Merge branch develop into claude/perf-iterator-ranges

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

include/nlohmann/detail/input/number_parse.hpp

@@ -316,6 +316,30 @@ JSON_HEDLEY_ALWAYS_INLINE std::size_t accumulate_digits(const char* data, std::s
     return i;
 }
 
+/// the index of the first byte at or after @a i that is not a digit: the
+/// digits of accumulate_digits() without their value
+JSON_HEDLEY_ALWAYS_INLINE std::size_t skip_digits(const char* data, std::size_t i, std::size_t avail) noexcept
+{
+    while (avail - i >= 8)
+    {
+        if (!is_eight_digits(read_eight_bytes(data + i)))
+        {
+            // a byte of the word is not a digit: no bounds checks before it
+            while (static_cast<unsigned char>(data[i] - '0') <= 9)
+            {
+                ++i;
+            }
+            return i;
+        }
+        i += 8;
+    }
+    while (i < avail && data[i] >= '0' && data[i] <= '9')
+    {
+        ++i;
+    }
+    return i;
+}
+
 /// whether [first, last) contains a digit other than '0'; a plain loop, as
 /// GCC calls std::any_of out of line even for the usual empty range
 JSON_HEDLEY_ALWAYS_INLINE bool has_nonzero_digit(const char* first, const char* last) noexcept

include/nlohmann/detail/input/string_scan.hpp

@@ -520,7 +520,10 @@ JSON_HEDLEY_NEVER_INLINE inline std::size_t string_bulk_run_from(const unsigned
 }
 #endif
 
-// string_bulk_run() for the lexer. With NEON, only the first four words are
+// string_bulk_run() for the lexer. The run must be the longest one: the lexer
+// would only lose speed with a shorter run, but contiguous_parser rejects a
+// string whose run ends at a byte other than a quote or a backslash, so a
+// shorter run would reject valid input there. With NEON, only the first four words are
 // checked inline (most keys and short values end there), and longer runs and
 // non-ASCII text continue out of line. The lexer's scan function runs once per
 // token, and the vector code inlined into it needs more registers, which every

include/nlohmann/json.hpp

@@ -58,6 +58,7 @@
 #include <nlohmann/detail/exceptions.hpp> // IWYU pragma: export
 #include <nlohmann/detail/hash.hpp>
 #include <nlohmann/detail/input/binary_reader.hpp>
+#include <nlohmann/detail/input/contiguous_parser.hpp>
 #include <nlohmann/detail/input/input_adapters.hpp>
 #include <nlohmann/detail/input/json_sax.hpp>
 #include <nlohmann/detail/input/lexer.hpp>
@@ -3109,6 +3110,15 @@ public:
                                  const bool ignore_trailing_commas)
     {
         basic_json result;
+        // JSON in one block of memory, with the default options, is read by
+        // the faster contiguous_parser; on an error, the default parser reads
+        // it again to report it (see contiguous_parser)
+        using contiguous = std::integral_constant<bool, detail::can_parse_contiguous<basic_json, typename std::decay<InputAdapterType>::type>::value>;
+        if (cb == nullptr && !ignore_comments && !ignore_trailing_commas
+                && detail::parse_contiguous(adapter, result, allow_exceptions, contiguous {}))
+        {
+            return result;
+        }
         parser(std::forward<InputAdapterType>(adapter), std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas).parse(true, result);
         return result;
     }
@@ -3119,8 +3129,17 @@ public:
                             const bool ignore_comments,
                             const bool ignore_trailing_commas)
     {
+        // JSON in one block of memory, with the default options, is checked by
+        // the faster contiguous_parser (see parse_impl())
+        using adapter_t = typename std::decay<InputAdapterType>::type;
+        bool accepted = false;
+        if (!ignore_comments && !ignore_trailing_commas
+                && detail::accept_contiguous<basic_json>(adapter, accepted, std::integral_constant<bool, detail::can_parse_contiguous<basic_json, adapter_t>::value> {}))
+        {
+            return accepted;
+        }
         // the parser and lexer that discard the values of tokens (see lexer)
-        return ::nlohmann::detail::parser<basic_json, typename std::decay<InputAdapterType>::type, true>(std::forward<InputAdapterType>(adapter),
+        return ::nlohmann::detail::parser<basic_json, adapter_t, true>(std::forward<InputAdapterType>(adapter),
                 nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
     }
 
@@ -3135,6 +3154,15 @@ public:
     {
         if (format == input_format_t::json)
         {
+            // JSON in one block of memory, with the default options, is read by
+            // the faster contiguous_parser; on an error, the default parser
+            // reads it again to report it (see parse_impl())
+            bool result = false;
+            if (strict && !ignore_comments && !ignore_trailing_commas
+                    && detail::sax_parse_contiguous<basic_json>(ia, sax, result, std::integral_constant<bool, detail::can_parse_contiguous<basic_json, InputAdapterType>::value> {}))
+            {
+                return result;
+            }
             return parser(std::move(ia), nullptr, true, ignore_comments, ignore_trailing_commas).sax_parse(sax, strict);
         }
         return detail::binary_reader<basic_json, InputAdapterType, SAX>(std::move(ia), format).sax_parse(sax, strict, tag_handler);