From 13d2b3e224df07f1019d92d523b13f17e310031f Mon Sep 17 00:00:00 2001 From: Niels Lohmann Date: Fri, 9 Oct 2026 23:20:51 +0200 Subject: [PATCH 1/4] Return the first member of duplicate keys from lookups again Looking up the last member of a duplicate key cannot stop at a match, so every lookup scanned the whole object (1.6 to 3.4 times slower for small objects). operator[](key), at, find, value, contains, count, and JSON pointer resolution return the first member again, as yyjson and simdjson do; materialize() and get() keep the last value, as parse(). The documentation says so in the feature page and on each lookup page, and explains how to get the value parse() would give. The integer index templates and the discarded chaining of operator[] stay. Signed-off-by: Niels Lohmann --- docs/mkdocs/docs/api/basic_json_view/at.md | 13 ++++- docs/mkdocs/docs/api/basic_json_view/begin.md | 2 +- .../docs/api/basic_json_view/contains.md | 9 ++- docs/mkdocs/docs/api/basic_json_view/count.md | 11 +++- docs/mkdocs/docs/api/basic_json_view/find.md | 11 +++- docs/mkdocs/docs/api/basic_json_view/get.md | 6 +- docs/mkdocs/docs/api/basic_json_view/items.md | 6 +- .../docs/api/basic_json_view/operator[].md | 21 ++++--- docs/mkdocs/docs/api/basic_json_view/value.md | 13 ++++- .../docs/examples/basic_json_view__items.cpp | 6 +- .../examples/basic_json_view__items.output | 2 +- docs/mkdocs/docs/features/json_view.md | 57 +++++++++++++++---- include/nlohmann/detail/view/lookup.hpp | 16 +++--- include/nlohmann/json_view.hpp | 10 ++-- tests/src/unit-json_view.cpp | 50 ++++++++-------- 15 files changed, 153 insertions(+), 80 deletions(-) diff --git a/docs/mkdocs/docs/api/basic_json_view/at.md b/docs/mkdocs/docs/api/basic_json_view/at.md index b5deab72c..a0a57c9bc 100644 --- a/docs/mkdocs/docs/api/basic_json_view/at.md +++ b/docs/mkdocs/docs/api/basic_json_view/at.md @@ -15,7 +15,7 @@ basic_json_view at(IntegerType idx) const; basic_json_view at(const json_pointer& ptr) const; ``` -1. Returns the value of the object member with key `key` -- the last one, should the key occur more than once (see +1. Returns the value of the object member with key `key` -- the first one, should the key occur more than once (see [Notes on duplicate keys](operator[].md#notes)). 2. Returns the array element at index `idx`. The template accepts every integer type except `#!cpp bool` and `#!cpp std::size_t` and forwards to the `size_type` overload, as for [`operator[]`](operator[].md); a negative @@ -35,7 +35,7 @@ basic_json_view at(const json_pointer& ptr) const; ## Return value -1. the value of the last member with key `key` +1. the value of the first member with key `key` 2. the element at index `idx` 3. the value `ptr` resolves to, starting at this value @@ -75,7 +75,7 @@ None of these exceptions carry a [`JSON_DIAGNOSTICS`](../macros/json_diagnostics ## Complexity 1. Linear in the number of members: as for [`ordered_json`](../ordered_json.md), members are compared one after - another, in document order, scanning all of them, since the last match is wanted. Each comparison first checks the + another, in document order, stopping at the first match. Each comparison first checks the key's length -- already known from the index, without reading the key bytes -- before comparing its content. 2. Linear in `idx`: elements are skipped one at a time from the first one, since they are not a fixed size in the index (unlike `BasicJsonType`'s array, which is random-access). @@ -84,6 +84,13 @@ None of these exceptions carry a [`JSON_DIAGNOSTICS`](../macros/json_diagnostics ## Notes +!!! warning "Duplicate keys: the first member wins" + + If the source text repeats a key, this resolves to the *first* member with it, not to the last one that + [`materialize()`](materialize.md) and `parse()` keep. See the [Notes on duplicate keys](operator[].md#notes) of + `operator[]` and [Duplicate keys](../../features/json_view.md#duplicate-keys) for the reasons and for how to get + the last value. + Unlike [`operator[]`](operator[].md), which returns a [discarded](is_discarded.md) view for a missing key or an out-of-range index, `at` always throws -- exactly as `BasicJsonType::at` does, and with the same messages, so existing error handling written against `BasicJsonType::at` keeps working unchanged when switched to a view. This diff --git a/docs/mkdocs/docs/api/basic_json_view/begin.md b/docs/mkdocs/docs/api/basic_json_view/begin.md index f9c43802f..ae2665ee9 100644 --- a/docs/mkdocs/docs/api/basic_json_view/begin.md +++ b/docs/mkdocs/docs/api/basic_json_view/begin.md @@ -24,7 +24,7 @@ Constant. For an object, iteration visits **every** member, including all occurrences of a duplicate key -- unlike [`operator[]`](operator[].md), [`at`](at.md), [`find`](find.md), [`contains`](contains.md), and [`count`](count.md), -which all resolve to the *last* member with a given key. See the +which all resolve to the *first* member with a given key. See the [Notes on duplicate keys](operator[].md#notes) of `operator[]`. Because objects are iterated in document order rather than sorted by key, the order seen here can differ from what diff --git a/docs/mkdocs/docs/api/basic_json_view/contains.md b/docs/mkdocs/docs/api/basic_json_view/contains.md index 7c1e706cd..5094fe25c 100644 --- a/docs/mkdocs/docs/api/basic_json_view/contains.md +++ b/docs/mkdocs/docs/api/basic_json_view/contains.md @@ -33,7 +33,7 @@ No-throw guarantee: this function never throws exceptions. ## Complexity 1. Linear in the number of members: as for [`ordered_json`](../ordered_json.md), members are compared one after - another, in document order, scanning all of them, since the last match is wanted. Each comparison first checks the + another, in document order, stopping at the first match. Each comparison first checks the key's length -- already known from the index, without reading the key bytes -- before comparing its content. 