From 677eb1e1017630a1d1abbb528d28b90110990ef4 Mon Sep 17 00:00:00 2001
From: Boris Kolpackov <boris@codesynthesis.com>
Date: Mon, 22 Jan 2024 12:02:41 +0200
Subject: Initial take

---
 libbuild2/json.cxx     | 169 ++++++++++++++++++++++++++++
 libbuild2/json.hxx     | 233 +++++++++++++++++++++++++++++++++++++++
 libbuild2/variable.cxx | 293 ++++++++++++++++++++++++++++++++++++++++++++++++-
 libbuild2/variable.hxx |  20 ++++
 libbuild2/variable.ixx |  22 ++++
 5 files changed, 736 insertions(+), 1 deletion(-)
 create mode 100644 libbuild2/json.cxx
 create mode 100644 libbuild2/json.hxx

diff --git a/libbuild2/json.cxx b/libbuild2/json.cxx
new file mode 100644
index 0000000..0fee8af
--- /dev/null
+++ b/libbuild2/json.cxx
@@ -0,0 +1,169 @@
+// file      : libbuild2/json.cxx -*- C++ -*-
+// license   : MIT; see accompanying LICENSE file
+
+#include <libbuild2/json.hxx>
+
+#ifndef BUILD2_BOOTSTRAP
+#  include <libbutl/json/parser.hxx>
+#  include <libbutl/json/serializer.hxx>
+#endif
+
+using namespace butl::json;
+
+namespace build2
+{
+#ifndef BUILD2_BOOTSTRAP
+  json_value::
+  json_value (parser& p)
+  {
+    // A JSON input text cannot be empty.
+    //
+    event e (*p.next ());
+
+    switch (e)
+    {
+    case event::begin_object:
+      {
+        container_type c; // For exception safety.
+        while (*p.next () != event::end_object)
+        {
+          string_type n (p.name ());
+          json_value v (p);
+          v.name = move (n);
+          c.push_back (move (v));
+        }
+
+        new (&container) container_type (move (c));
+        type = json_type::object;
+        break;
+      }
+    case event::begin_array:
+      {
+        container_type c; // For exception safety.
+        while (*p.peek () != event::end_array)
+          c.push_back (json_value (p));
+        p.next (); // Consume end_array.
+
+        new (&container) container_type (move (c));
+        type = json_type::array;
+        break;
+      }
+    case event::string:
+      {
+        string_type& s (p.value ());
+
+        // Don't move if small string optimized.
+        //
+        if (s.size () > 15)
+          new (&string) string_type (move (s));
+        else
+          new (&string) string_type (s);
+
+        type = json_type::string;
+        break;
+      }
+    case event::number:
+      {
+        string_type& s (p.value ());
+
+        if (s[0] == '-')
+        {
+          signed_number = p.value<int64_t> ();
+          type = json_type::signed_number;
+        }
+        else
+        {
+          unsigned_number = p.value<uint64_t> ();
+          type = json_type::unsigned_number;
+        }
+
+        break;
+      }
+    case event::boolean:
+      {
+        boolean = p.value<bool> ();
+        type = json_type::boolean;
+        break;
+      }
+    case event::null:
+      {
+        type = json_type::null;
+        break;
+      }
+    case event::name:
+    case event::end_array:
+    case event::end_object:
+      {
+        assert (false);
+        type = json_type::null;
+        break;
+      }
+    }
+  }
+
+  void
+  serialize (buffer_serializer& s, const json_value& v)
+  {
+    if (v.name)
+      s.member_name (*v.name);
+
+    switch (v.type)
+    {
+    case json_type::null:
+      {
+        s.value (nullptr);
+        break;
+      }
+    case json_type::boolean:
+      {
+        s.value (v.boolean);
+        break;
+      }
+    case json_type::signed_number:
+      {
+        s.value (v.signed_number);
+        break;
+      }
+    case json_type::unsigned_number:
+      {
+        s.value (v.unsigned_number);
+        break;
+      }
+    case json_type::string:
+      {
+        s.value (v.string);
+        break;
+      }
+    case json_type::array:
+      {
+        s.begin_array ();
+        for (const json_value& e: v.container)
+          serialize (s, e);
+        s.end_array ();
+        break;
+      }
+    case json_type::object:
+      {
+        s.begin_object ();
+        for (const json_value& m: v.container)
+          serialize (s, m);
+        s.end_object ();
+        break;
+      }
+    }
+  }
+#else
+  json_value::
+  json_value (parser&)
+  {
+    assert (false);
+    type = json_type::null;
+  }
+
+  void
+  serialize (buffer_serializer&, const json_value&)
+  {
+    assert (false);
+  }
+#endif
+}
diff --git a/libbuild2/json.hxx b/libbuild2/json.hxx
new file mode 100644
index 0000000..816b55c
--- /dev/null
+++ b/libbuild2/json.hxx
@@ -0,0 +1,233 @@
+// file      : libbuild2/json.hxx -*- C++ -*-
+// license   : MIT; see accompanying LICENSE file
+
+#ifndef LIBBUILD2_JSON_HXX
+#define LIBBUILD2_JSON_HXX
+
+#include <libbuild2/types.hxx>
+#include <libbuild2/utility.hxx>
+
+#include <libbuild2/export.hxx>
+
+namespace butl
+{
+  namespace json
+  {
+    class parser;
+    class buffer_serializer;
+  }
+}
+
+namespace build2
+{
+  // This JSON representation has two extensions compared to the standard JSON
+  // model: it distinguishes between signed and unsigned numbers and
+  // represents an object member as a JSON value rather than, say, a pair of a
+  // string and value. The latter allows us to use the JSON value itself as an
+  // element of a container.
+  //
+  enum class json_type
+  {
+    null,
+    boolean,
+    signed_number,
+    unsigned_number,
+    string,
+    array,
+    object,
+  };
+
+  class LIBBUILD2_SYMEXPORT json_value
+  {
+  public:
+    using string_type = build2::string;
+    using container_type = vector<json_value>;
