Guard the null value of a value-initialized iterator; drop the unneeded found flag

With the root's byte range, diagnostics() reaches get_byte_positions() also
with JSON_DIAGNOSTICS when there is no value, as for a value-initialized
iterator (invalid_iterator.212). get_byte_positions() now returns no range
for a null value, the same change as #6003, so either can be merged first.

In the view, a value that value_path() does not find leaves no tokens, so the
found flag added nothing to the tokens.empty() test.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

docs/mkdocs/docs/api/macros/json_diagnostic_positions.md

@@ -35,6 +35,9 @@ Note that enabling this macro increases the size of every JSON value by two `std
 overhead to parsing, copying JSON value objects, and the generation of error messages for exceptions. It also causes
 these values to be reported in those error messages.
 
+If [`JSON_DIAGNOSTICS`](json_diagnostics.md) is also set, the message contains the path and the byte range, such as
+`(/1) (bytes 4-8)`. An exception about the root value has no path and only the range, such as `(bytes 0-4)`.
+
 ## Default definition
 
 The default value is `0` (position diagnostics are switched off).

include/nlohmann/detail/exceptions.hpp

@@ -198,18 +198,19 @@ class exception : public std::exception
             // all other parent types (primitives) contribute no token
         }
 
-        if (tokens.empty())
+        // the root value has no path, but still has a byte range
+        std::string prefix;
+        if (!tokens.empty())
         {
-            return "";
+            const auto str = std::accumulate(tokens.rbegin(), tokens.rend(), std::string{},
-        }
-
-        auto str = std::accumulate(tokens.rbegin(), tokens.rend(), std::string{},
                                              [](const std::string & a, const std::string & b)
             {
                 return concat(a, '/', detail::escape(b));
             });
+            prefix = concat('(', str, ") ");
+        }
 
-        return concat('(', str, ") ", get_byte_positions(leaf_element));
+        return concat(prefix, get_byte_positions(leaf_element));
 #else
         return get_byte_positions(leaf_element);
 #endif
@@ -222,7 +223,8 @@ class exception : public std::exception
     template<typename BasicJsonType>
     static std::string get_byte_positions(const BasicJsonType* leaf_element)
     {
-        if ((leaf_element->start_pos() != std::string::npos) && (leaf_element->end_pos() != std::string::npos))
+        // a value-initialized iterator has no value (invalid_iterator.212)
+        if (leaf_element != nullptr && leaf_element->start_pos() != std::string::npos && leaf_element->end_pos() != std::string::npos)
         {
             return concat("(bytes ", std::to_string(leaf_element->start_pos()), "-", std::to_string(leaf_element->end_pos()), ") ");
         }

include/nlohmann/detail/view/errors.hpp

@@ -234,8 +234,7 @@ void value_range(const document_data& d, const node* n, std::size_t& start, std:
 
 /// the context basic_json puts in front of the message of an exception about
 /// a value: "(/path) " with JSON_DIAGNOSTICS (none for the root), then
-/// "(bytes a-b) " with JSON_DIAGNOSTIC_POSITIONS (with JSON_DIAGNOSTICS, only
+/// "(bytes a-b) " with JSON_DIAGNOSTIC_POSITIONS (also for the root)
-/// if there is a path)
 ///
 /// This and the throw helpers that take an error_site are templates, so that
 /// the path and range code is instantiated only where an exception can be
@@ -256,12 +255,11 @@ std::string diagnostics(const error_site site)
     std::string context;
 #if JSON_DIAGNOSTICS
     std::vector<std::string> tokens;
-    const bool found = edited ? value_path<true>(d, site.value(), tokens) : value_path<false>(d, site.value(), tokens);
+    // a value that is not found leaves no tokens, like the root
-    if (!found || tokens.empty())
+    static_cast<void>(edited ? value_path<true>(d, site.value(), tokens) : value_path<false>(d, site.value(), tokens));
+    if (!tokens.empty())
     {
-        // context is still empty; returning it keeps the copy elided (-Wnrvo)
+        // the root value has no path, but still has a byte range
-        return context;
-    }
         std::string path;
         for (const std::string& token : tokens)
         {
@@ -269,6 +267,7 @@ std::string diagnostics(const error_site site)
             path += detail::escape(token);
         }
         context = concat('(', path, ") ");
+    }
 #endif
 #if JSON_DIAGNOSTIC_POSITIONS
     std::size_t start = 0;

single_include/nlohmann/json.hpp

@@ -5695,18 +5695,19 @@ class exception : public std::exception
             // all other parent types (primitives) contribute no token
         }
 
