Copy the tokens of json_pointer::to_string() with std::copy

clang-tidy (bugprone-not-null-terminated-result) took the memcpy into
the result string for a C string missing its terminator. std::copy is
the same memmove; to_string() instructions are unchanged (Apple clang).

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

include/nlohmann/detail/json_pointer.hpp

@@ -8,7 +8,7 @@
 
 #pragma once
 
-#include <algorithm> // all_of
+#include <algorithm> // all_of, copy
 #include <array> // array
 #include <cctype> // isdigit
 #include <cerrno> // errno, ERANGE
@@ -82,12 +82,34 @@ class json_pointer
     {
         // one buffer: every token adds its escaped form (at least its length) and a slash
         std::size_t length = 0;
+        bool plain = true;
         for (const auto& reference_token : reference_tokens)
         {
             length += reference_token.size() + 1;
+            const char* const data = reference_token.data();
+            for (std::size_t i = 0, size = reference_token.size(); plain && i < size; ++i)
+            {
+                plain = data[i] != '~' && data[i] != '/';
+            }
         }
 
         string_t result;
+        if (JSON_HEDLEY_LIKELY(plain))
+        {
+            // nothing to escape: the tokens are copied into the string
+            result.resize(length);
+            if (length != 0)
+            {
+                char* out = &result[0];
+                for (const auto& reference_token : reference_tokens)
+                {
+                    *out++ = '/';
+                    out = std::copy(reference_token.data(), reference_token.data() + reference_token.size(), out);
+                }
+            }
+            return result;
+        }
+
         result.reserve(length);
         for (const auto& reference_token : reference_tokens)
         {
@@ -1198,33 +1220,32 @@ class json_pointer
         }
         result.reserve(token_count);
 
-        // extract the reference tokens:
-        // - slash: position of the last read slash (or end of string)
-        // - start: position after the previous slash
-        for (
-            // search for the first slash after the first character
-            std::size_t slash = reference_string.find_first_of('/', 1),
-            // set the beginning of the first reference token
-            start = 1;
-            // we can stop if start == 0 (if slash == string_t::npos)
-            start != 0;
-            // set the beginning of the next reference token
-            // (will eventually be 0 if slash == string_t::npos)
-            start = (slash == string_t::npos) ? 0 : slash + 1,
-            // find next slash
-            slash = reference_string.find_first_of('/', start))
+        // extract the reference tokens: every one runs from after a slash to
+        // the next slash or the end of the string; a token without a '~' (the
+        // common case) is stored as it is, others are checked and unescaped
+        const char* const data = reference_string.data();
+        const char* const end = data + size;
+        for (const char* start = data + 1;; ++start)
         {
-            // use the text between the beginning of the reference token
-            // (start) and the last slash (slash).
-            const auto count = (slash == string_t::npos ? reference_string.size() : slash) - start;
-            auto reference_token = string_t(reference_string.data() + start, count);
-
-            // check reference tokens are properly escaped; a token without
-            // a '~' (the common case) needs neither check nor unescaping
-            std::size_t pos = reference_token.find_first_of('~');
-            if (pos != string_t::npos)
+            const char* slash = start;
+            bool escaped = false;
+            while (slash != end && *slash != '/')
             {
-                for (; pos != string_t::npos; pos = reference_token.find_first_of('~', pos + 1))
+                escaped = escaped || *slash == '~';
+                ++slash;
+            }
+
+            const auto count = static_cast<std::size_t>(slash - start);
+            if (JSON_HEDLEY_LIKELY(!escaped))
+            {
+                result.emplace_back(start, count);
+            }
+            else
+            {
+                auto reference_token = string_t(start, count);
+
+                // check reference tokens are properly escaped
+                for (std::size_t pos = reference_token.find_first_of('~'); pos != string_t::npos; pos = reference_token.find_first_of('~', pos + 1))
                 {
                     JSON_ASSERT(reference_token[pos] == '~');
 
@@ -1238,10 +1259,14 @@ class json_pointer
                 }
 
                 detail::unescape(reference_token);
+                result.push_back(std::move(reference_token));
             }
 
