json_view: no per-object allocations in ordered_json comparisons

For an object type that keeps the order of its members (ordered_json),
resolve_indices() allocated a vector per compared object, and
resolve_members() two. They now use one working vector owned by equal(),
whose capacity is reused, and resolve_indices() needs none when the keys
are unique. resolve_members() sorts small objects by insertion, as the
other paths do.

Instructions per comparison (callgrind, GCC 13 and clang 18, x86-64):
twitter, ordered_json view == ordered_json: 0.939 / 0.941; 20000 small
objects with a duplicate key: 0.741-0.768; all other rows (json,
citm_catalog, canada, view == view) within 0.988-1.003.

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

include/nlohmann/detail/view/image.hpp

@@ -255,6 +255,81 @@ struct number_token
     bool is_float; ///< a fraction or an exponent
 };
 
+/// advance over ASCII digits, eight bytes at a time
+inline const unsigned char* digit_run(const unsigned char* p, const unsigned char* e) noexcept
+{
+    constexpr std::uint64_t ones = 0x0101010101010101ull;
+    while (e - p >= 8)
+    {
+        // (the digits become 0..9; a byte above 9, or with bit 7 set, is no digit. A carry
+        // out of a byte with bit 7 set only affects the bytes above, after the first one
+        // that count_trailing_zeros finds.)
+        const std::uint64_t x = read_eight_bytes(p) ^ (ones * 0x30u);
+        const std::uint64_t not_digit = ((x + (ones * 0x76u)) | x) & (ones * 0x80u);
+        if (not_digit != 0)
+        {
+            return p + (static_cast<std::size_t>(count_trailing_zeros(not_digit)) / 8);
+        }
+        p += 8;
+    }
+    while (p != e && is_digit(*p))
+    {
+        ++p;
+    }
+    return p;
+}
+
+/// whether the n bytes at p are ASCII digits (n > 0)
+inline bool all_digits(const unsigned char* p, std::size_t n) noexcept
+{
+    const auto digits = [](const unsigned char* q)
+    {
+        constexpr std::uint64_t ones = 0x0101010101010101ull;
+        const std::uint64_t x = read_eight_bytes(q) ^ (ones * 0x30u);
+        return (((x + (ones * 0x76u)) | x) & (ones * 0x80u)) == 0;
+    };
+    if (n >= 8)
+    {
+        for (std::size_t i = 0; i + 8 < n; i += 8)
+        {
+            if (!digits(p + i))
+            {
+                return false;
+            }
+        }
+        return digits(p + n - 8); // (overlapping the bytes before: they are digits)
+    }
+    for (std::size_t i = 0; i < n; ++i)
+    {
+        if (!is_digit(p[i]))
+        {
+            return false;
+        }
+    }
+    return true;
+}
+
+/// Whether a float token has the shape that the parser records for most of
+/// them: [-]digits.digits, with the numbers of digits of the node's layout
+/// (extra). Then the token is a number of that layout, and the general scan
+/// that follows is not needed.
+inline bool plain_float_token(const unsigned char* s, std::size_t len, std::uint16_t extra) noexcept
+{
+    const std::size_t int_digits = extra & 0xFFu;
+    const std::size_t frac_digits = extra >> 8u;
+    if (int_digits == 0 || int_digits >= 255 || frac_digits == 0 || frac_digits >= 255 || len == 0)
+    {
+        return false;
+    }
+    const std::size_t negative = *s == '-' ? 1 : 0;
+    if (len != negative + int_digits + 1 + frac_digits)
+    {
+        return false;
+    }
+    const unsigned char* const p = s + negative;
+    return !(int_digits > 1 && *p == '0') && p[int_digits] == '.' && all_digits(p, int_digits) && all_digits(p + int_digits + 1, frac_digits);
+}
+
 /// whether [s, s + len) is a JSON number (the grammar the parser accepts)
 inline bool scan_number_token(const unsigned char* s, std::size_t len, number_token& t)
 {
@@ -273,11 +348,7 @@ inline bool scan_number_token(const unsigned char* s, std::size_t len, number_to
     }
     else if (*p >= '1' && *p <= '9')
     {
-        do
+        p = digit_run(p + 1, e);
-        {
-            ++p;
-        }
-        while (p != e && is_digit(*p));
     }
     else
     {
@@ -289,10 +360,7 @@ inline bool scan_number_token(const unsigned char* s, std::size_t len, number_to
     if (p != e && *p == '.')
     {
         const unsigned char* const f0 = ++p;
-        while (p != e && is_digit(*p))
+        p = digit_run(p, e);
-        {
-            ++p;
-        }
         if (p == f0)
         {
             return false;
@@ -403,10 +471,15 @@ struct float_range
 template<typename Check>
 bool check_distinct_ranges(std::vector<byte_range>& ranges, Check check)
 {
-    std::sort(ranges.begin(), ranges.end(), [](const byte_range & a, const byte_range & b)
+    // (save() writes the ranges in the order of the nodes, which is sorted already)
+    const auto before = [](const byte_range & a, const byte_range & b)
     {
         return a.off != b.off ? a.off < b.off : a.len < b.len;
-    });
+    };
+    if (!std::is_sorted(ranges.begin(), ranges.end(), before))
+    {
+        std::sort(ranges.begin(), ranges.end(), before);
+    }
     std::size_t end = 0;
     for (std::size_t i = 0; i < ranges.size(); ++i)
     {
@@ -428,7 +501,8 @@ bool check_distinct_ranges(std::vector<byte_range>& ranges, Check check)
 /// record layouts that match it), tokens must not overlap.
 inline bool check_float_ranges(std::vector<float_range>& ranges, const unsigned char* text)
 {
-    std::sort(ranges.begin(), ranges.end(), [](const float_range & a, const float_range & b)
+    // (save() writes the tokens in the order of the nodes, which is sorted already)
+    const auto before = [](const float_range & a, const float_range & b)
     {
         if (a.off != b.off)
         {
@@ -439,7 +513,11 @@ inline bool check_float_ranges(std::vector<float_range>& ranges, const unsigned
             return a.len < b.len;
         }
         return a.extra < b.extra;
-    });
+    };
+    if (!std::is_sorted(ranges.begin(), ranges.end(), before))
+    {
+        std::sort(ranges.begin(), ranges.end(), before);
+    }
     std::size_t end = 0;
     std::size_t i = 0;
     while (i < ranges.size())
@@ -449,14 +527,18 @@ inline bool check_float_ranges(std::vector<float_range>& ranges, const unsigned
         {
             return false;
         }
-        number_token t{};
         const unsigned char* const s = text + r.off;
+        std::uint16_t layout = r.extra;
+        if (!plain_float_token(s, r.len, r.extra))
+        {
+            number_token t{};
             if (!scan_number_token(s, r.len, t) || !float_token_finite(s, r.len, t))
             {
                 return false;
             }
             // the digit layout the parser records (or "many", as compaction writes it)
-        const std::uint16_t layout = float_layout(t);
+            layout = float_layout(t);
+        }
         for (; i < ranges.size() && ranges[i].off == r.off && ranges[i].len == r.len; ++i)
         {
             if (ranges[i].extra != layout && ranges[i].extra != 0xFFFFu)

include/nlohmann/json_view.hpp

@@ -743,8 +743,12 @@ class basic_json_view
     template<typename, bool> friend class basic_json_document;
     template<typename, bool> friend class basic_json_view;
     template<typename, typename> friend class detail::view::editor;
+    template<typename, typename> friend class detail::view::view_side;
     friend iterator;
 