+
+    json_type type;
+
+    optional<string_type> name; // If present, then this is a member with value.
+
+    union
+    {
+      bool           boolean;
+      int64_t        signed_number;
+      uint64_t       unsigned_number;
+      string_type    string;
+      container_type container; // arrary and object
+    };
+
+    // Throws invalid_json_input.
+    //
+    explicit
+    json_value (butl::json::parser&);
+
+    explicit
+    json_value (json_type t = json_type::null)
+        : type (t)
+    {
+      switch (type)
+      {
+      case json_type::null:                                          break;
+      case json_type::boolean:         boolean = false;              break;
+      case json_type::signed_number:   signed_number = 0;            break;
+      case json_type::unsigned_number: unsigned_number = 0;          break;
+      case json_type::string:          new (&string) string_type (); break;
+      case json_type::array:
+      case json_type::object:          new (&container) container_type (); break;
+      }
+    }
+
+    json_value (string_type member_name, json_type t)
+        : json_value (t) {name = move (member_name);}
+
+    explicit
+    json_value (std::nullptr_t)
+        : type (json_type::null) {}
+
+    json_value (string_type member_name, std::nullptr_t v)
+        : json_value (v) {name = move (member_name);}
+
+    explicit
+    json_value (bool v)
+        : type (json_type::boolean), boolean (v) {}
+
+    json_value (string_type member_name, bool v)
+        : json_value (v) {name = move (member_name);}
+
+    explicit
+    json_value (int64_t v)
+        : type (json_type::signed_number), signed_number (v) {}
+
+    json_value (string_type member_name, int64_t v)
+        : json_value (v) {name = move (member_name);}
+
+    explicit
+    json_value (uint64_t v)
+        : type (json_type::unsigned_number), unsigned_number (v) {}
+
+    json_value (string_type member_name, uint64_t v)
+        : json_value (v) {name = move (member_name);}
+
+    explicit
+    json_value (string_type v)
+        : type (json_type::string), string (move (v)) {}
+
+    json_value (string_type member_name, string_type v)
+        : json_value (move (v)) {name = move (member_name);}
+
+    explicit
+    json_value (container_type v, json_type t)
+        : type (t), container (move (v))
+    {
+#ifndef NDEBUG
+      assert (t == json_type::array || t == json_type::object);
+
+      for (const json_value& e: container)
+        assert (e.name.has_value () == (t == json_type::object));
+#endif
+    }
+
+    json_value (string_type member_name, container_type v, json_type t)
+        : json_value (move (v), t) {name = move (member_name);}
+
+    // Note that the moved-from value becomes null.
+    //
+    json_value (json_value&& v) noexcept
+      : type (v.type), name (move (v.name))
+    {
+      switch (type)
+      {
+      case json_type::null:
+        break;
+      case json_type::boolean:
+        boolean = v.boolean;
+        break;
+      case json_type::signed_number:
+        signed_number = v.signed_number;
+        break;
+      case json_type::unsigned_number:
+        unsigned_number = v.unsigned_number;
+        break;
+      case json_type::string:
+        new (&string) string_type (move (v.string));
+        v.string.~string_type ();
+        break;
+      case json_type::array:
+      case json_type::object:
+        new (&container) container_type (move (v.container));
+        v.container.~container_type ();
+        break;
+      }
+
+      v.type = json_type::null;
+      v.name = nullopt;
+    }
+
+    json_value& operator= (json_value&& v) noexcept
+    {
+      if (this != &v)
+      {
+        this->~json_value ();
+        new (this) json_value (move (v));
+      }
+      return *this;
+    }
+
+    json_value (const json_value& v)
+        : type (v.type), name (v.name)
+    {
+      switch (type)
+      {
+      case json_type::null:
+        break;
+      case json_type::boolean:
+        boolean = v.boolean;
+        break;
+      case json_type::signed_number:
+        signed_number = v.signed_number;
+        break;
+      case json_type::unsigned_number:
+        unsigned_number = v.unsigned_number;
+        break;
+      case json_type::string:
+        new (&string) string_type (v.string);
+        break;
+      case json_type::array:
+      case json_type::object:
+        new (&container) container_type (v.container);
+        break;
+      }
+    }
+
+    json_value& operator= (const json_value& v)
+    {
+      if (this != &v)
+      {
+        this->~json_value ();
+        new (this) json_value (v);
+      }
+      return *this;
+    }
+
+    ~json_value () noexcept
+    {
+      switch (type)
+      {
+      case json_type::null:
+      case json_type::boolean:
+      case json_type::signed_number:
+      case json_type::unsigned_number:                               break;
+      case json_type::string:          string.~string_type ();       break;
+      case json_type::array:
+      case json_type::object:          container.~container_type (); break;
+      }
+    }
+  };
+
+  // Throws invalid_json_output.
+  //
+  LIBBUILD2_SYMEXPORT void
+  serialize (butl::json::buffer_serializer&, const json_value&);
+}
+
+#endif // LIBBUILD2_JSON_HXX
diff --git a/libbuild2/variable.cxx b/libbuild2/variable.cxx
index 392c9bb..62da025 100644
--- a/libbuild2/variable.cxx
+++ b/libbuild2/variable.cxx
@@ -7,6 +7,11 @@
 
