set<string> v)         {return v.size ();};
     f["size"] += [] (map<string, string> v) {return v.size ();};
     f["size"] += [] (string v)              {return v.size ();};
 
diff --git a/libbuild2/parser.cxx b/libbuild2/parser.cxx
index b68f009..bf806be 100644
--- a/libbuild2/parser.cxx
+++ b/libbuild2/parser.cxx
@@ -6101,6 +6101,7 @@ namespace build2
           if (n[6] == '\0') return &value_traits<string>::value_type;
           if (n[6] == 's' &&
               n[7] == '\0') return &value_traits<strings>::value_type;
+          if (n == "string_set") return &value_traits<set<string>>::value_type;
           if (n == "string_map")
             return &value_traits<map<string,string>>::value_type;
         }
diff --git a/libbuild2/variable.cxx b/libbuild2/variable.cxx
index 40eeccd..6f9f0fb 100644
--- a/libbuild2/variable.cxx
+++ b/libbuild2/variable.cxx
@@ -3292,6 +3292,8 @@ namespace build2
   template struct LIBBUILD2_DEFEXPORT
   value_traits<vector<pair<string, optional<bool>>>>;
 
+  template struct LIBBUILD2_DEFEXPORT value_traits<set<string>>;
+
   template struct LIBBUILD2_DEFEXPORT
   value_traits<map<string, string>>;
 
diff --git a/libbuild2/variable.hxx b/libbuild2/variable.hxx
index d67098e..b157806 100644
--- a/libbuild2/variable.hxx
+++ b/libbuild2/variable.hxx
@@ -1177,6 +1177,26 @@ namespace build2
     static const pair_vector_value_type<K, V> value_type;
   };
 
+  // set<T>
+  //
+  template <typename T>
+  struct set_value_type;
+
+  template <typename T>
+  struct value_traits<set<T>>
+  {
+    static_assert (sizeof (set<T>) <= value::size_, "insufficient space");
+
+    static set<T> convert (names&&);
+    static void assign (value&, set<T>&&);
+    static void append (value&, set<T>&&);
+    static void prepend (value&, set<T>&&);
+    static bool empty (const set<T>& x) {return x.empty ();}
+
+    static const set<T> empty_instance;
+    static const set_value_type<T> value_type;
+  };
+
   // map<K, V>
   //
   // Either K or V can be optional<T> making the key or value optional.
@@ -1321,6 +1341,8 @@ namespace build2
   extern template struct LIBBUILD2_DECEXPORT
   value_traits<vector<pair<string, optional<bool>>>>;
 
+  extern template struct LIBBUILD2_DECEXPORT value_traits<set<string>>;
+
   extern template struct LIBBUILD2_DECEXPORT
   value_traits<map<string, string>>;
 
diff --git a/libbuild2/variable.ixx b/libbuild2/variable.ixx
index b8f80e3..a448cd8 100644
--- a/libbuild2/variable.ixx
+++ b/libbuild2/variable.ixx
@@ -853,6 +853,44 @@ namespace build2
       new (&v.data_) vector<pair<K, V>> (move (x));
   }
 
+  // set<T> value
+  //
+  template <typename T>
+  inline void value_traits<set<T>>::
+  assign (value& v, set<T>&& x)
+  {
+    if (v)
+      v.as<set<T>> () = move (x);
+    else
+      new (&v.data_) set<T> (move (x));
+  }
+
+  template <typename T>
+  inline void value_traits<set<T>>::
+  append (value& v, set<T>&& x)
+  {
+    if (v)
+    {
+      set<T>& p (v.as<set<T>> ());
+
+      if (p.empty ())
+        p.swap (x);
+      else
+        // Keys (being const) can only be copied.
+        //
+        p.insert (x.begin (), x.end ());
+    }
+    else
+      new (&v.data_) set<T> (move (x));
+  }
+
+  template <typename T>
+  inline void value_traits<set<T>>::
+  prepend (value& v, set<T>&& x)
+  {
+    append (v, move (x));
+  }
+
   // map<K, V> value
   //
   template <typename K, typename V>
diff --git a/libbuild2/variable.txx b/libbuild2/variable.txx
index 485f9dc..501e103 100644
--- a/libbuild2/variable.txx
+++ b/libbuild2/variable.txx
@@ -479,6 +479,7 @@ namespace build2
   convert (names&& ns)
   {
     vector<T> v;
+    v.reserve (ns.size ()); // Normally there won't be any pairs.
 