+    /// whether the view is one of an editable document
+    static constexpr bool is_editable = Editable;
+
     basic_json_view(const document_data* d, const node* n) noexcept
         : m_doc(d), m_node(n)
     {}

tests/benchmarks/json_view/README.md

@@ -21,10 +21,6 @@ python3 tests/benchmarks/json_view/compare.py --data <json_test_data directory>
 - The other libraries come from the system: pkg-config, or Homebrew (`brew install yyjson simdjson boost`). With
   `--download`, pinned releases are downloaded instead and checked against their SHA-256. Without Boost headers (or
   with `--no-boost`), the Boost.JSON columns are skipped, and the results say so.
-- `--aligned` additionally builds and runs everything with all functions aligned to 64 bytes (`-mllvm
-  -align-all-functions=6` for Clang, `-falign-functions=64 -falign-loops=64` for GCC), and reports both result
-  tables as "default build" and "aligned build". Code layout alone can move a result by a few percent; a difference
-  that appears in only one of the two tables is a layout artifact. Off by default, which doubles the run time.
 - `--corpus file...` adds files to the corpus benchmark, e.g. those of
   [simdjson-data](https://github.com/simdjson/simdjson-data) or the
   [yyjson benchmark](https://github.com/ibireme/yyjson_benchmark).
@@ -43,7 +39,7 @@ where `json_view` stands on another architecture; they are not meant for publica
 
 ## What is measured
 
-`bench_view.cpp` runs these workloads on twitter, citm_catalog, canada, jeopardy, a single tweet (`status`), and a
+`bench_view.cpp` runs four workloads on twitter, citm_catalog, canada, jeopardy, a single tweet (`status`), and a
 JSON-RPC request (`rpc`):
 
 | workload | what it does |
@@ -52,7 +48,6 @@ JSON-RPC request (`rpc`):
 | traverse | parse, then visit every value, convert every number, touch every string and key |
 | select | parse, then read a few fields per record (e.g. id, user name, and retweet count of each tweet) |
 | dump | serialize a parsed document (compact) |
-| parse+dump | build a fresh document, then serialize it (compact), in one timed call |
 
 `bench_corpus.cpp` runs parse, traverse, and dump on any list of files, so that no library is tuned to a handful of
 documents. Its dump also writes the numbers as they are in the input: `json_view` with `number_format::source`, and
@@ -71,32 +66,11 @@ call follows an untimed call of the same engine: otherwise the engine after `jso
 cleaning up the tens of thousands of nodes `json::parse` just freed (with glibc, this made `json_view` look 1.7 times
 slower on citm_catalog traverse).
 
-`json_view` is an index into the source text, not a tree of owning nodes. Its like-for-like peers are yyjson and
-simdjson DOM (immutable, indexed, no per-node allocation). Boost.JSON and `json::parse` build mutable, owning DOMs and
-are reference points for what that costs, not equals; simdjson On-Demand is lazy and forward-only, so it is the other
-way round: it has no random access to pay for. All engines validate UTF-8 and syntax by default.
-
-Number conversion differs: `json_view` converts integers while parsing but converts floating-point numbers lazily,
-when they are read or dumped; yyjson (default flags) and simdjson DOM convert every number while parsing. The cost of
-float conversion therefore appears in the traverse and dump rows for `json_view`, and in the parse row for the others.
-For float-heavy documents (canada), the fair reading is a sum of parse and use: the `traverse` workload already
-includes the parse, and `parse+dump` measures a fresh document and its dump in one timed call; the `dump` row alone
-leaves the conversion in `json_view` and out of the others. Eager conversion at parse time was prototyped as an opt-in
-and measured: canada traverse (with its parse) was 4-7 % faster, but parse+dump 11-30 % slower and parse 36-90 % slower. It was
-dropped, so lazy conversion is the only mode.
-
-`json_view` can also be edited: `json_editable_document` has the same read API, and the `(editable)` rows in
-`bench_view` measure it on the same workloads. They are the fair counterpart of Boost.JSON and `json::parse`, which are
-mutable too; the plain `json_view` rows are the counterpart of yyjson and simdjson DOM, which are not. `bench_edit` adds
-the read-modify-write workloads. Read the tables with that in mind: an immutable-only library is not compared with an
-editable `json_view` unless it says so.
-
 The engines do not all offer the same features, which the numbers should be read with:
 
 | engine | document | random access | editable | notes |
 |---|---|---|---|---|
 | `json_view` | immutable index into the text | yes | no | a fresh document per parse; "reused" parses into the same document |
-| `json_view` (editable) | index into the text plus edits | yes | yes, in place | `json_editable_document`; keeps member order and number spellings |
 | yyjson | immutable (`yyjson_read`) | yes | via a mutable copy | |
 | simdjson DOM | immutable, parser reused | yes | no | "fresh" uses a new parser per parse |
 | simdjson On-Demand | none: forward-only, lazy | no | no | only traverse and select |

tests/benchmarks/json_view/bench_view.cpp

@@ -8,8 +8,7 @@
 
 // Same-feature-set benchmark: read-only JSON documents with random access.
 //
-//   json_view      nlohmann/json_view.hpp (fresh document per parse / reused;
+//   json_view      nlohmann/json_view.hpp (fresh document per parse / reused)
-//                  "(editable)": json_editable_document, same read API)
 //   yyjson         yyjson_read(): immutable document, random access
 //   simdjson DOM   dom::parser (reused, as recommended; "fresh": a new parser
 //                  per parse): immutable, random access
@@ -20,11 +19,7 @@
 //
 // Workloads: parse (build + free), traverse (visit everything, convert every
 // number, touch every string and key), select (a few fields per document),
-// dump (compact serialization of the parsed document), and parse+dump (a fresh
+// dump (compact serialization of the parsed document).
-// document, then its dump, in one timed call). json_view converts floating-point
-// numbers lazily (when read or dumped), yyjson and simdjson DOM while parsing:
-// for float-heavy documents, traverse (which includes the parse) and parse+dump
-// are the fair reading of the parse and dump rows.
 // All engines run interleaved in every round, each timed call after an untimed
 // one of the same engine; the best round is reported.
 #include <nlohmann/json_view.hpp>
@@ -48,8 +43,6 @@
 
 using nlohmann::json;
 using nlohmann::json_document;
-using nlohmann::json_editable_document;
-using nlohmann::json_editable_view;
 using nlohmann::json_view;
 
 static volatile double g_sink;
@@ -62,8 +55,7 @@ struct stats
 
 // ---------------- traversal ----------------
 
-template<class V>
+static void walk(json_view v, stats& st)
-static void walk_view(V v, stats& st)
 {
     ++st.nodes;
     switch (v.type())
@@ -72,42 +64,32 @@ static void walk_view(V v, stats& st)
             for (auto it = v.begin(); it != v.end(); ++it)
             {
                 st.str += it.key().size();
-                walk_view<V>(*it, st);
+                walk(*it, st);
             }
             break;
         case json::value_t::array:
-            for (const V e : v)
+            for (const json_view e : v)
             {
-                walk_view<V>(e, st);
+                walk(e, st);
             }
             break;
         case json::value_t::string:
             st.str += v.get_string().size();
             break;
         case json::value_t::number_integer:
-            st.num += static_cast<double>(v.template get<std::int64_t>());
+            st.num += static_cast<double>(v.get<std::int64_t>());
             break;
         case json::value_t::number_unsigned:
-            st.num += static_cast<double>(v.template get<std::uint64_t>());
+            st.num += static_cast<double>(v.get<std::uint64_t>());
             break;
         case json::value_t::number_float:
-            st.num += v.template get<double>();
+            st.num += v.get<double>();
             break;
         default:
             break;
     }
 }
 