 #include <libbutl/path-pattern.hxx>
 
+#ifndef BUILD2_BOOTSTRAP
+#  include <libbutl/json/parser.hxx>
+#  include <libbutl/json/serializer.hxx>
+#endif
+
 #include <libbuild2/target.hxx>
 #include <libbuild2/diagnostics.hxx>
 
@@ -460,7 +465,7 @@ namespace build2
         m += "name '" + to_string (n) + '\'';
     }
 
-    throw invalid_argument (m);
+    throw invalid_argument (move (m));
   }
 
   // names
@@ -1475,6 +1480,292 @@ namespace build2
     &default_empty<project_name>
   };
 
+  // json
+  //
+  json_value value_traits<json_value>::
+  convert (names&& ns)
+  {
+    auto to_string_value = [] (name& n, const char* what) -> string
+    {
+      if (n.typed () || n.qualified () || n.pattern)
+        throw_invalid_argument (n, nullptr, what);
+
+      string s;
+
+      if (n.simple ())
+        s.swap (n.value);
+      else
+      {
+        // Note that here we cannot assume what's in dir is really a path
+        // (think s/foo/bar/) so we have to reverse it exactly.
+        //
+        s = move (n.dir).representation (); // Move out of path.
+
+        if (!n.value.empty ())
+          s += n.value; // Separator is already there.
+      }
+
+      return s;
+    };
+
+    auto to_json_value = [] (name& n, const char* what) -> json_value
+    {
+      if (n.typed () || n.qualified () || n.pattern)
+        throw_invalid_argument (n, nullptr, what);
+
+      string s;
+
+      if (n.simple ())
+        s.swap (n.value);
+      else
+      {
+        // Note that here we cannot assume what's in dir is really a path
+        // (think s/foo/bar/) so we have to reverse it exactly.
+        //
+        s = move (n.dir).representation (); // Move out of path.
+
+        if (!n.value.empty ())
+          s += n.value; // Separator is already there.
+
+        // A path is always interpreted as a JSON string.
+        //
+        return json_value (move (s));
+      }
+
+      bool f;
+      if (s == "null")
+        return json_value ();
+      else if ((f = (s == "true")) || s == "false")
+        return json_value (f);
+      else if (s.find_first_not_of (
+                 "0123456789", (f = (s[0] == '-')) ? 1 : 0) == string::npos)
+      {
+        name n (move (s));
+        return f
+          ? json_value (value_traits<int64_t>::convert (n, nullptr))
+          : json_value (value_traits<uint64_t>::convert (n, nullptr));
+      }
+      else
+      {
+        // If this is not already a JSON string, array, or object, treat it as
+        // a string.
+        //
+        if (s[0] != '"')
+        {
+          // While the quote character must be first, `{` and `[` could be
+          // preceded with whitespaces.
+          //
+          size_t p (s.find_first_not_of (" \t\n\r"));
+
+          if (p == string::npos || (s[p] != '{' && s[p] != '['))
+          {
+            return json_value (move (s));
+          }
+        }
+
+        // Parse as valid JSON input.
+        //
+#ifndef BUILD2_BOOTSTRAP
+        using namespace butl::json;
+
+        try
+        {
+          parser p (s, empty_string /* name */);
+          return json_value (p);
+        }
+        catch (const invalid_json_input& e)
+        {
+          // @@ How can we communicate value, line/column, position?
+
+          string m ("invalid json value: ");
+          m += e.what ();
+
+          throw invalid_argument (move (m));
+        }
+#else
+        throw invalid_argument ("json parsing requested during bootstrap");
+#endif
+      }
+    };
+
+    size_t n (ns.size ());
+
+    if (n == 0)
+    {
+      return json_value (); // null
+    }
+    else if (n == 1)
+    {
+      return to_json_value (ns.front (), "json");
+    }
+    else
+    {
+      if (ns.front ().pair) // object
+      {
+        json_value r (json_type::object);
+        r.container.reserve (n / 2);
+
+        for (auto i (ns.begin ()); i != ns.end (); ++i)
+        {
+          if (!i->pair)
+            throw invalid_argument (
+              "pair expected in json member value '" + to_string (*i) + '\'');
+
+          // @@ Should we handle quoted member names?
+          //
