Check the float tokens of a json_document image without a sort and a scan of every character

load(image_check::full) checked every float token of an image by sorting
the token ranges, scanning the token character by character, and comparing
the digit layout with the node's. Now:

- the ranges are sorted only if they are not sorted already (save() writes
  them in the order of the nodes, so they are);
- a token of the shape [-]digits.digits whose digit counts are the ones the
  node records (nearly all of them) is accepted by checking its digits eight
  at a time, without the general scan;
- the general scan skips runs of digits eight at a time.

Damaged tokens are still rejected as before: the check accepts exactly the
tokens that the general scan accepts.

Instructions of load(image_check::full) (develop -> now):

  macOS arm64        canada 44.6M -> 30.9M (-31 %), jeopardy 11.3M -> 10.7M,
                     citm 10.4M -> 10.0M, twitter 5.06M -> 4.94M
  Linux GCC 13       canada -50 %, jeopardy -43 %, twitter -31 %, citm -28 %
  Linux Clang 18     canada -42 %, jeopardy -48 %, twitter -35 %, citm -32 %

image_check::bounds is unchanged (within 0.4 %).

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

include/nlohmann/detail/view/image.hpp

@@ -255,6 +255,82 @@ 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
+{
+    constexpr std::uint64_t ones = 0x0101010101010101ull;
+    const auto digits = [](const unsigned char* q)
+    {
+        const std::uint64_t x = read_eight_bytes(q) ^ (ones * 0x30u);
+        return (((x + (ones * 0x76u)) | x) & (ones * 0x80u)) == 0;
+    };
+    if (n >= 8)
+    {
+        std::size_t i = 0;
+        for (; 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 +349,7 @@ inline bool scan_number_token(const unsigned char* s, std::size_t len, number_to
     }
     else if (*p >= '1' && *p <= '9')
     {
-        do
-        {
-            ++p;
-        }
-        while (p != e && is_digit(*p));
+        p = digit_run(p + 1, e);
     }
     else
     {
@@ -289,10 +361,7 @@ 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;
-        }
+        p = digit_run(p, e);
         if (p == f0)
         {
             return false;
@@ -403,10 +472,15 @@ 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 +502,8 @@ 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 +514,11 @@ 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 +528,18 @@ 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;
-        if (!scan_number_token(s, r.len, t) || !float_token_finite(s, r.len, t))
+        std::uint16_t layout = r.extra;
+        if (!plain_float_token(s, r.len, r.extra))
         {
-            return false;
+            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)
+            layout = float_layout(t);
         }
-        // the digit layout the parser records (or "many", as compaction writes it)
-        const std::uint16_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)

single_include/nlohmann/json_view.hpp

@@ -5712,6 +5712,82 @@ 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
+{
+    constexpr std::uint64_t ones = 0x0101010101010101ull;
+    const auto digits = [](const unsigned char* q)
+    {
+        const std::uint64_t x = read_eight_bytes(q) ^ (ones * 0x30u);
+        return (((x + (ones * 0x76u)) | x) & (ones * 0x80u)) == 0;
+    };
+    if (n >= 8)
+    {
+        std::size_t i = 0;
+        for (; 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)
 {
@@ -5730,11 +5806,7 @@ inline bool scan_number_token(const unsigned char* s, std::size_t len, number_to
     }
     else if (*p >= '1' && *p <= '9')
     {
-        do
-        {
-            ++p;
-        }
-        while (p != e && is_digit(*p));
+        p = digit_run(p + 1, e);
     }
     else
     {
@@ -5746,10 +5818,7 @@ 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;
-        }
+        p = digit_run(p, e);
         if (p == f0)
         {
             return false;
@@ -5860,10 +5929,15 @@ 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)
     {
@@ -5885,7 +5959,8 @@ 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)
         {
@@ -5896,7 +5971,11 @@ 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())
@@ -5906,14 +5985,18 @@ 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;
-        if (!scan_number_token(s, r.len, t) || !float_token_finite(s, r.len, t))
+        std::uint16_t layout = r.extra;
+        if (!plain_float_token(s, r.len, r.extra))
         {
-            return false;
+            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)
+            layout = float_layout(t);
         }
-        // the digit layout the parser records (or "many", as compaction writes it)
-        const std::uint16_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)

tests/src/unit-json_view_image.cpp

@@ -682,6 +682,66 @@ TEST_CASE("json_view images: ownership")
 #if !defined(JSON_NOEXCEPTION)
 TEST_CASE("json_view images: errors")
 {
+#if !defined(JSON_NOEXCEPTION)
+    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)
+                                             && ((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);
+                }
+            }
+        }
+    }
+#endif
+
     SECTION("a literal as the root: dump() after loading")
     {
         for (const char* text :