     // Similar to vector_append() below except we throw instead of issuing
     // diagnostics.
@@ -511,6 +512,8 @@ namespace build2
                   ? v.as<vector<T>> ()
                   : *new (&v.data_) vector<T> ());
 
+    p.reserve (p.size () + ns.size ()); // Normally there won't be any pairs.
+
     // Convert each element to T while merging pairs.
     //
     for (auto i (ns.begin ()); i != ns.end (); ++i)
@@ -834,6 +837,226 @@ namespace build2
     nullptr                      // Iterate.
   };
 
+  // set<T> value
+  //
+  template <typename T>
+  set<T> value_traits<set<T>>::
+  convert (names&& ns)
+  {
+    set<T> s;
+
+    // Similar to set_append() below except we throw instead of issuing
+    // diagnostics.
+    //
+    for (auto i (ns.begin ()); i != ns.end (); ++i)
+    {
+      name& n (*i);
+      name* r (nullptr);
+
+      if (n.pair)
+      {
+        r = &*++i;
+
+        if (n.pair != '@')
+          throw invalid_argument (
+            string ("invalid pair character: '") + n.pair + '\'');
+      }
+
+      s.insert (value_traits<T>::convert (move (n), r));
+    }
+
+    return s;
+  }
+
+  template <typename T>
+  void
+  set_append (value& v, names&& ns, const variable* var)
+  {
+    set<T>& s (v ? v.as<set<T>> () : *new (&v.data_) set<T> ());
+
+    // Convert each element to T while merging pairs.
+    //
+    for (auto i (ns.begin ()); i != ns.end (); ++i)
+    {
+      name& n (*i);
+      name* r (nullptr);
+
+      if (n.pair)
+      {
+        r = &*++i;
+
+        if (n.pair != '@')
+        {
+          diag_record dr (fail);
+
+          dr << "unexpected pair style for "
+             << value_traits<T>::value_type.name << " value "
+             << "'" << n << "'" << n.pair << "'" << *r << "'";
+
+          if (var != nullptr)
+            dr << " in variable " << var->name;
+        }
+      }
+
+      try
+      {
+        s.insert (value_traits<T>::convert (move (n), r));
+      }
+      catch (const invalid_argument& e)
+      {
+        diag_record dr (fail);
+
+        dr << e;
+        if (var != nullptr)
+          dr << " in variable " << var->name;
+
+        dr << info << "while converting ";
+        if (n.pair)
+          dr << " element pair '" << n << "'@'" << *r << "'";
+        else
+          dr << " element '" << n << "'";
+      }
+    }
+  }
+
+  template <typename T>
+  void
+  set_assign (value& v, names&& ns, const variable* var)
+  {
+    if (v)
+      v.as<set<T>> ().clear ();
+
+    set_append<T> (v, move (ns), var);
+  }
+
+  template <typename T>
+  names_view
+  set_reverse (const value& v, names& s, bool)
+  {
+    auto& sv (v.as<set<T>> ());
+    s.reserve (sv.size ());
+
+    for (const T& x: sv)
+      s.push_back (value_traits<T>::reverse (x));
+
+    return s;
+  }
+
+  template <typename T>
+  int
+  set_compare (const value& l, const value& r)
+  {
+    auto& ls (l.as<set<T>> ());
+    auto& rs (r.as<set<T>> ());
+
+    auto li (ls.begin ()), le (ls.end ());
+    auto ri (rs.begin ()), re (rs.end ());
+
+    for (; li != le && ri != re; ++li, ++ri)
+      if (int r = value_traits<T>::compare (*li, *ri))
+        return r;
+
+    if (li == le && ri != re) // l shorter than r.
+      return -1;
+
+    if (ri == re && li != le) // r shorter than l.
+      return 1;
+
+    return 0;
+  }
+
+  // Map subscript to set::contains().
+  //
+  template <typename T>
+  value
+  set_subscript (const value& val, value*,
+                 value&& sub,
+                 const location& sloc,
+                 const location& bloc)
+  {
+    // Process subscript even if the value is null to make sure it is valid.
+    //
+    T k;
+    try
+    {
+      k = convert<T> (move (sub));
+    }
+    catch (const invalid_argument& e)
+    {
+      fail (sloc) << "invalid " << value_traits<set<T>>::value_type.name
+                  << " value subscript: " << e <<
+        info (bloc) << "use the '\\[' escape sequence if this is a "
+                    << "wildcard pattern";
+    }
+
+    bool r (false);
+    if (!val.null)
+    {
+      const auto& s (val.as<set<T>> ());
+      r = s.find (k) != s.end ();
+    }
+
+    return value (r);
+  }
+
+  // Make sure these are static-initialized together. Failed that VC will make
+  // sure it's done in the wrong order.
+  //
+  template <typename T>
+  struct set_value_type: value_type
+  {
+    string type_name;
+
+    set_value_type (value_type&& v)
+        : value_type (move (v))
+    {
+      // set<T>
+      //
+      type_name  = "set<";
+      type_name += value_traits<T>::type_name;
+      type_name += '>';
+      name = type_name.c_str ();
+    }
+  };
+
+  // Convenience aliases for certain set<T> cases.
+  //
+  template <>
+  struct set_value_type<string>: value_type
+  {
+    set_value_type (value_type&& v)
+        : value_type (move (v))
+    {
+      name = "string_set";
+    }
+  };
+
+  template <typename T>
+  const set<T> value_traits<set<T>>::empty_instance;
+
+  template <typename T>
+  const set_value_type<T>
+  value_traits<set<T>>::value_type = build2::value_type // VC14 wants =.
+  {
+    nullptr,                          // Patched above.
+    sizeof (set<T>),
+    nullptr,                          // No base.
+    true,                             // Container.
+    &value_traits<T>::value_type,     // Element type.
+    &default_dtor<set<T>>,
+    &default_copy_ctor<set<T>>,
+    &default_copy_assign<set<T>>,
+    &set_assign<T>,
+    &set_append<T>,
+    &set_append<T>,                   // Prepend the same as append.
+    &set_reverse<T>,
+    nullptr,                          // No cast (cast data_ directly).
+    &set_compare<T>,
+    &default_empty<set<T>>,
+    &set_subscript<T>,
+    nullptr                           // Iterate.
+  };
+
   // map<K, V> value
   //
   template <typename K, typename V>
diff --git a/tests/function/string/testscript b/tests/function/string/testscript
index a363cc3..96f5c52 100644
--- a/tests/function/string/testscript
+++ b/tests/function/string/testscript
@@ -46,7 +46,8 @@
   $* <'print $size([string] abc)'             >'3' : basics
   $* <'print $size([string] )'                >'0' : zero
   $* <'print $size([strings] a b c)'          >'3' : strings
-  $* <'print $size([string_map] a@1 b@2 c@3)' >'3' : string_map
+  $* <'print $size([string_set] a b b)'       >'2' : string-set
+  $* <'print $size([string_map] a@1 b@2 b@3)' >'2' : string-map
 }
 