+          string m (to_string_value (*i, "json member name"));
+          json_value v (to_json_value (*++i, "json member"));
+          v.name = move (m);
+
+          // @@ Override duplicates or fail?
+          //
+          r.container.push_back (move (v));
+        }
+
+        return r;
+      }
+      else // array
+      {
+        json_value r (json_type::array);
+        r.container.reserve (n);
+
+        for (name& n: ns)
+          r.container.push_back (to_json_value (n, "json array element"));
+
+        return r;
+      }
+    }
+  }
+
+  void value_traits<json_value>::
+  assign (value& v, json_value&& x)
+  {
+    if (v)
+      v.as<json_value> () = move (x);
+    else
+      new (&v.data_) json_value (move (x));
+  }
+
+  void value_traits<json_value>::
+  append (value& v, json_value&& x)
+  {
+    if (v)
+    {
+      json_value& p (v.as<json_value> ());
+
+      if (p.empty ())
+        p.swap (x);
+      else
+        p.insert (p.end (),
+                  make_move_iterator (x.begin ()),
+                  make_move_iterator (x.end ()));
+    }
+    else
+      new (&v.data_) json_value (move (x));
+  }
+
+  void value_traits<json_value>::
+  prepend (value& v, json_value&& x)
+  {
+    if (v)
+    {
+      json_value& p (v.as<json_value> ());
+
+      if (!p.empty ())
+        x.insert (x.end (),
+                  make_move_iterator (p.begin ()),
+                  make_move_iterator (p.end ()));
+
+      p.swap (x);
+    }
+    else
+      new (&v.data_) json_value (move (x));
+  }
+
+  void
+  json_value_assign (value& v, names&& ns, const variable*)
+  {
+    if (!v)
+    {
+      new (&v.data_) json_value ();
+      v.null = false;
+    }
+
+    v.as<json_value> ().assign (make_move_iterator (ns.begin ()),
+                             make_move_iterator (ns.end ()));
+  }
+
+  void
+  json_value_append (value& v, names&& ns, const variable*)
+  {
+    if (!v)
+    {
+      new (&v.data_) json_value ();
+      v.null = false;
+    }
+
+    auto& x (v.as<json_value> ());
+    x.insert (x.end (),
+              make_move_iterator (ns.begin ()),
+              make_move_iterator (ns.end ()));
+  }
+
+  void
+  json_value_prepend (value& v, names&& ns, const variable*)
+  {
+    if (!v)
+    {
+      new (&v.data_) json_value ();
+      v.null = false;
+    }
+
+    auto& x (v.as<json_value> ());
+    x.insert (x.begin (),
+              make_move_iterator (ns.begin ()),
+              make_move_iterator (ns.end ()));
+  }
+
+  static names_view
+  json_value_reverse (const value& v, names&, bool)
+  {
+    const auto& x (v.as<json_value> ());
+    return names_view (x.data (), x.size ());
+  }
+
+  static int
+  json_value_compare (const value& l, const value& r)
+  {
+    return vector_compare<name> (l, r);
+  }
+
+  const json_value value_traits<json_value>::empty_instance;
+
+  const char* const value_traits<json_value>::type_name = "json";
+
+  // Note that whether the json value is a container or not depends on its
+  // payload type. However, for our purposes it feels correct to assume it is
+  // a container rather than not with itself as the element type (see
+  // value_traits::{container, element_type} usage for details).
+  //
+  const value_type value_traits<json_value>::value_type
+  {
+    type_name,
+    sizeof (json_value),
+    nullptr,                               // No base.
+    true,                                  // Container.
+    &value_traits<json_value>::value_type, // Element (itself).
+    &default_dtor<json_value>,
+    &default_copy_ctor<json_value>,
+    &default_copy_assign<json_value>,
+    &cmdline_assign,
+    &cmdline_append,
+    &cmdline_prepend,
+    &cmdline_reverse,
+    nullptr,                           // No cast (cast data_ directly).
+    &cmdline_compare,
+    &default_empty<cmdline>
+  };
+
   // cmdline
   //
   cmdline value_traits<cmdline>::
diff --git a/libbuild2/variable.hxx b/libbuild2/variable.hxx
index a91a7e0..eddf1ac 100644
--- a/libbuild2/variable.hxx
+++ b/libbuild2/variable.hxx
@@ -15,6 +15,8 @@
 #include <libbuild2/forward.hxx>
 #include <libbuild2/utility.hxx>
 