2. Linear in the number of reference tokens of `ptr` and, for each token, in the number of members of the object at that level or the index into the array -- as for [`operator[]`](operator[].md#complexity) and @@ -41,6 +41,13 @@ No-throw guarantee: this function never throws exceptions. ## Notes +!!! warning "Duplicate keys: the first member wins" + + If the source text repeats a key, this resolves to the *first* member with it, not to the last one that + [`materialize()`](materialize.md) and `parse()` keep. See the [Notes on duplicate keys](operator[].md#notes) of + `operator[]` and [Duplicate keys](../../features/json_view.md#duplicate-keys) for the reasons and for how to get + the last value. + Overload 1 always returns `#!cpp false` when the value is not an object -- including a [discarded](is_discarded.md) view. diff --git a/docs/mkdocs/docs/api/basic_json_view/count.md b/docs/mkdocs/docs/api/basic_json_view/count.md index 7e0091d90..30d90b8e1 100644 --- a/docs/mkdocs/docs/api/basic_json_view/count.md +++ b/docs/mkdocs/docs/api/basic_json_view/count.md @@ -24,11 +24,18 @@ No-throw guarantee: this function never throws exceptions. ## Complexity Linear in the number of members: as for [`ordered_json`](../ordered_json.md), members are compared one after another, -in document order, scanning all of them, since the last match is wanted. Each comparison first checks the key's length +in document order, stopping at the first match. Each comparison first checks the key's length -- already known from the index, without reading the key bytes -- before comparing its content. ## Notes +!!! warning "Duplicate keys: the first member wins" + + If the source text repeats a key, this resolves to the *first* member with it, not to the last one that + [`materialize()`](materialize.md) and `parse()` keep. See the [Notes on duplicate keys](operator[].md#notes) of + `operator[]` and [Duplicate keys](../../features/json_view.md#duplicate-keys) for the reasons and for how to get + the last value. + This method always returns `#!cpp 0` when the value is not an object -- including a [discarded](is_discarded.md) view. @@ -36,7 +43,7 @@ Unlike [`BasicJsonType::count()`](../basic_json/count.md), whose return value ca an `ObjectType` that allows multiple entries per key, `count()` here never does: it is exactly [`contains()`](contains.md) as `#!cpp 0`/`#!cpp 1`. This holds even if the source text has a duplicate key -- see the [Notes on duplicate keys](operator[].md#notes) of `operator[]` -- because a `#!cpp count() > 1` result would require -counting every member with a matching key (the lookup functions resolve to the *last* one). +counting every member with a matching key (the lookup functions resolve to the *first* one). ## Examples diff --git a/docs/mkdocs/docs/api/basic_json_view/find.md b/docs/mkdocs/docs/api/basic_json_view/find.md index d2323353a..bb0cab041 100644 --- a/docs/mkdocs/docs/api/basic_json_view/find.md +++ b/docs/mkdocs/docs/api/basic_json_view/find.md @@ -6,7 +6,7 @@ iterator find(const char* key) const; iterator find(const string_t& key) const; ``` -Finds a member with key `key` -- the last one, should the key occur more than once (see +Finds a member with key `key` -- the first one, should the key occur more than once (see [Notes on duplicate keys](operator[].md#notes)). If the value is not an object, or no member has this key, [`end()`](end.md) is returned. @@ -26,11 +26,18 @@ No-throw guarantee: this function never throws exceptions. ## Complexity Linear in the number of members: as for [`ordered_json`](../ordered_json.md), members are compared one after another, -in document order, scanning all of them, since the last match is wanted. Each comparison first checks the key's length +in document order, stopping at the first match. Each comparison first checks the key's length -- already known from the index, without reading the key bytes -- before comparing its content. ## Notes +!!! warning "Duplicate keys: the first member wins" + + If the source text repeats a key, this resolves to the *first* member with it, not to the last one that + [`materialize()`](materialize.md) and `parse()` keep. See the [Notes on duplicate keys](operator[].md#notes) of + `operator[]` and [Duplicate keys](../../features/json_view.md#duplicate-keys) for the reasons and for how to get + the last value. + Unlike [`BasicJsonType::find`](../basic_json/find.md), which always returns `#!cpp end()` for a non-object type, this also does so for a [discarded](is_discarded.md) view -- there is no separate "invalid" iterator to return. diff --git a/docs/mkdocs/docs/api/basic_json_view/get.md b/docs/mkdocs/docs/api/basic_json_view/get.md index c3bb85790..d8ec333c9 100644 --- a/docs/mkdocs/docs/api/basic_json_view/get.md +++ b/docs/mkdocs/docs/api/basic_json_view/get.md @@ -87,9 +87,9 @@ exception thrown while