-static void walk(json_view v, stats& st)
-{
-    walk_view<json_view>(v, st);
-}
-
-static void walk(json_editable_view v, stats& st)
-{
-    walk_view<json_editable_view>(v, st);
-}
-
 static void walk(const json& j, stats& st)
 {
     ++st.nodes;
@@ -318,21 +300,20 @@ static void walk(const boost::json::value& v, stats& st)
 // status (one tweet): id, user.screen_name, retweet_count
 // rpc: method, params.minuend, id
 
-template<class V>
+static double pick(const std::string& name, json_view r)
-static double pick_view(const std::string& name, V r)
 {
     double acc = 0;
     if (name == "twitter" || name == "status")
     {
-        auto one = [&](V s)
+        auto one = [&](json_view s)
         {
-            acc += static_cast<double>(s["id"].template get<std::uint64_t>());
+            acc += static_cast<double>(s["id"].get<std::uint64_t>());
             acc += static_cast<double>(s["user"]["screen_name"].get_string().size());
-            acc += static_cast<double>(s["retweet_count"].template get<std::int64_t>());
+            acc += static_cast<double>(s["retweet_count"].get<std::int64_t>());
         };
         if (name == "twitter")
         {
-            for (const V s : r["statuses"])
+            for (const json_view s : r["statuses"])
             {
                 one(s);
             }
@@ -344,20 +325,20 @@ static double pick_view(const std::string& name, V r)
     }
     else if (name == "citm_catalog")
     {
-        for (const V p : r["performances"])
+        for (const json_view p : r["performances"])
         {
-            acc += static_cast<double>(p["id"].template get<std::uint64_t>() + p["eventId"].template get<std::uint64_t>() + p["seatCategories"].size());
+            acc += static_cast<double>(p["id"].get<std::uint64_t>() + p["eventId"].get<std::uint64_t>() + p["seatCategories"].size());
         }
         acc += static_cast<double>(r["events"].size());
     }
     else if (name == "canada")
     {
-        const V g = r["features"][0]["geometry"];
+        const json_view g = r["features"][0]["geometry"];
         acc += static_cast<double>(r["type"].get_string().size() + g["type"].get_string().size() + g["coordinates"].size());
     }
     else if (name == "jeopardy")
     {
-        for (const V q : r)
+        for (const json_view q : r)
         {
             acc += q["round"].get_string() == "Final Jeopardy!" ? 1 : 0;
             acc += static_cast<double>(q["category"].get_string().size());
@@ -366,21 +347,11 @@ static double pick_view(const std::string& name, V r)
     else if (name == "rpc")
     {
         acc += static_cast<double>(r["method"].get_string().size());
-        acc += static_cast<double>(r["params"]["minuend"].template get<std::int64_t>() + r["id"].template get<std::int64_t>());
+        acc += static_cast<double>(r["params"]["minuend"].get<std::int64_t>() + r["id"].get<std::int64_t>());
     }
     return acc;
 }
 
-static double pick(const std::string& name, json_view r)
-{
-    return pick_view<json_view>(name, r);
-}
-
-static double pick(const std::string& name, json_editable_view r)
-{
-    return pick_view<json_editable_view>(name, r);
-}
-
 static double pick(const std::string& name, const json& r)
 {
     double acc = 0;
@@ -663,35 +634,15 @@ int main(int argc, char** argv)
         walk(json::parse(dc.text), a);
         auto d = json_document::parse(dc.text);
         walk(d.root(), b);
-        auto ed = json_editable_document::parse(dc.text);
-        stats e;
-        walk(ed.root(), e);
         yyjson_doc* y = yyjson_read(dc.text.data(), dc.text.size(), 0);
         walk(yyjson_doc_get_root(y), c);
         simdjson::dom::parser p;
         walk(p.parse(dc.text).value(), dd);
-        const bool ok = a.nodes == b.nodes && a.nodes == e.nodes && a.str == e.str && std::fabs(a.num - e.num) <= 1e-9 * std::fabs(a.num) && a.nodes == c.nodes && a.nodes == dd.nodes && a.str == b.str && a.str == c.str && a.str == dd.str
+        const bool ok = a.nodes == b.nodes && a.nodes == c.nodes && a.nodes == dd.nodes && a.str == b.str && a.str == c.str && a.str == dd.str
                         && std::fabs(a.num - b.num) <= 1e-9 * std::fabs(a.num) && std::fabs(a.num - c.num) <= 1e-9 * std::fabs(a.num);
-        const double pa = pick(dc.name, json::parse(dc.text)), pb = pick(dc.name, d.root()), pe = pick(dc.name, ed.root()), pc = pick(dc.name, yyjson_doc_get_root(y)), pd = pick(dc.name, p.parse(dc.text).value());
+        const double pa = pick(dc.name, json::parse(dc.text)), pb = pick(dc.name, d.root()), pc = pick(dc.name, yyjson_doc_get_root(y)), pd = pick(dc.name, p.parse(dc.text).value());
-        std::printf("check %-13s traverse %s select %s\n", dc.name.c_str(), ok ? "OK" : "MISMATCH", (pa == pb && pa == pe && pa == pc && pa == pd) ? "OK" : "MISMATCH");
+        std::printf("check %-13s traverse %s select %s\n", dc.name.c_str(), ok ? "OK" : "MISMATCH", (pa == pb && pa == pc && pa == pd) ? "OK" : "MISMATCH");
         yyjson_doc_free(y);
-
-        // the dumps of the engines may format floats differently, so only: every dump is non-empty, and the
-        // dump of json_view (also editable) and of json::parse parse back to the same number of nodes
-        const std::string dj = json::parse(dc.text).dump();
-        const std::string dv = d.root().dump();
-        const std::string de = ed.root().dump();
-        std::size_t yn = 0;
-        yyjson_doc* y2 = yyjson_read(dc.text.data(), dc.text.size(), 0);
-        char* yo = yyjson_write(y2, 0, &yn);
-        const bool dumps_ok = !dj.empty() && !dv.empty() && !de.empty() && yo != nullptr && yn > 0 && !simdjson::to_string(p.parse(dc.text).value()).empty();
-        std::free(yo);
-        yyjson_doc_free(y2);
-        stats sj_nodes, sv_nodes, se_nodes;
-        walk(json::parse(dj), sj_nodes);
-        walk(json::parse(dv), sv_nodes);
-        walk(json::parse(de), se_nodes);
-        std::printf("check %-13s dump %s\n", dc.name.c_str(), (dumps_ok && sj_nodes.nodes == a.nodes && sv_nodes.nodes == a.nodes && se_nodes.nodes == a.nodes) ? "OK" : "MISMATCH");
     }
 