 : find
diff --git a/tests/type/set/buildfile b/tests/type/set/buildfile
new file mode 100644
index 0000000..55b37bb
--- /dev/null
+++ b/tests/type/set/buildfile
@@ -0,0 +1,4 @@
+# file      : tests/type/set/buildfile
+# license   : MIT; see accompanying LICENSE file
+
+./: testscript $b
diff --git a/tests/type/set/testscript b/tests/type/set/testscript
new file mode 100644
index 0000000..3897220
--- /dev/null
+++ b/tests/type/set/testscript
@@ -0,0 +1,52 @@
+# file      : tests/type/set/testscript
+# license   : MIT; see accompanying LICENSE file
+
+# See also tests in function/*/ (size()).
+
+.include ../../common.testscript
+
+: basics
+:
+$* <<EOI >>EOO
+s = [string_set] a b a
+print $s
+s += c b
+print $s
+s =+ d b
+print $s
+EOI
+a b
+a b c
+a b c d
+EOO
+
+: type
+:
+$* <<EOI >>EOO
+s = [string_set]
+print $type($s)
+EOI
+string_set
+EOO
+
+: subscript
+:
+$* <<EOI >>EOO
+s = [string_set] a b c
+print ($s[b])
+print ($s[z])
+EOI
+true
+false
+EOO
+
+: iteration
+:
+$* <<EOI >>EOO
+for s: [string_set] a b c
+  print $s
+EOI
+a
+b
+c
+EOO