Merge remote-tracking branch 'origin/develop' into claude/fix-issue-3989-db7e45

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

include/nlohmann/detail/input/lexer.hpp

@@ -2035,6 +2035,39 @@ scan_number_done:
         // read the next character and ignore whitespace
         skip_whitespace();
 
+        return scan_after_whitespace();
+    }
+
+    /*!
+    @brief scan the next token when the caller expects a separator (':' or
+           ',') most of the time
+
+    After an object key the next token is almost always ':', after a value
+    inside an object or array almost always ','. Testing for that character
+    first is a compare and a well-predicted branch, where the switch in
+    scan_after_whitespace() is an indirect jump through a table. Anything else
+    goes through the switch, so the result is the same as scan()'s.
+
+    May only be called after scan() has run once (the BOM check is skipped).
+    */
+    token_type scan_expecting(token_type expected_type)
+    {
+        JSON_ASSERT(expected_type == token_type::name_separator || expected_type == token_type::value_separator);
+        JSON_ASSERT(position.chars_read_total > 0);
+        const char_int_type expected_char = static_cast<unsigned char>((expected_type == token_type::name_separator) ? ':' : ',');
+        skip_whitespace();
+        if (JSON_HEDLEY_LIKELY(current == expected_char))
+        {
+            return expected_type;
+        }
+        return scan_after_whitespace();
+    }
+
+  private:
+    /// the part of scan() after the leading whitespace: skip comments and
+    /// scan the token that starts with current
+    token_type scan_after_whitespace()
+    {
         // ignore comments
         while (ignore_comments && current == '/')
         {
@@ -2114,6 +2147,7 @@ scan_number_done:
         }
     }
 
+  public:
     /////////////////////
     // error recovery
     /////////////////////
@@ -2681,7 +2715,6 @@ scan_number_done:
         }
     }
 
-  private:
     /// input adapter
     InputAdapterType ia;
 

include/nlohmann/detail/input/parser.hpp

@@ -308,7 +308,7 @@ class parser
                         }
 
                         // parse separator (:)
-                        if (JSON_HEDLEY_UNLIKELY(get_token() != token_type::name_separator))
+                        if (JSON_HEDLEY_UNLIKELY(!get_token_expecting(token_type::name_separator)))
                         {
                             if (!continue_after(key_error(sax, allow_recovery, true), skip_to_state_evaluation))
                             {
@@ -538,7 +538,7 @@ class parser
             {
                 // comma -> next value
                 // or end of array (ignore_trailing_commas = true)
-                if (get_token() == token_type::value_separator)
+                if (get_token_expecting(token_type::value_separator))
                 {
                     // parse a new value
                     get_token();
@@ -599,7 +599,7 @@ class parser
 
             // comma -> next value
             // or end of object (ignore_trailing_commas = true)
-            if (get_token() == token_type::value_separator)
+            if (get_token_expecting(token_type::value_separator))
             {
                 get_token();
 
@@ -621,7 +621,7 @@ class parser
                     }
 
                     // parse separator (:)
-                    if (JSON_HEDLEY_UNLIKELY(get_token() != token_type::name_separator))
+                    if (JSON_HEDLEY_UNLIKELY(!get_token_expecting(token_type::name_separator)))
                     {
                         if (!continue_after(key_error(sax, allow_recovery, true), skip_to_state_evaluation))
                         {
@@ -1134,6 +1134,13 @@ class parser
         return last_token = m_lexer.scan();
     }
 
+    /// get next token from lexer; true if it is the separator @a expected_type
+    /// (name_separator or value_separator), which it usually is
+    bool get_token_expecting(token_type expected_type)
+    {
+        return (last_token = m_lexer.scan_expecting(expected_type)) == expected_type;
+    }
+
     std::string exception_message(const token_type expected, const std::string& context)
     {
         std::string error_msg = "syntax error ";