converting through `materialize()` (the last bullet) is d !!! info "Duplicate keys" `#!cpp std::map`/`#!cpp std::unordered_map` conversions keep the *last* value of a repeated key, like - [`materialize()`](materialize.md) and [`BasicJsonType::parse()`](../basic_json/parse.md) do. This is the member - [`operator[]`](operator[].md)/[`at`](at.md)/[`find`](find.md)/[`contains`](contains.md) resolve to, too (see the - [Notes on duplicate keys](operator[].md#notes)). + [`materialize()`](materialize.md) and [`BasicJsonType::parse()`](../basic_json/parse.md) do. This is the opposite + of [`operator[]`](operator[].md)/[`at`](at.md)/[`find`](find.md)/[`contains`](contains.md), which resolve to the + *first* occurrence (see the [Notes on duplicate keys](operator[].md#notes)). !!! info "No pointers, references, or implicit conversion" diff --git a/docs/mkdocs/docs/api/basic_json_view/items.md b/docs/mkdocs/docs/api/basic_json_view/items.md index 8e13852da..d54f8d723 100644 --- a/docs/mkdocs/docs/api/basic_json_view/items.md +++ b/docs/mkdocs/docs/api/basic_json_view/items.md @@ -48,7 +48,7 @@ Constant. As for [`begin()`](begin.md)/[`end()`](end.md), `items()` visits **every** member of an object, including all occurrences of a duplicate key -- unlike [`operator[]`](operator[].md), [`at`](at.md), [`find`](find.md), -[`contains`](contains.md), and [`count`](count.md), which resolve to the *last* member with a given key. See the +[`contains`](contains.md), and [`count`](count.md), which resolve to the *first* member with a given key. See the [Notes on duplicate keys](operator[].md#notes) of `operator[]`. !!! danger "Lifetime issues" @@ -63,8 +63,8 @@ occurrences of a duplicate key -- unlike [`operator[]`](operator[].md), [`at`](a The example below shows a settings object whose source text records every update to a key as a duplicate member, in the order they happened. `items()` walks all of them, so the update history is visible, while - [`operator[]`](operator[].md) sees the *last* one, and so does [`materialize()`](materialize.md) -- like - [`BasicJsonType::parse()`](../basic_json/parse.md). + [`operator[]`](operator[].md) only ever sees the *first* one and [`materialize()`](materialize.md) -- like + [`BasicJsonType::parse()`](../basic_json/parse.md) -- keeps only the *last*. ```cpp --8<-- "examples/basic_json_view__items.cpp" diff --git a/docs/mkdocs/docs/api/basic_json_view/operator[].md b/docs/mkdocs/docs/api/basic_json_view/operator[].md index 53d95bed0..00ab1e9ac 100644 --- a/docs/mkdocs/docs/api/basic_json_view/operator[].md +++ b/docs/mkdocs/docs/api/basic_json_view/operator[].md @@ -15,7 +15,7 @@ basic_json_view operator[](IntegerType idx) const; basic_json_view operator[](const json_pointer& ptr) const; ``` -1. Returns the value of the object member with key `key` -- the last one, should the key occur more than once (see +1. Returns the value of the object member with key `key` -- the first one, should the key occur more than once (see the [Notes](#notes) below) -- or a [discarded](is_discarded.md) view if there is no such member. 2. Returns the array element at index `idx`, or a [discarded](is_discarded.md) view if `idx` is out of range. The template accepts every integer type except `#!cpp bool` and `#!cpp std::size_t` (`#!cpp int`, `#!cpp unsigned`, @@ -38,7 +38,7 @@ basic_json_view operator[](const json_pointer& ptr) const; ## Return value -1. the value of the last member with key `key`, or a discarded view if no member has this key (or if this view is +1. the value of the first member with key `key`, or a discarded view if no member has this key (or if this view is [discarded](is_discarded.md)) 2. the element at index `idx`, or a discarded view if `#!cpp idx >= size()` or `idx` is negative (or if this view is [discarded](is_discarded.md)) @@ -80,7 +80,7 @@ None of these exceptions carry a [`JSON_DIAGNOSTICS`](../macros/json_diagnostics ## Complexity 1. Linear in the number of members: as for [`ordered_json`](../ordered_json.md), members are compared one after - another, in document order, scanning all of them, since the last match is wanted. Each comparison first checks the + another, in document order, stopping at the first match. Each comparison first checks the key's length -- already known from the index, without reading the key bytes -- before comparing its content, so a key of a different length than `key` is rejected without touching the source text. 2. Linear in `idx`: elements are skipped one at a time from the first one, since they are not a fixed size in the @@ -105,15 +105,18 @@ document. key on an array or a primitive, or an index on an object or a primitive, is `type_error.305` as for `BasicJsonType`. [`at`](at.md) still throws for a discarded view, as it does for a missing key. -!!! info "Duplicate keys" +!!! warning "Duplicate keys: the first member wins" If the source text has an object with a duplicate key, `#!cpp operator[]` (and [`at`](at.md), [`find`](find.md), [`contains`](contains.md), [`count`](count.md), [`value`](value.md), and JSON pointer resolution) all resolve to - the *last* member with that key. This is the member [`materialize()`](materialize.md) (and - [`BasicJsonType::parse()`](../basic_json/parse.md)) keeps, so a lookup in the view and in the materialized value - agree. [`begin()`](begin.md)/[`end()`](end.md) and [`items()`](items.md) iterate over *all* members, including - duplicates, in document order. A lookup scans all members for this: it cannot stop at the first match. See the - example below and [`size()`](size.md#notes). + the *first* member with that key, because a lookup can stop as soon as it finds a match. This is different from + [`materialize()`](materialize.md) (and [`BasicJsonType::parse()`](../basic_json/parse.md)), which replay every + member in order and so keep the *last* value for a repeated key, so `#!cpp v["a"]` and + `#!cpp v.materialize()["a"]` can differ. To get the value `parse()` would give, use + [`materialize()`](materialize.md) or iterate the members with [`items()`](items.md) and keep the last match. + [`begin()`](begin.md)/[`end()`](end.md) and [`items()`](items.md) iterate over *all* members, including + duplicates, in document order. See [Duplicate keys](../../features/json_view.md#duplicate-keys) and + [`size()`](size.md#notes). !!! info "JSON pointer resolution" diff --git a/docs/mkdocs/docs/api/basic_json_view/value.md b/docs/mkdocs/docs/api/basic_json_view/value.md index c13c0cd63..2a8b9d828 100644 --- a/docs/mkdocs/docs/api/basic_json_view/value.md +++ b/docs/mkdocs/docs/api/basic_json_view/value.md @@ -12,7 +12,7 @@ T value(const json_pointer& ptr, const T& default_value) const; string_t value(const json_pointer& ptr, const char* default_value) const; ``` -1. Returns the value of the object member with key `key` -- the last one, should the key occur more than once (see +1. Returns the value of the object member with key `key` -- the first one, should the key occur more than once (see [Notes on duplicate keys](operator[].md#notes)) -- converted to `T`, or `default_value` if there is no such member. 2. Returns the value a JSON pointer `ptr` refers to, starting at this value, converted to `T`, or `default_value` if `ptr` cannot be resolved. @@ -39,7 +39,7 @@ equivalent) deduce `string_t`, not `const char*`, for their return type and for ## Return value -1. the last member with key `key`, converted to `T`, or `default_value` +1. the first member with key `key`, converted to `T`, or `default_value` 2. the value `ptr` resolves to, converted to `T`, or `default_value` ## Exception safety @@ -68,7 +68,7 @@ None of these exceptions carry a [`JSON_DIAGNOSTICS`](../macros/json_diagnostics ## Complexity 1. Linear in the number of members: as for [`operator[]`](operator[].md#complexity), members are compared one after - another, in document order, scanning all of them, since the last match is wanted. Plus the complexity of converting + another, in document order, stopping at the first match. Plus the complexity of converting the found member to `T` (see [`get`](get.md)). 2. Linear in the number of reference tokens of `ptr` and, for each token, in the number of members of the object at that level or the index into the array -- as for the [`operator[]`](operator[].md#complexity) and @@ -77,6 +77,13 @@ None of these exceptions carry a [`JSON_DIAGNOSTICS`](../macros/json_diagnostics ## Notes +!!! warning "Duplicate keys: the first member wins" + + If the source text repeats a key, this resolves to the *first* member with it, not to the last one that + [`materialize()`](materialize.md) and `parse()` keep. See the [Notes on duplicate keys](operator[].md#notes) of + `operator[]` and [Duplicate keys](../../features/json_view.md#duplicate-keys) for the reasons and for how to get + the last value. + !!! info "Differences to `at` and `operator[]`" Unlike [`at`](at.md), this function does not throw if `key`/`ptr` resolves to no value. Unlike diff --git a/docs/mkdocs/docs/examples/basic_json_view__items.cpp b/docs/mkdocs/docs/examples/basic_json_view__items.cpp index 6357c7e4b..3f7779c19 100644 --- a/docs/mkdocs/docs/examples/basic_json_view__items.cpp +++ b/docs/mkdocs/docs/examples/basic_json_view__items.cpp @@ -7,8 +7,8 @@ int main() { // a settings object whose source text records every update to a key as // a duplicate member. items() visits all of them, in document order, so - // the update history is visible; operator[] and materialize() -- like - // basic_json::parse() -- see the last one + // the update history is visible; operator[] only ever sees the first + // one, and materialize() -- like basic_json::parse() -- keeps the last json_document updates = json_document::parse(R"({"retries": 1, "timeout": 30, "retries": 5})"); const auto settings = updates.root(); @@ -17,6 +17,6 @@ int main() std::cout << item.key() << '=' << item.value().materialize().dump() << '\n'; } - std::cout << "last \"retries\" seen by operator[]: " << settings["retries"].materialize().dump() << '\n'; + std::cout << "first \"retries\" seen by operator[]: " << settings["retries"].materialize().dump() << '\n'; std::cout << "last \"retries\" kept by materialize(): " << settings.materialize()["retries"].dump() << '\n'; } diff --git a/docs/mkdocs/docs/examples/basic_json_view__items.output b/docs/mkdocs/docs/examples/basic_json_view__items.output index 8f51dbf18..78609c8ee 100644 --- a/docs/mkdocs/docs/examples/basic_json_view__items.output +++ b/docs/mkdocs/docs/examples/basic_json_view__items.output @@ -1,5 +1,5 @@ retries=1 timeout=30 retries=5 -last "retries" seen by operator[]: 5 +first "retries" seen by operator[]: 1 last "retries" kept by materialize(): 5 diff --git a/docs/mkdocs/docs/features/json_view.md b/docs/mkdocs/docs/features/json_view.md index 67b56cbe1..c42f2d642 100644 --- a/docs/mkdocs/docs/features/json_view.md +++ b/docs/mkdocs/docs/features/json_view.md @@ -134,16 +134,8 @@ document: `#!cpp auto v = json_document::parse(text).root();` does not compile. `operator[]` on a discarded view returns a discarded view without throwing: `#!cpp v["a"]["b"][0]` can be tested once at the end. Type errors on values that exist (a key on an array, an index on an object) still throw, and [`at`](../api/basic_json_view/at.md) throws for every missing value. -- **Duplicate keys are visible.