+#include <libbuild2/json.hxx>
+
 #include <libbuild2/context.hxx>
 #include <libbuild2/target-type.hxx>
 #include <libbuild2/diagnostics.hxx>
@@ -1179,6 +1181,24 @@ namespace build2
     static const map_value_type<K, V> value_type;
   };
 
+  // json
+  //
+  template <>
+  struct LIBBUILD2_SYMEXPORT value_traits<json_value>
+  {
+    static_assert (sizeof (json_value) <= value::size_, "insufficient space");
+
+    static json_value convert (names&&);
+    static void assign (value&, json_value&&);
+    static void append (value&, json_value&&);
+    static void prepend (value&, json_value&&);
+    static bool empty (const json_value&); // null or empty string|array|object
+
+    static const json_value empty_instance; // null
+    static const char* const type_name;
+    static const build2::value_type value_type;
+  };
+
   // Canned command line to be re-lexed (used in {Build,Test}scripts).
   //
   // Note that because the executable can be specific as a target or as
diff --git a/libbuild2/variable.ixx b/libbuild2/variable.ixx
index 51c35fd..4a0176f 100644
--- a/libbuild2/variable.ixx
+++ b/libbuild2/variable.ixx
@@ -906,6 +906,28 @@ namespace build2
       new (&v.data_) map<K, V> (move (x));
   }
 
+  // json
+  //
+  inline bool value_traits<json_value>::
+  empty (const json_value& v)
+  {
+    if (!v.name)
+    {
+      switch (v.type)
+      {
+      case json_type::null:            return true;
+      case json_type::boolean:
+      case json_type::signed_number:
+      case json_type::unsigned_number: break;
+      case json_type::string:          return v.string.empty ();
+      case json_type::array:
+      case json_type::object:          return v.container.empty ();
+      }
+    }
+
+    return false;
+  }
+
   // variable_pool
   //
   inline const variable* variable_pool::
-- 
cgit v1.1