     std::FILE* csv = std::fopen("bench_view.csv", "w");
@@ -718,7 +669,6 @@ int main(int argc, char** argv)
         workloads.push_back({"parse", {
                 {"json_view", [&] { auto d = json_document::parse(s); g_sink = static_cast<double>(d.node_count()); }},
                 {"json_view (reused)", [&] { reused.read(s); g_sink = static_cast<double>(reused.node_count()); }},
-                {"json_view (editable)", [&] { auto d = json_editable_document::parse(s); g_sink = static_cast<double>(d.root().size()); }},
                 {"yyjson", [&] { yyjson_doc* d = yyjson_read(s.data(), s.size(), 0); g_sink = static_cast<double>(yyjson_doc_get_val_count(d)); yyjson_doc_free(d); }},
                 {"simdjson DOM", [&] { auto e = sj.parse(ps).value_unsafe(); g_sink = e.is_object(); }},
                 {"simdjson DOM (fresh)", [&] { simdjson::dom::parser p; auto e = p.parse(ps).value_unsafe(); g_sink = e.is_object(); }},
@@ -730,7 +680,6 @@ int main(int argc, char** argv)
         workloads.push_back({"traverse", {
                 {"json_view", [&] { auto d = json_document::parse(s); stats st; walk(d.root(), st); g_sink = st.num; }},
                 {"json_view (reused)", [&] { reused.read(s); stats st; walk(reused.root(), st); g_sink = st.num; }},
-                {"json_view (editable)", [&] { auto d = json_editable_document::parse(s); stats st; walk(d.root(), st); g_sink = st.num; }},
                 {"yyjson", [&] { yyjson_doc* d = yyjson_read(s.data(), s.size(), 0); stats st; walk(yyjson_doc_get_root(d), st); g_sink = st.num; yyjson_doc_free(d); }},
                 {"simdjson DOM", [&] { stats st; walk(sj.parse(ps).value_unsafe(), st); g_sink = st.num; }},
                 {"simdjson OD", [&] { auto d = od.iterate(ps).value_unsafe(); stats st; walk_od(d.get_value().value_unsafe(), st); g_sink = st.num; }},
@@ -742,31 +691,15 @@ int main(int argc, char** argv)
         workloads.push_back({"select", {
                 {"json_view", [&] { auto d = json_document::parse(s); g_sink = pick(name, d.root()); }},
                 {"json_view (reused)", [&] { reused.read(s); g_sink = pick(name, reused.root()); }},
-                {"json_view (editable)", [&] { auto d = json_editable_document::parse(s); g_sink = pick(name, d.root()); }},
                 {"yyjson", [&] { yyjson_doc* d = yyjson_read(s.data(), s.size(), 0); g_sink = pick(name, yyjson_doc_get_root(d)); yyjson_doc_free(d); }},
                 {"simdjson DOM", [&] { g_sink = pick(name, sj.parse(ps).value_unsafe()); }},
                 {"simdjson OD", [&] { auto d = od.iterate(ps).value_unsafe(); g_sink = pick_od(name, d); }},
                 {"json::parse", [&] { json j = json::parse(s); g_sink = pick(name, j); }},
             }});
-        // pipeline: a fresh document, then a dump of it, in one timed call
-        // (simdjson DOM reuses its parser, as in the parse row); the traverse
-        // workload above is already parse+traverse
-        workloads.push_back({"parse+dump", {
-                {"json_view", [&] { auto d = json_document::parse(s); std::string o = d.root().dump(); g_sink = static_cast<double>(o.size()); }},
-                {"json_view (editable)", [&] { auto d = json_editable_document::parse(s); std::string o = d.root().dump(); g_sink = static_cast<double>(o.size()); }},
-                {"yyjson", [&] { yyjson_doc* d = yyjson_read(s.data(), s.size(), 0); std::size_t n = 0; char* o = yyjson_write(d, 0, &n); g_sink = static_cast<double>(n); std::free(o); yyjson_doc_free(d); }},
-                {"simdjson DOM", [&] { std::string o = simdjson::to_string(sj.parse(ps).value_unsafe()); g_sink = static_cast<double>(o.size()); }},
-#if JSON_VIEW_BENCH_BOOST
-                {"Boost.JSON", [&] { boost::json::monotonic_resource mr; auto v = boost::json::parse(s, &mr); std::string o = boost::json::serialize(v); g_sink = static_cast<double>(o.size()); }},
-#endif
-                {"json::parse", [&] { json j = json::parse(s); std::string o = j.dump(); g_sink = static_cast<double>(o.size()); }},
-            }});
         {
             // serialization of an already parsed document
             static json_document vd;
             vd.read(s);
-            static json_editable_document ed = json_editable_document::parse(s);
-            ed = json_editable_document::parse(s);
             static yyjson_doc* yd = nullptr;
             if (yd)
             {
@@ -780,7 +713,6 @@ int main(int argc, char** argv)
             jd = json::parse(s);
             workloads.push_back({"dump", {
                     {"json_view", [&] { std::string o = vd.root().dump(); g_sink = static_cast<double>(o.size()); }},
-                    {"json_view (editable)", [&] { std::string o = ed.root().dump(); g_sink = static_cast<double>(o.size()); }},
                     {"yyjson", [&] { std::size_t n = 0; char* o = yyjson_write(yd, 0, &n); g_sink = static_cast<double>(n); std::free(o); }},
                     {"simdjson DOM", [&] { std::string o = simdjson::to_string(se); g_sink = static_cast<double>(o.size()); }},
                     {"json::parse", [&] { std::string o = jd.dump(); g_sink = static_cast<double>(o.size()); }},
@@ -808,7 +740,7 @@ int main(int argc, char** argv)
                 }
             }
             const double ref = best[0];
-            std::printf("%-13s %-14s", dc.name.c_str(), wl.first.c_str());
+            std::printf("%-13s %-9s", dc.name.c_str(), wl.first.c_str());
             for (std::size_t k = 0; k < wl.second.size(); ++k)
             {
                 const double us = best[k] / 1e3;

tests/benchmarks/json_view/compare.py

@@ -239,8 +239,6 @@ def main():
     ap.add_argument('--download', action='store_true', help='use pinned downloads instead of system libraries')
     ap.add_argument('--no-boost', action='store_true', help='skip Boost.JSON')
     ap.add_argument('--native', action='store_true', help='compile for this CPU (-march=native / -mcpu=native)')
-    ap.add_argument('--aligned', action='store_true',
-                    help='also build and run with all functions (and loops) aligned, to make code layout artifacts visible')
     ap.add_argument('--rounds', type=int, default=30, help='rounds of bench_view (default: 30)')
     ap.add_argument('--corpus', nargs='*', default=[], help='more files for bench_corpus')
     ap.add_argument('--build-dir', default=os.path.join(HERE, 'build'), help='where to build (default: build/ next to this script)')
@@ -284,44 +282,30 @@ def main():
                 + ['-I' + d for d in lib.include])
             objects.append(obj)
 