** If an object in the source text repeats a key, - [`begin()`](../api/basic_json_view/begin.md)/[`end()`](../api/basic_json_view/end.md) and - [`items()`](../api/basic_json_view/items.md) visit *every* occurrence (and [`size()`](../api/basic_json_view/size.md) - counts all of them), while [`operator[]`](../api/basic_json_view/operator%5B%5D.md), - [`at`](../api/basic_json_view/at.md), [`find`](../api/basic_json_view/find.md), - [`contains`](../api/basic_json_view/contains.md), and [`count`](../api/basic_json_view/count.md) resolve to the - *last* occurrence -- the one `basic_json::parse()` (and so - [`materialize()`](../api/basic_json_view/materialize.md)) keeps for a repeated key -- which makes a lookup scan all - members instead of stopping at a match. - See the [Notes on duplicate keys](../api/basic_json_view/operator%5B%5D.md#notes) of `operator[]`. +- **Duplicate keys: lookups find the first member, `parse()` keeps the last.** See [Duplicate keys](#duplicate-keys) + below. - **No [`JSON_DIAGNOSTICS`](../api/macros/json_diagnostics.md) path.** Exceptions thrown by `basic_json_view`'s own element access and lookup functions never carry the JSON Pointer path `JSON_DIAGNOSTICS` would otherwise add: the view has no `basic_json` value to point at, so the exception is created without one, regardless of how @@ -151,6 +143,51 @@ document: `#!cpp auto v = json_document::parse(text).root();` does not compile. - **`dump()` and comparison are not (yet) provided** by `basic_json_view`. For now, [`materialize()`](../api/basic_json_view/materialize.md) is the way to get a value you can do those things with. +## Duplicate keys + +!!! warning "A lookup in a view and in the parsed value can give different answers" + + If an object in the source text repeats a key, [`operator[]`](../api/basic_json_view/operator%5B%5D.md), + [`at`](../api/basic_json_view/at.md), [`find`](../api/basic_json_view/find.md), + [`value`](../api/basic_json_view/value.md), [`contains`](../api/basic_json_view/contains.md), + [`count`](../api/basic_json_view/count.md), and JSON pointer resolution all return the **first** member with that + key. `basic_json::parse()` instead keeps the **last** value of a repeated key, so for `#!cpp {"a":1,"a":2}`, + `#!cpp view["a"]` is `#!cpp 1` while `#!cpp parse(text)["a"]` is `#!cpp 2`. + +[`begin()`](../api/basic_json_view/begin.md)/[`end()`](../api/basic_json_view/end.md) and +[`items()`](../api/basic_json_view/items.md) visit *every* occurrence, in document order, and +[`size()`](../api/basic_json_view/size.md) counts all of them, so `#!cpp view.size()` can be larger than +`#!cpp view.materialize().size()`. + +**Why the first?** A lookup can stop as soon as it finds a match. Returning the last member would force every lookup +to scan all members of the object, even when the key is found at the very first one: this made lookups in small +objects 1.6 to 3.4 times slower. Other zero-copy parsers that index the source text, such as yyjson and simdjson, also +return the first member. RFC 8259 only says that names within an object SHOULD be unique and that the behavior of a +receiver that sees duplicates is unpredictable, so neither choice is wrong. + +**What stays the same as `parse()`?** [`materialize()`](../api/basic_json_view/materialize.md) and +[`get>()`](../api/basic_json_view/get.md) replay every member in order, so they keep the *last* value +exactly like `#!cpp basic_json::parse()` (at the position of the first occurrence of the key, for an +[`ordered_json`](../api/ordered_json.md)). + +**How do I get the value `parse()` would give?** Either call `#!cpp view.materialize()` and look the key up in the +result, or iterate the members and keep the last match: + +```cpp +// the last member with the key "a", as parse() would keep it +json_view last; +for (const auto item : view.items()) +{ + if (item.key() == "a") + { + last = item.value(); + } +} +``` + +If you cannot trust the source text to have unique keys, check [`size()`](../api/basic_json_view/size.md) against the +number of distinct keys, or reject duplicates when iterating. + ## Getting values out without copying [`get()`](../api/basic_json_view/get.md) converts many `T` directly from the flat index, without ever building a diff --git a/include/nlohmann/detail/view/lookup.hpp b/include/nlohmann/detail/view/lookup.hpp index a58c9a33a..8ec1c155b 100644 --- a/include/nlohmann/detail/view/lookup.hpp +++ b/include/nlohmann/detail/view/lookup.hpp @@ -83,14 +83,14 @@ class short_key std::uint64_t m_b = 0; }; -/// the key node of the last member of an object with the given key, or -/// nullptr (the last one, as materialize() and parse() keep it); most keys are -/// rejected by their length, from the index alone +/// the key node of the first member of an object with the given key, or +/// nullptr (the search