-        if (tokens.empty())
+        // the root value has no path, but still has a byte range
+        std::string prefix;
+        if (!tokens.empty())
         {
-            return "";
+            const auto str = std::accumulate(tokens.rbegin(), tokens.rend(), std::string{},
-        }
-
-        auto str = std::accumulate(tokens.rbegin(), tokens.rend(), std::string{},
                                              [](const std::string & a, const std::string & b)
             {
                 return concat(a, '/', detail::escape(b));
             });
+            prefix = concat('(', str, ") ");
+        }
 
-        return concat('(', str, ") ", get_byte_positions(leaf_element));
+        return concat(prefix, get_byte_positions(leaf_element));
 #else
         return get_byte_positions(leaf_element);
 #endif
@@ -5719,7 +5720,8 @@ class exception : public std::exception
     template<typename BasicJsonType>
     static std::string get_byte_positions(const BasicJsonType* leaf_element)
     {
-        if ((leaf_element->start_pos() != std::string::npos) && (leaf_element->end_pos() != std::string::npos))
+        // a value-initialized iterator has no value (invalid_iterator.212)
+        if (leaf_element != nullptr && leaf_element->start_pos() != std::string::npos && leaf_element->end_pos() != std::string::npos)
         {
             return concat("(bytes ", std::to_string(leaf_element->start_pos()), "-", std::to_string(leaf_element->end_pos()), ") ");
         }

single_include/nlohmann/json_view.hpp

@@ -5076,8 +5076,7 @@ void value_range(const document_data& d, const node* n, std::size_t& start, std:
 
 /// the context basic_json puts in front of the message of an exception about
 /// a value: "(/path) " with JSON_DIAGNOSTICS (none for the root), then
-/// "(bytes a-b) " with JSON_DIAGNOSTIC_POSITIONS (with JSON_DIAGNOSTICS, only
+/// "(bytes a-b) " with JSON_DIAGNOSTIC_POSITIONS (also for the root)
-/// if there is a path)
 ///
 /// This and the throw helpers that take an error_site are templates, so that
 /// the path and range code is instantiated only where an exception can be
@@ -5098,12 +5097,11 @@ std::string diagnostics(const error_site site)
     std::string context;
 #if JSON_DIAGNOSTICS
     std::vector<std::string> tokens;
-    const bool found = edited ? value_path<true>(d, site.value(), tokens) : value_path<false>(d, site.value(), tokens);
+    // a value that is not found leaves no tokens, like the root
-    if (!found || tokens.empty())
+    static_cast<void>(edited ? value_path<true>(d, site.value(), tokens) : value_path<false>(d, site.value(), tokens));
+    if (!tokens.empty())
     {
-        // context is still empty; returning it keeps the copy elided (-Wnrvo)
+        // the root value has no path, but still has a byte range
-        return context;
-    }
         std::string path;
         for (const std::string& token : tokens)
         {
@@ -5111,6 +5109,7 @@ std::string diagnostics(const error_site site)
             path += detail::escape(token);
         }
         context = concat('(', path, ") ");
+    }
 #endif
 #if JSON_DIAGNOSTIC_POSITIONS
     std::size_t start = 0;

tests/src/unit-diagnostic-positions.cpp

@@ -193,6 +193,28 @@ TEST_CASE("Better diagnostics with positions")
         check_conversion(300);
     }
 