-    cxx_version = output(cxx + ['--version'])
-    is_clang = 'clang' in cxx_version.lower()
-    # alignment flags: functions and (gcc) loops on 64-byte boundaries
-    align_flags = ['-mllvm', '-align-all-functions=6'] if is_clang else ['-falign-functions=64', '-falign-loops=64']
-
-    # the builds: the default one and, with --aligned, one with aligned code
-    variants = [('default build', args.build_dir, [])]
-    if args.aligned:
-        variants.append(('aligned build', os.path.join(args.build_dir, 'aligned'), align_flags))
-
-    corpus = [os.path.join(args.data, f) for f in DEFAULT_CORPUS] + args.corpus
-    # label -> {benchmark: output}
-    all_outputs = {}
-    for label, build_dir, extra in variants:
-        os.makedirs(build_dir, exist_ok=True)
     binaries = {}
     for bench in ['bench_view', 'bench_corpus', 'bench_edit']:
-            exe = os.path.join(build_dir, bench)
+        exe = os.path.join(args.build_dir, bench)
-            run(cxx + flags + extra + include + [os.path.join(HERE, bench + '.cpp')] + objects + link + ['-o', exe])
+        run(cxx + flags + include + [os.path.join(HERE, bench + '.cpp')] + objects + link + ['-o', exe])
         binaries[bench] = exe
 
     # run: bench_view on its documents, bench_corpus on those and the given files
+    corpus = [os.path.join(args.data, f) for f in DEFAULT_CORPUS] + args.corpus
     outputs = {}
-        outputs['bench_view'] = run([binaries['bench_view'], args.data, str(args.rounds)], cwd=build_dir,
+    outputs['bench_view'] = run([binaries['bench_view'], args.data, str(args.rounds)], cwd=args.build_dir,
                                 capture_output=True, text=True).stdout
-        outputs['bench_corpus'] = run([binaries['bench_corpus']] + corpus, cwd=build_dir,
+    outputs['bench_corpus'] = run([binaries['bench_corpus']] + corpus, cwd=args.build_dir,
                                   capture_output=True, text=True).stdout
-        outputs['bench_edit'] = run([binaries['bench_edit'], args.data, str(max(1, args.rounds // 2))], cwd=build_dir,
+    outputs['bench_edit'] = run([binaries['bench_edit'], args.data, str(max(1, args.rounds // 2))], cwd=args.build_dir,
                                 capture_output=True, text=True).stdout
     for name, text in outputs.items():
         print(text)
-        all_outputs[label] = outputs
 
     # results with their metadata
     now = datetime.datetime.now()
     host = re.sub(r'[^A-Za-z0-9-]+', '-', platform.node().split('.')[0]) or 'host'
     stem = os.path.join(HERE, 'results', f'{now:%Y-%m-%d}-{host}')
     os.makedirs(os.path.dirname(stem), exist_ok=True)
+    cxx_version = output(cxx + ['--version'])
     compiler_version = cxx_version.splitlines()[0] if cxx_version else ' '.join(cxx)
     meta = [
         ('date', f'{now:%Y-%m-%d %H:%M}'),
@@ -330,7 +314,6 @@ def main():
         ('OS', f'{platform.system()} {platform.release()} ({platform.machine()})'),
         ('compiler', compiler_version),
         ('flags', ' '.join(flags)),
-        ('aligned results', ('included (flags: ' + ' '.join(align_flags) + ')') if args.aligned else 'not included'),
         ('yyjson', libs['yyjson'].version),
         ('simdjson', libs['simdjson'].version),
         ('Boost.JSON', libs['boost'].version if with_boost else 'skipped (not found)'),
@@ -343,20 +326,15 @@ def main():
         f.write('| | |\n|---|---|\n')
         for key, value in meta:
             f.write(f'| {key} | {value} |\n')
-        for label, outputs in all_outputs.items():
-            # (without --aligned there is only the default build, and no extra heading level)
-            prefix = f'{label}: ' if args.aligned else ''
         for name, text in outputs.items():
-                f.write(f'\n## {prefix}{name}\n\n```\n{text.rstrip()}\n```\n')
+            f.write(f'\n## {name}\n\n```\n{text.rstrip()}\n```\n')
     with open(stem + '.csv', 'w', encoding='utf-8') as out:
         out.write(''.join(f'# {key}: {value}\n' for key, value in meta))
-        for label, build_dir, _ in variants:
         for name in ['bench_view', 'bench_corpus', 'bench_edit']:
-                path = os.path.join(build_dir, name + '.csv')
+            path = os.path.join(args.build_dir, name + '.csv')
             if os.path.isfile(path):
                 with open(path, encoding='utf-8') as f:
-                        # (the default build keeps its plain section names)
+                    out.write(f'# {name}\n' + f.read())
-                        out.write(f'# {name}' + (f' ({label})' if args.aligned else '') + '\n' + f.read())
     print(f'results: {stem}.md, {stem}.csv')
 
 