stops at the first match; materialize() and parse() +/// keep the last value of a duplicate key instead); most keys are rejected by +/// their length, from the index alone inline const node* find_member(const document_data& d, const node* object, const char* key, std::size_t n) noexcept { const node* const end = document_data::child_end(object); const auto* const k = reinterpret_cast(key); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast) - const node* last = nullptr; if (NLOHMANN_VIEW_LIKELY(n <= 16)) { const short_key probe(k, n); @@ -98,19 +98,19 @@ inline const node* find_member(const document_data& d, const node* object, const { if (m->len == n && probe.matches(reinterpret_cast(d.str(*m)))) // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast) { - last = m; + return m; } } - return last; + return nullptr; } for (const node* m = document_data::first_child(object); m != end; m = document_data::after(m + 1)) { if (m->len == n && std::memcmp(d.str(*m), key, n) == 0) { - last = m; + return m; } } - return last; + return nullptr; } /// whether an integer type is accepted as an array index by the view's diff --git a/include/nlohmann/json_view.hpp b/include/nlohmann/json_view.hpp index d71d54488..256466fa0 100644 --- a/include/nlohmann/json_view.hpp +++ b/include/nlohmann/json_view.hpp @@ -228,7 +228,7 @@ class basic_json_view // element access // //////////////////// - /// the value of the member with this key (the last one, should the key + /// the value of the member with this key (the first one, should the key /// occur more than once); a discarded view if there is none, or if this /// is a discarded view (so that v["a"]["b"] is safe). Throws type_error.305 /// if this is any other value but an object. @@ -292,7 +292,7 @@ class basic_json_view return detail::view::resolve_pointer(*this, detail::json_pointer_access::reference_tokens(ptr), detail::view::pointer_mode::unchecked); } - /// the value of the member with this key (the last one, should the key + /// the value of the member with this key (the first one, should the key /// occur more than once). Throws type_error.304 if this is not an object, /// and out_of_range.403 if there is no such member. basic_json_view at(string_view_t key) const @@ -350,7 +350,7 @@ class basic_json_view } /// the member with this key converted to T, or the default value if there - /// is no such member (the last one, should the key occur more than + /// is no such member (the first one, should the key occur more than /// once). Throws type_error.306 if this is not an object. template < typename T, typename std::enable_if < !std::is_same::type, const char*>::value, int >::type = 0 > T value(string_view_t key, const T& default_value) const @@ -415,7 +415,7 @@ class basic_json_view // lookup // //////////// - /// an iterator to the member with this key (the last one, should the + /// an iterator to the member with this key (the first one, should the /// key occur more than once), or end(); end() also for non-objects iterator find(string_view_t key) const { @@ -593,7 +593,7 @@ class basic_json_view : m_doc(d), m_node(n) {} - /// the value of the last member with this key, or a discarded view + /// the value of the first member with this key, or a discarded view /// (object required) NLOHMANN_VIEW_ALWAYS_INLINE basic_json_view lookup(string_view_t key) const noexcept { diff --git a/tests/src/unit-json_view.cpp b/tests/src/unit-json_view.cpp index bc43a97bd..17d0fcb3b 100644 --- a/tests/src/unit-json_view.cpp +++ b/tests/src/unit-json_view.cpp @@ -576,7 +576,7 @@ std::string exception_of(F f) // compares a view with the ordered_json value materialize() gives for it: // types, sizes, elements and members (by index, key, and iteration), in -// document order; duplicate keys are found as their last occurrence +// document order; duplicate keys are found as their first occurrence void check_access(const ordered_json_view& v, const ordered_json& j) { REQUIRE(v.type() == j.type()); @@ -617,23 +617,13 @@ void check_access(const ordered_json_view& v, const ordered_json& j) const std::string key(it.key().data(), it.key().size()); CHECK(v.contains(key)); CHECK(v.count(key) == 1); - if (std::find(keys.begin(), keys.end(), key) == keys.end()) - { - keys.push_back(key); - } - // lookups find the last member with the key, which is this one if - // there is no later one - auto next = it; - ++next; - bool is_last = true; - for (; next != v.end(); ++next) - { - is_last = is_last && next.key() != it.key(); - } - if (!is_last) + // lookups find the first member with the key, which is this one if + // there is no earlier one + if (std::find(keys.begin(), keys.end(), key) != keys.end()) { continue; } + keys.push_back(key); CHECK(v.find(key) == it); CHECK(v[key].materialize() == it->materialize()); CHECK(v.at(key).materialize() == it.value().materialize()); @@ -724,20 +714,28 @@ TEST_CASE("json_view element access and iteration") #endif } - SECTION("duplicate keys: lookups find the last member, iteration all") + SECTION("duplicate keys: lookups find the first member, iteration all") { const json_document d = json_document::parse(R"({"a":1,"b":2,"a":3})"); const json_view v = d.root(); CHECK(v.size() == 3); - CHECK(v["a"].materialize() == 3); - CHECK(v.at("a").materialize() == 3); - CHECK(v.find("a") == std::next(v.begin(), 2)); - CHECK(v.find("a").value().materialize() == 