+    SECTION("exception about the root value (#5987)")
+    {
+        // the root has no path, but still has a byte range
+        const json root = json::parse("true");
+        const json nested = json::parse("[1, true]");
+        const json constructed = true;
+#if JSON_DIAGNOSTICS
+        CHECK_THROWS_WITH_AS(root.get<std::string>(),
+                             "[json.exception.type_error.302] (bytes 0-4) type must be string, but is boolean", json::type_error);
+        CHECK_THROWS_WITH_AS(nested[1].get<std::string>(),
+                             "[json.exception.type_error.302] (/1) (bytes 4-8) type must be string, but is boolean", json::type_error);
+#else
+        CHECK_THROWS_WITH_AS(root.get<std::string>(),
+                             "[json.exception.type_error.302] (bytes 0-4) type must be string, but is boolean", json::type_error);
+        CHECK_THROWS_WITH_AS(nested[1].get<std::string>(),
+                             "[json.exception.type_error.302] (bytes 4-8) type must be string, but is boolean", json::type_error);
+#endif
+        // a value without positions gets no range and no stray whitespace
+        CHECK_THROWS_WITH_AS(constructed.get<std::string>(),
+                             "[json.exception.type_error.302] type must be string, but is boolean", json::type_error);
+    }
+
     SECTION("JSON patch add to primitive parent (#4292)")
     {
         // the JSON Patch "add" target /foo/bar/baz has a string parent
@@ -243,3 +265,14 @@ TEST_CASE("values read from a binary format have no positions")
         check_no_positions(j);
     }
 }
+
+TEST_CASE("comparing a value-initialized iterator throws invalid_iterator.212")
+{
+    // such an iterator has no value to take the byte positions from; the
+    // comparison used to dereference the null pointer instead of throwing
+    json j = {1, 2};
+    json::iterator it{};
+    CHECK_THROWS_WITH_AS(it == j.begin(), "[json.exception.invalid_iterator.212] cannot compare iterators of different containers", json::invalid_iterator);
+    CHECK_THROWS_WITH_AS(it < j.begin(), "[json.exception.invalid_iterator.212] cannot compare iterators of different containers", json::invalid_iterator);
+    CHECK_THROWS_WITH_AS(j.begin() == it, "[json.exception.invalid_iterator.212] cannot compare iterators of different containers", json::invalid_iterator);
+}

tests/src/unit-json_view_positions.cpp

@@ -300,6 +300,27 @@ TEST_CASE("json_view materialize() source positions")
             static_cast<void>(j.at("list").at(1).get<int>());
         }));
     }
+
+    SECTION("exception about the root value (#5987)")
+    {
+        const json_document root = json_document::parse("true");
+        const json_document nested = json_document::parse("[1, true]");
+        CHECK(json_view_test::exception_of_call([&]
+        {
+            static_cast<void>(root.root().get<std::string>());
+        }) == "[json.exception.type_error.302] (bytes 0-4) type must be string, but is boolean");
+#if JSON_DIAGNOSTICS
+        CHECK(json_view_test::exception_of_call([&]
+        {
+            static_cast<void>(nested.root()[1].get<std::string>());
+        }) == "[json.exception.type_error.302] (/1) (bytes 4-8) type must be string, but is boolean");
+#else
+        CHECK(json_view_test::exception_of_call([&]
+        {
+            static_cast<void>(nested.root()[1].get<std::string>());
+        }) == "[json.exception.type_error.302] (bytes 4-8) type must be string, but is boolean");
+#endif
+    }
 #endif
 
     SECTION("edited documents")
@@ -550,12 +571,8 @@ TEST_CASE("json_view exceptions name the path and the bytes of the value")
         expected_zz += "(bytes 12-35) key 'zz' not found";
         CHECK(exception_of_call([&] { static_cast<void>(d.root().at(json::json_pointer("/people/0/zz"))); }) == expected_zz);
 
-        // the root has no path, and with JSON_DIAGNOSTICS then no bytes either (as basic_json)
+        // the root has no path, but still its bytes (#5987)
-        std::string expected_missing = "[json.exception.out_of_range.403] ";
+        const std::string expected_missing = "[json.exception.out_of_range.403] (bytes 0-79) key 'missing' not found";
-#if !JSON_DIAGNOSTICS
-        expected_missing += "(bytes 0-79) ";
-#endif
-        expected_missing += "key 'missing' not found";
         CHECK(exception_of_call([&] { static_cast<void>(d.root().at("missing")); }) == expected_missing);
     }