tests/src/unit-json_view_compare.cpp

@@ -0,0 +1,364 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
+// |  |  |__   |  |  | | | |  version 3.12.0
+// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
+//
+// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
+// SPDX-License-Identifier: MIT
+
+#include "doctest_compatibility.h"
+
+#include <nlohmann/json_view.hpp>
+using nlohmann::json;
+using nlohmann::ordered_json;
+using nlohmann::json_document;
+using nlohmann::ordered_json_editable_document;
+using nlohmann::json_view;
+using nlohmann::ordered_json_document;
+
+#include "json_view_test_helpers.hpp"
+using json_view_test::generator;
+
+#include <array>
+#include <cstddef>
+#include <string>
+#include <vector>
+
+// These tests were split off unit-json_view_dump.cpp, whose object file got too
+// large for the MinGW assembler ("file too big"). Like that file, this one is
+// also built with C++17, as it mentions JSON_HAS_CPP_17.
+
+TEST_CASE("json_view comparison")
+{
+    SECTION("equality of the values parse() produces")
+    {
+        generator g;
+        std::vector<std::string> texts;
+        for (int i = 0; i < 600; ++i)
+        {
+            std::string text;
+            g.value(text, 0);
+            texts.push_back(text);
+            // the same value written differently: sorted keys, canonical numbers
+            texts.push_back(json::parse(text).dump(1));
+        }
+        for (std::size_t i = 0; i + 2 < texts.size(); ++i)
+        {
+            for (std::size_t k = i; k < i + 3; ++k)
+            {
+                CAPTURE(texts[i])
+                CAPTURE(texts[k])
+                const json_document a = json_document::parse(texts[i]);
+                const json_document b = json_document::parse(texts[k]);
+                const json ja = json::parse(texts[i]);
+                const json jb = json::parse(texts[k]);
+                CHECK((a.root() == b.root()) == (ja == jb));
+                CHECK((a.root() != b.root()) == (ja != jb));
+                CHECK((a.root() == jb) == (ja == jb));
+                CHECK((jb == a.root()) == (ja == jb));
+                CHECK((a.root() != jb) == (ja != jb));
+                CHECK((jb != a.root()) == (ja != jb));
+
+                // ordered_json compares members in order
+                const ordered_json_document oa = ordered_json_document::parse(texts[i]);
+                const ordered_json_document ob = ordered_json_document::parse(texts[k]);
+                const ordered_json oja = ordered_json::parse(texts[i]);
+                const ordered_json ojb = ordered_json::parse(texts[k]);
+                CHECK((oa.root() == ob.root()) == (oja == ojb));
+                CHECK((oa.root() == ojb) == (oja == ojb));
+            }
+        }
+    }
+
+    SECTION("objects whose first keys differ or repeat")
+    {
+        const std::array<const char*, 17> texts =
+        {
+            {
+                R"({"a":1,"b":2})", R"({"a":1,"c":2})", R"({"b":1,"a":2})", R"({"a":1,"a":2,"b":3})", R"({"a":2,"b":3})",
+                R"({"a":1,"b":1,"a":2})", R"({"a":2,"b":1})", R"({"a":1,"a":2})", R"({"b":1})", R"({"a":1,"b":2,"c":3,"d":4,"e":5})",
+                R"({"a":1,"b":2,"c":3,"d":4,"f":5})", R"({"a":1,"b":2,"c":3,"a":4,"e":5})", R"({"a":4,"b":2,"c":3,"e":5})",
+                R"({"\u0061":1,"b":2})", R"({})", R"([{"a":1,"b":2}])", R"([{"a":1,"c":2}])"
+            }
+        };
+        for (const char* const x : texts)
+        {
+            for (const char* const y : texts)
+            {
+                CAPTURE(x)
+                CAPTURE(y)
+                const ordered_json_document dx = ordered_json_document::parse(x);
+                const ordered_json_document dy = ordered_json_document::parse(y);
+                const ordered_json_editable_document ex = ordered_json_editable_document::parse(x);
+                const ordered_json jx = ordered_json::parse(x);
+                const ordered_json jy = ordered_json::parse(y);
+                CHECK((dx.root() == dy.root()) == (jx == jy));
+                CHECK((dx.root() == jy) == (jx == jy));
+                CHECK((ex.root() == dy.root()) == (jx == jy));
+            }
+        }
+    }
+
+    SECTION("objects with duplicate keys, small and large")
+    {
+        // n members with keys in descending order; with duplicates, some keys
+        // repeat later (the first after unique ones in key order); in reverse,
+        // the members are in ascending key order
+        const auto object = [](int n, bool duplicates, bool reverse, int value)
+        {
+            std::string s = "{";
+            for (int i = 0; i < n; ++i)
+            {
+                const int k = reverse ? i : n - 1 - i;
+                s += (i != 0 ? ",\"k" : "\"k") + std::to_string(100 + k) + "\":" + std::to_string(value + k);
+            }
+            if (duplicates)
+            {
+                for (int k = n / 2; k < n; k += 3)
+                {
+                    s += ",\"k" + std::to_string(100 + k) + "\":" + std::to_string(value + k);
+                }
+            }
+            return s + "}";
+        };
+        std::vector<std::string> texts;
+        for (const int n :
+                {
+                    3, 16, 17, 40
+                })
+        {
+            for (const int flags :
+                    {
+                        0, 1, 2, 3
+                    })
+            {
+                texts.push_back(object(n, (flags & 1) != 0, (flags & 2) != 0, 0));
+            }
+            texts.push_back(object(n, true, false, 1)); // other values
+        }
+        // many objects in one comparison (working memory reused across objects)
+        std::string array = "[";
+        std::string array_other = "[";
+        for (std::size_t i = 0; i < texts.size(); ++i)
+        {
+            array += (i != 0 ? "," : "") + texts[i];
+            array_other += (i != 0 ? "," : "") + texts[texts.size() - 1 - i];
+        }
+        texts.push_back(array + "]");
+        texts.push_back(array_other + "]");
+        for (const std::string& x : texts)
+        {
+            for (const std::string& y : texts)
+            {
+                CAPTURE(x)
+                CAPTURE(y)
+                const ordered_json_document dx = ordered_json_document::parse(x);
+                const ordered_json_document dy = ordered_json_document::parse(y);
+                const ordered_json jx = ordered_json::parse(x);
+                const ordered_json jy = ordered_json::parse(y);
+                CHECK((dx.root() == dy.root()) == (jx == jy));
+                CHECK((dx.root() == jy) == (jx == jy));
+                const json_document ux = json_document::parse(x);
+                const json uy = json::parse(y);
+                CHECK((ux.root() == uy) == (json::parse(x) == uy));
+            }
+        }
+    }
+
+    SECTION("numbers, duplicate keys, member order")
+    {
+        const auto same = [](const char* x, const char* y)
+        {
+            const json_document dx = json_document::parse(x);
+            const json_document dy = json_document::parse(y);
+            return dx.root() == dy.root();
+        };
+        CHECK(same("1", "1.0"));
+        CHECK(same("[1, -1, 2.5]", "[1.0, -1.0, 25e-1]"));
+        CHECK(!same("1", "1.5"));
+        CHECK(same("18446744073709551615", "18446744073709551615"));
+        CHECK(same(R"({"a": 1, "a": 2})", R"({"a": 2})"));
+        CHECK(!same(R"({"a": 1, "a": 2})", R"({"a": 1})"));
+        CHECK(same(R"({"a": 1, "b": 2})", R"({"b": 2, "a": 1})"));
+        CHECK(!same(R"({"a": 1})", R"({"a": 1, "b": 2})"));
+        CHECK(!same("[1, 2]", "[2, 1]"));
+        CHECK(!same("\"a\"", "\"b\""));
+        CHECK(same("\"\\u00e9\"", "\"\xc3\xa9\""));
+        CHECK(!same("null", "false"));
+        CHECK(!same("[]", "{}"));
+        const ordered_json_document dup = ordered_json_document::parse(R"({"a": 1, "b": 2, "a": 3})");
+        const ordered_json_document last = ordered_json_document::parse(R"({"a": 3, "b": 2})");
+        CHECK(dup.root() == last.root());
+        // (== compares as parse() resolves duplicates, a lookup finds the first)
+        CHECK(dup.root()["a"].materialize() == 1);
+        CHECK(dup.root()["a"] != last.root()["a"]);