3); + CHECK(v["a"].materialize() == 1); + CHECK(v.at("a").materialize() == 1); + CHECK(v.find("a") == v.begin()); + CHECK(v.find("a").value().materialize() == 1); CHECK(v.find("b") == std::next(v.begin())); CHECK(v.count("a") == 1); CHECK(v.contains("a")); - CHECK(v.value("a", 0) == 3); - CHECK(v["a"].materialize() == v.materialize()["a"]); // as materialize() + CHECK(v.value("a", 0) == 1); + CHECK(v.materialize()["a"] == 3); // materialize() keeps the last value, unlike the lookups + // JSON pointers resolve to the first member at every level + const json_document dp = json_document::parse(R"({"a":{"b":1},"a":{"b":2,"b":3}})"); + CHECK(dp.root()[json::json_pointer("/a/b")].materialize() == 1); + CHECK(dp.root().at(json::json_pointer("/a/b")).materialize() == 1); + CHECK(dp.root().value(json::json_pointer("/a/b"), 0) == 1); + CHECK(dp.root().materialize()[json::json_pointer("/a/b")] == 3); + // get keeps the last value, as materialize() + CHECK((v.get>() == std::map {{"a", 3}, {"b", 2}})); // keys of every length class (the 16-byte short compare and memcmp) for (const std::size_t n : { @@ -747,10 +745,10 @@ TEST_CASE("json_view element access and iteration") const std::string key(n, 'k'); const json_document dk = json_document::parse("{\"" + key + "\":1,\"" + key + "x\":2,\"" + key + "\":3,\"" + key + "\":4}"); CAPTURE(n) - CHECK(dk.root()[key].materialize() == 4); - CHECK(dk.root().at(key).materialize() == 4); - CHECK(dk.root().find(key) == std::next(dk.root().begin(), 3)); - CHECK(dk.root().value(key, 0) == 4); + CHECK(dk.root()[key].materialize() == 1); + CHECK(dk.root().at(key).materialize() == 1); + CHECK(dk.root().find(key) == dk.root().begin()); + CHECK(dk.root().value(key, 0) == 1); CHECK(dk.root()[key + "x"].materialize() == 2); } std::string order; From 3faacc1c2fa5779a2dbc8a5986095ecccc33d03a Mon Sep 17 00:00:00 2001 From: Niels Lohmann Date: Fri, 9 Oct 2026 23:20:52 +0200 Subject: [PATCH 2/4] Regenerate the amalgamated headers Signed-off-by: Niels Lohmann --- single_include/nlohmann/json_view.hpp | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/single_include/nlohmann/json_view.hpp b/single_include/nlohmann/json_view.hpp index 0d9bc1f15..97185d18d 100644 --- a/single_include/nlohmann/json_view.hpp +++ b/single_include/nlohmann/json_view.hpp @@ -2173,14 +2173,14 @@ class short_key std::uint64_t m_b = 0; }; -/// the key node of the last member of an object with the given key, or -/// nullptr (the last one, as materialize() and parse() keep it); most keys are -/// rejected by their length, from the index alone +/// the key node of the first member of an object with the given key, or +/// nullptr (the search stops at the first match; materialize() and parse() +/// keep the last value of a duplicate key instead); most keys are rejected by +/// their length, from the index alone inline const node* find_member(const document_data& d, const node* object, const char* key, std::size_t n) noexcept { const node* const end = document_data::child_end(object); const auto* const k = reinterpret_cast(key); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast) - const node* last = nullptr; if (NLOHMANN_VIEW_LIKELY(n <= 16)) { const short_key probe(k, n); @@ -2188,19 +2188,19 @@ inline const node* find_member(const document_data& d, const node* object, const { if (m->len == n && probe.matches(reinterpret_cast(d.str(*m)))) // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast) { - last = m; + return m; } } - return last; + return nullptr; } for (const node* m = document_data::first_child(object); m != end; m = document_data::after(m + 1)) { if (m->len == n && std::memcmp(d.str(*m), key, n) == 0) { - last = m; + return m; } } - return last; + return nullptr; } /// whether an integer type is accepted as an array index by the view's @@ -3039,7 +3039,7 @@ class basic_json_view // element access // //////////////////// - /// the value of the member with this key (the last one, should the key + /// the value of the member with this key (the first one, should the key /// occur more than once); a discarded view if there is none, or if this /// is a discarded view (so that v["a"]["b"] is safe). Throws type_error.305 /// if this is any other value but an object. @@ -3103,7 +3103,7 @@ class basic_json_view return detail::view::resolve_pointer(*this, detail::json_pointer_access::reference_tokens(ptr), detail::view::pointer_mode::unchecked); } - /// the value of the member with this key (the last one, should the key + /// the value of the member with this key (the first one, should the key /// occur more than once). Throws type_error.304 if this is not an object, /// and out_of_range.403 if there is no such member. basic_json_view at(string_view_t key) const @@ -3161,7 +3161,7 @@ class basic_json_view } /// the member with this key converted to T, or the default value if there - /// is no such member (the last one, should the key occur more than + /// is no such member (the first one, should the key occur more than /// once). Throws type_error.306 if this is not an object. template < typename T, typename std::enable_if < !std::is_same::type, const char*>::value, int >::type = 0 > T value(string_view_t key, const T& default_value) const @@ -3226,7 +3226,7 @@ class basic_json_view // lookup // //////////// - /// an iterator to the member with this key (the last one, should the + /// an iterator to the