-            // finally, store the reference token
-            result.push_back(std::move(reference_token));
+            if (slash == end)
+            {
+                break;
+            }
+            start = slash;
         }
 
         return result;

single_include/nlohmann/json.hpp

@@ -22350,7 +22350,7 @@ NLOHMANN_JSON_NAMESPACE_END
 
 
 
-#include <algorithm> // all_of
+#include <algorithm> // all_of, copy
 #include <array> // array
 #include <cctype> // isdigit
 #include <cerrno> // errno, ERANGE
@@ -22432,12 +22432,34 @@ class json_pointer
     {
         // one buffer: every token adds its escaped form (at least its length) and a slash
         std::size_t length = 0;
+        bool plain = true;
         for (const auto& reference_token : reference_tokens)
         {
             length += reference_token.size() + 1;
+            const char* const data = reference_token.data();
+            for (std::size_t i = 0, size = reference_token.size(); plain && i < size; ++i)
+            {
+                plain = data[i] != '~' && data[i] != '/';
+            }
         }
 
         string_t result;
+        if (JSON_HEDLEY_LIKELY(plain))
+        {
+            // nothing to escape: the tokens are copied into the string
+            result.resize(length);
+            if (length != 0)
+            {
+                char* out = &result[0];
+                for (const auto& reference_token : reference_tokens)
+                {
+                    *out++ = '/';
+                    out = std::copy(reference_token.data(), reference_token.data() + reference_token.size(), out);
+                }
+            }
+            return result;
+        }
+
         result.reserve(length);
         for (const auto& reference_token : reference_tokens)
         {
@@ -23548,33 +23570,32 @@ class json_pointer
         }
         result.reserve(token_count);
 
-        // extract the reference tokens:
-        // - slash: position of the last read slash (or end of string)
-        // - start: position after the previous slash
-        for (
-            // search for the first slash after the first character
-            std::size_t slash = reference_string.find_first_of('/', 1),
-            // set the beginning of the first reference token
-            start = 1;
-            // we can stop if start == 0 (if slash == string_t::npos)
-            start != 0;
-            // set the beginning of the next reference token
-            // (will eventually be 0 if slash == string_t::npos)
-            start = (slash == string_t::npos) ? 0 : slash + 1,
-            // find next slash
-            slash = reference_string.find_first_of('/', start))
+        // extract the reference tokens: every one runs from after a slash to
+        // the next slash or the end of the string; a token without a '~' (the
+        // common case) is stored as it is, others are checked and unescaped
+        const char* const data = reference_string.data();
+        const char* const end = data + size;
+        for (const char* start = data + 1;; ++start)
         {
-            // use the text between the beginning of the reference token
-            // (start) and the last slash (slash).
-            const auto count = (slash == string_t::npos ? reference_string.size() : slash) - start;
-            auto reference_token = string_t(reference_string.data() + start, count);
-
-            // check reference tokens are properly escaped; a token without
-            // a '~' (the common case) needs neither check nor unescaping
-            std::size_t pos = reference_token.find_first_of('~');
-            if (pos != string_t::npos)
+            const char* slash = start;
+            bool escaped = false;
+            while (slash != end && *slash != '/')
             {
-                for (; pos != string_t::npos; pos = reference_token.find_first_of('~', pos + 1))
+                escaped = escaped || *slash == '~';
+                ++slash;
+            }
+
+            const auto count = static_cast<std::size_t>(slash - start);
+            if (JSON_HEDLEY_LIKELY(!escaped))
+            {
+                result.emplace_back(start, count);
+            }
+            else
+            {
+                auto reference_token = string_t(start, count);
+
+                // check reference tokens are properly escaped
+                for (std::size_t pos = reference_token.find_first_of('~'); pos != string_t::npos; pos = reference_token.find_first_of('~', pos + 1))
                 {
                     JSON_ASSERT(reference_token[pos] == '~');
 
@@ -23588,10 +23609,14 @@ class json_pointer
                 }
 
                 detail::unescape(reference_token);
+                result.push_back(std::move(reference_token));
             }
 
-            // finally, store the reference token
-            result.push_back(std::move(reference_token));
+            if (slash == end)
+            {
+                break;
+            }
+            start = slash;
         }
 
         return result;