+        const ordered_json_document ab = ordered_json_document::parse(R"({"a": 1, "b": 2})");
+        const ordered_json_document ba = ordered_json_document::parse(R"({"b": 2, "a": 1})");
+        CHECK(ab.root() != ba.root());
+
+        // discarded values compare as basic_json's do
+        const json discarded(json::value_t::discarded);
+        CHECK((json_view() == json_view()) == (discarded == discarded)); // NOLINT(readability-container-size-empty): operator== is tested
+        CHECK((json_view() == discarded) == (discarded == discarded)); // NOLINT(readability-container-size-empty)
+        const json_document null_document = json_document::parse("null");
+        CHECK(!(json_view() == null_document.root())); // NOLINT(readability-container-size-empty)
+        CHECK(!(null_document.root() == discarded));
+    }
+
+    SECTION("values that are the same text, or the same value written differently, at any depth")
+    {
+        // nested arrays and objects around depths where the walk over equal text gives up
+        for (const int depth :
+                {
+                    1, 5, 47, 48, 49, 50, 60, 300
+                })
+        {
+            CAPTURE(depth)
+            std::string head;
+            std::string tail;
+            for (int i = 0; i < depth; ++i)
+            {
+                head += i % 2 == 0 ? R"({"k":[1,"s",{"x":true},)" : R"([null,2.5,{"y":)";
+                tail.insert(0, i % 2 == 0 ? "]}" : "}]");
+            }
+            // the same text, one number changed, and one number written differently
+            const auto with_number = [&](const char* number)
+            {
+                std::string result = head;
+                result += number;
+                result += tail;
+                return result;
+            };
+            const std::string text = with_number("7");
+            const std::string changed = with_number("8");
+            const std::string spelled = with_number("7.0");
+            const json_document a = json_document::parse(text);
+            const json_document b = json_document::parse(text);
+            const json_document c = json_document::parse(changed);
+            const json_document d = json_document::parse(spelled);
+            CHECK(a.root() == b.root());
+            CHECK(a.root() != c.root());
+            CHECK(c.root() != a.root());
+            CHECK(a.root() == d.root());
+            CHECK(d.root() == a.root());
+            CHECK(a.root() == json::parse(text));
+            CHECK(a.root() != json::parse(changed));
+            CHECK(json::parse(spelled) == a.root());
+            const nlohmann::json_editable_document e = nlohmann::json_editable_document::parse(text);
+            CHECK(a.root() == e.root());
+            CHECK(e.root() == a.root());
+            CHECK(c.root() != e.root());
+            CHECK(e.root() == e.root());
+            const ordered_json_document oa = ordered_json_document::parse(text);
+            const ordered_json_document oc = ordered_json_document::parse(changed);
+            CHECK(oa.root() != oc.root());
+            CHECK(oa.root() == ordered_json::parse(text));
+            CHECK(oc.root() != ordered_json::parse(text));
+        }
+
+        // not the same text, but the same value
+        const auto same = [](const char* x, const char* y)
+        {
+            const json_document dx = json_document::parse(x);
+            const json_document dy = json_document::parse(y);
+            const bool equal = dx.root() == dy.root();
+            CHECK(equal == (json::parse(x) == json::parse(y)));
+            CHECK(equal == (dx.root() == json::parse(y)));
+            return equal;
+        };
+        CHECK(same(R"({"a":1,"a":2})", R"({"a":3,"a":2})"));
+        CHECK(same(R"({"a":1,"b":[1,{"c":2,"c":3}]})", R"({"b":[1,{"c":9,"c":3}],"a":1})"));
+        CHECK(!same(R"({"a":1,"a":2})", R"({"a":2,"a":3})"));
+        CHECK(same("[1.0,-0,0,1e2]", "[1.00,0,-0,100.0]"));
+        CHECK(same(R"(["\u00e9","\n"])", "[\"\xc3\xa9\",\"\\n\"]"));
+        CHECK(!same(R"({"a":[1,2,{"b":null}]})", R"({"a":[1,2,{"b":false}]})"));
+        CHECK(!same(R"({"a":[1,2,{"b":null}]})", R"({"a":[1,2,{"c":null}]})"));
+        CHECK(!same(R"({"a":[1,2,{"b":null}]})", R"({"a":[1,2,{"b":null,"c":1}]})"));
+
+        // edited documents: moved sequences, links, and values of new nodes
+        nlohmann::json_editable_document edited = nlohmann::json_editable_document::parse(R"({"a":[1,2,3],"b":{"c":"d"},"e":0.5})");
+        const json_document plain = json_document::parse(R"({"a":[1,2,3,4],"b":{"c":"x","y":null},"e":0.5,"z":[]})");
+        edited.push_back(edited.root()["a"], 4);
+        edited.set(edited.root()["b"], "c", "x");
+        edited.set(edited.root()["b"], "y", nullptr);
+        edited.set(edited.root(), "z", json::array());
+        CHECK(edited.root() == plain.root());
+        CHECK(plain.root() == edited.root());
+        edited.erase(edited.root()["a"], 0);
+        CHECK(edited.root() != plain.root());
+        CHECK(edited.root()["a"] == json::parse("[2,3,4]"));
+        const json_document tail = json_document::parse("[2,3,4]");
+        CHECK(edited.root()["a"] == tail.root());
+    }
+
+    SECTION("large documents, with a difference at any place")
+    {
+        const auto make = [](std::size_t count, std::size_t changed, bool swap_members)
+        {
+            std::string text = R"({"b":1,"list":[)";
+            for (std::size_t i = 0; i < count; ++i)
+            {
+                text += (i != 0 ? "," : "");
+                const std::string id = std::to_string(i == changed ? i + 1 : i);
+                if (swap_members && i % 3 == 0)
+                {
+                    text += R"({"v":[1.5,"s",{"k":)";
+                    text += id;
+                    text += R"(}],"id":)";
+                    text += id;
+                    text += "}";
+                }
+                else
+                {
+                    text += R"({"id":)";
+                    text += id;
+                    text += R"(,"v":[1.5,"s",{"k":)";
+                    text += id;
+                    text += "}]}";
+                }
+            }
+            return text + R"(],"a":{"y":2,"x":3}})";
+        };
+        const std::size_t count = 3000;
+        for (const std::size_t changed :
+                {
+                    count, std::size_t{0}, std::size_t{1}, count / 2, count - 1
+                })
+        {
+            for (const bool swap :
+                    {
+                        false, true
+                    })
+            {
+                CAPTURE(changed)
+                CAPTURE(swap)
+                const std::string text_a = make(count, count, false);
+                const std::string text_b = make(count, changed, swap);
+                const json_document a = json_document::parse(text_a);
+                const json_document b = json_document::parse(text_b);
+                const bool equal = changed == count;
+                CHECK((a.root() == b.root()) == equal);
+                CHECK((b.root() == a.root()) == equal);
+                CHECK((a.root() == json::parse(text_b)) == equal);
+                CHECK((json::parse(text_b) == a.root()) == equal);
+                CHECK((a.root()["list"] == b.root()["list"]) == equal);
+                const ordered_json_document oa = ordered_json_document::parse(text_a);
+                const ordered_json_document ob = ordered_json_document::parse(text_b);
+                CHECK((oa.root() == ob.root()) == (equal && !swap));
+                CHECK((oa.root() == ordered_json::parse(text_b)) == (equal && !swap));
+            }
+        }
+    }
+
+    SECTION("deep nesting")
+    {
+        const std::string deep = std::string(100000, '[') + std::string(100000, ']');
+        const json_document a = json_document::parse(deep);
+        const json_document b = json_document::parse(deep);
+        CHECK(a.root() == b.root());
+        CHECK(a.root() == json::parse(deep));
+        const std::string other = std::string(100000, '[') + "1" + std::string(100000, ']');
+        const json_document c = json_document::parse(other);
+        CHECK(a.root() != c.root());
+    }
+}

tests/src/unit-json_view_dump.cpp

@@ -432,101 +432,6 @@ TEST_CASE("json_view dump")
     }
 }
 
-TEST_CASE("json_view comparison")
-{
-    SECTION("equality of the values parse() produces")
-    {
-        generator g;
-        std::vector<std::string> texts;
-        for (int i = 0; i < 600; ++i)
-        {
-            std::string text;
-            g.value(text, 0);
-            texts.push_back(text);
-            // the same value written differently: sorted keys, canonical numbers
-            texts.push_back(json::parse(text).dump(1));
-        }
-        for (std::size_t i = 0; i + 2 < texts.size(); ++i)
-        {
-            for (std::size_t k = i; k < i + 3; ++k)
-            {
-                CAPTURE(texts[i])
-                CAPTURE(texts[k])
-                const json_document a = json_document::parse(texts[i]);
-                const json_document b = json_document::parse(texts[k]);
-                const json ja = json::parse(texts[i]);
-                const json jb = json::parse(texts[k]);
-                CHECK((a.root() == b.root()) == (ja == jb));
-                CHECK((a.root() != b.root()) == (ja != jb));
-                CHECK((a.root() == jb) == (ja == jb));
-                CHECK((jb == a.root()) == (ja == jb));
-                CHECK((a.root() != jb) == (ja != jb));
-                CHECK((jb != a.root()) == (ja != jb));
-
-                // ordered_json compares members in order
-                const ordered_json_document oa = ordered_json_document::parse(texts[i]);
-                const ordered_json_document ob = ordered_json_document::parse(texts[k]);
-                const ordered_json oja = ordered_json::parse(texts[i]);
-                const ordered_json ojb = ordered_json::parse(texts[k]);
-                CHECK((oa.root() == ob.root()) == (oja == ojb));
-                CHECK((oa.root() == ojb) == (oja == ojb));
-            }
-        }
-    }
-
-    SECTION("numbers, duplicate keys, member order")
-    {
-        const auto same = [](const char* x, const char* y)
-        {
-            const json_document dx = json_document::parse(x);
-            const json_document dy = json_document::parse(y);
-            return dx.root() == dy.root();
-        };
-        CHECK(same("1", "1.0"));
-        CHECK(same("[1, -1, 2.5]", "[1.0, -1.0, 25e-1]"));
-        CHECK(!same("1", "1.5"));
-        CHECK(same("18446744073709551615", "18446744073709551615"));
-        CHECK(same(R"({"a": 1, "a": 2})", R"({"a": 2})"));
-        CHECK(!same(R"({"a": 1, "a": 2})", R"({"a": 1})"));
-        CHECK(same(R"({"a": 1, "b": 2})", R"({"b": 2, "a": 1})"));
-        CHECK(!same(R"({"a": 1})", R"({"a": 1, "b": 2})"));
-        CHECK(!same("[1, 2]", "[2, 1]"));
-        CHECK(!same("\"a\"", "\"b\""));
-        CHECK(same("\"\\u00e9\"", "\"\xc3\xa9\""));
-        CHECK(!same("null", "false"));
-        CHECK(!same("[]", "{}"));
-        const ordered_json_document dup = ordered_json_document::parse(R"({"a": 1, "b": 2, "a": 3})");
-        const ordered_json_document last = ordered_json_document::parse(R"({"a": 3, "b": 2})");
-        CHECK(dup.root() == last.root());
-        // (== compares as parse() resolves duplicates, a lookup finds the first)
-        CHECK(dup.root()["a"].materialize() == 1);
-        CHECK(dup.root()["a"] != last.root()["a"]);
-        const ordered_json_document ab = ordered_json_document::parse(R"({"a": 1, "b": 2})");
-        const ordered_json_document ba = ordered_json_document::parse(R"({"b": 2, "a": 1})");
-        CHECK(ab.root() != ba.root());
-
-        // discarded values compare as basic_json's do
-        const json discarded(json::value_t::discarded);
-        CHECK((json_view() == json_view()) == (discarded == discarded)); // NOLINT(readability-container-size-empty): operator== is tested
-        CHECK((json_view() == discarded) == (discarded == discarded)); // NOLINT(readability-container-size-empty)
-        const json_document null_document = json_document::parse("null");
-        CHECK(!(json_view() == null_document.root())); // NOLINT(readability-container-size-empty)
-        CHECK(!(null_document.root() == discarded));
-    }
-
-    SECTION("deep nesting")
-    {
-        const std::string deep = std::string(100000, '[') + std::string(100000, ']');
-        const json_document a = json_document::parse(deep);
-        const json_document b = json_document::parse(deep);
-        CHECK(a.root() == b.root());
-        CHECK(a.root() == json::parse(deep));
-        const std::string other = std::string(100000, '[') + "1" + std::string(100000, ']');
-        const json_document c = json_document::parse(other);
-        CHECK(a.root() != c.root());
-    }
-}
-
 TEST_CASE("json_view large objects")
 {
     // objects with 128 members or more are looked up with a hash index

tests/src/unit-json_view_image.cpp

@@ -682,6 +682,64 @@ TEST_CASE("json_view images: ownership")
 #if !defined(JSON_NOEXCEPTION)
 TEST_CASE("json_view images: errors")
 {
+    SECTION("float tokens: a changed byte is accepted if the text is still a number with the digits the node records")
+    {
+        for (const char* const token :
+                {
+                    "-12.375", "0.5", "123456.0", "-0.0", "9999999999999999999.5", "0.000000000000000000000001", "1.25e10", "5E-3"
+                })
+        {
+            CAPTURE(token)
+            const std::string text = std::string("[") + token + "]";
+            const json_document d = json_document::parse(text);
+            const std::vector<std::uint8_t> image = d.save();
+            const std::size_t at = text_at(image) + 1; // the first byte of the token
+            const std::uint16_t recorded = node_at(image, 1).extra;
+            CHECK(loaded_dump(image) == json::parse(text).dump());
+            for (std::size_t pos = 0; token[pos] != '\0'; ++pos)
+            {
+                for (unsigned int byte = 0; byte < 256; ++byte)
+                {
+                    std::vector<std::uint8_t> changed = image;
+                    changed[at + pos] = static_cast<std::uint8_t>(byte);
+                    std::string t = token;
+                    t[pos] = static_cast<char>(byte);
+                    // the digits of the integer part and of the fraction of the changed token
+                    std::size_t integer = 0;
+                    std::size_t fraction = 0;
+                    std::size_t k = (t[0] == '-') ? 1 : 0;
+                    for (; k < t.size() && t[k] >= '0' && t[k] <= '9'; ++k)
+                    {
+                        ++integer;
+                    }
+                    if (k < t.size() && t[k] == '.')
+                    {
+                        for (++k; k < t.size() && t[k] >= '0' && t[k] <= '9'; ++k)
+                        {
+                            ++fraction;
+                        }
+                    }
+                    // (as a JSON text, the token may have white space around it)
+                    const bool float_token = json::accept(t) && t.find_first_of(std::string(" \t\r\n\0", 5)) == std::string::npos && (t.find('.') != std::string::npos || t.find_first_of("eE") != std::string::npos) // NOLINT(abseil-string-find-str-contains)
+                                             && ((integer | (fraction << 8U)) == recorded);
+                    CAPTURE(pos)
+                    CAPTURE(byte)
+                    std::string result;
+                    try
+                    {
+                        result = loaded_dump(changed);
+                    }
+                    catch (const json::parse_error& e)
+                    {
+                        CHECK(std::string(e.what()) == check_failed);
+                        result = "rejected";
+                    }
+                    CHECK((result != "rejected") == float_token);
+                }
+            }
+        }
+    }
+
     SECTION("invalid UTF-8 of a decoded string: the compact dump writes it, the others throw")
     {
         const json_document d = json_document::parse(R"({"k\n":"\u00e9x"})");