member with this key (the first one, should the /// key occur more than once), or end(); end() also for non-objects iterator find(string_view_t key) const { @@ -3404,7 +3404,7 @@ class basic_json_view : m_doc(d), m_node(n) {} - /// the value of the last member with this key, or a discarded view + /// the value of the first member with this key, or a discarded view /// (object required) NLOHMANN_VIEW_ALWAYS_INLINE basic_json_view lookup(string_view_t key) const noexcept { From 32853d2c905133230968c6fc69aad96e55c21040 Mon Sep 17 00:00:00 2001 From: Niels Lohmann Date: Fri, 9 Oct 2026 23:22:34 +0200 Subject: [PATCH 3/4] Do not shrink the output of dump() finish() copied the whole output when the buffer was more than twice as large as the result (citm dump +11%). The tighter source_extent() estimate already keeps the buffer of a small value small. Signed-off-by: Niels Lohmann --- include/nlohmann/detail/view/serializer.hpp | 5 ----- single_include/nlohmann/json_view.hpp | 5 ----- 2 files changed, 10 deletions(-) diff --git a/include/nlohmann/detail/view/serializer.hpp b/include/nlohmann/detail/view/serializer.hpp index 7870601bc..bde8797c5 100644 --- a/include/nlohmann/detail/view/serializer.hpp +++ b/include/nlohmann/detail/view/serializer.hpp @@ -46,11 +46,6 @@ class output_buffer { const auto size = static_cast(m_pos - m_out.data()); m_out.resize(size); - // do not keep a buffer that was sized for a much larger output - if (m_out.capacity() > 1024 && m_out.capacity() / 2 > size) - { - m_out.shrink_to_fit(); - } } NLOHMANN_VIEW_ALWAYS_INLINE void reserve(std::size_t n) diff --git a/single_include/nlohmann/json_view.hpp b/single_include/nlohmann/json_view.hpp index 273e11474..5cd836097 100644 --- a/single_include/nlohmann/json_view.hpp +++ b/single_include/nlohmann/json_view.hpp @@ -3108,11 +3108,6 @@ class output_buffer { const auto size = static_cast(m_pos - m_out.data()); m_out.resize(size); - // do not keep a buffer that was sized for a much larger output - if (m_out.capacity() > 1024 && m_out.capacity() / 2 > size) - { - m_out.shrink_to_fit(); - } } NLOHMANN_VIEW_ALWAYS_INLINE void reserve(std::size_t n) From ef9a151308f301de545fb34e4962d6c3774dacc3 Mon Sep 17 00:00:00 2001 From: Niels Lohmann Date: Fri, 9 Oct 2026 23:26:08 +0200 Subject: [PATCH 4/4] Document and test first-wins lookups next to dump() and == dump() writes every member and == resolves duplicate keys as parse() does, whereas lookups find the first member of a duplicate key. Signed-off-by: Niels Lohmann --- docs/mkdocs/docs/api/basic_json_view/operator_eq.md | 2 ++ docs/mkdocs/docs/features/json_view.md | 4 ++-- tests/src/unit-json_view.cpp | 5 +++++ 3 files changed, 9 insertions(+), 2 deletions(-) diff --git a/docs/mkdocs/docs/api/basic_json_view/operator_eq.md b/docs/mkdocs/docs/api/basic_json_view/operator_eq.md index 6f96f4692..b43f5c633 100644 --- a/docs/mkdocs/docs/api/basic_json_view/operator_eq.md +++ b/docs/mkdocs/docs/api/basic_json_view/operator_eq.md @@ -18,6 +18,8 @@ bool operator==(const BasicJsonType& lhs, const basic_json_view& rhs); Neither overload builds a `BasicJsonType` value for a view to do the comparison (see [Notes](#notes) below). Numbers compare by value across their types (`#!cpp 1 == 1.0`), and an object compares by its members, with duplicate keys resolved exactly as `parse()` resolves them -- the last value, at the position of the first occurrence of the key. +This is not what [`operator[]`](operator[].md) and the other lookups return for a duplicate key: they find the *first* +member (see [Duplicate keys](../../features/json_view.md#duplicate-keys)). ## Parameters diff --git a/docs/mkdocs/docs/features/json_view.md b/docs/mkdocs/docs/features/json_view.md index f1664c89b..668eeb837 100644 --- a/docs/mkdocs/docs/features/json_view.md +++ b/docs/mkdocs/docs/features/json_view.md @@ -221,8 +221,8 @@ Both results are only valid as long as the view -- and, for a string with no esc [`dump()`](../api/basic_json_view/dump.md) serializes a view directly from the flat index, without ever building a `basic_json` value. An object's members are written in document order, not sorted by key, and *every* occurrence of a repeated key is written, not only the last one -- the same two ways [iteration](#what-is-different) already differs -from a [`materialize()`](../api/basic_json_view/materialize.md)d value, see above. `#!cpp materialize().dump()` gives -a different result in both respects for a `json_view`. +from a [`materialize()`](../api/basic_json_view/materialize.md)d value, see [Duplicate keys](#duplicate-keys). +`#!cpp materialize().dump()` gives a different result in both respects for a `json_view`. By default, numbers are written the way [`basic_json::dump()`](../api/basic_json/dump.md) would. [`number_format::source`](../api/basic_json_view/number_format.md) instead copies every number exactly as it was diff --git a/tests/src/unit-json_view.cpp b/tests/src/unit-json_view.cpp index f03660301..132f7c8d0 100644 --- a/tests/src/unit-json_view.cpp +++ b/tests/src/unit-json_view.cpp @@ -1461,6 +1461,8 @@ TEST_CASE("json_view dump") const json_document d = json_document::parse(R"({"b": 1, "a": 2, "b": 3})"); CHECK(d.root().dump() == R"({"b":1,"a":2,"b":3})"); CHECK(d.root().dump(1) == "{\n \"b\": 1,\n \"a\": 2,\n \"b\": 3\n}"); + // dump() writes all members, though the lookup finds the first + CHECK(d.root()["b"].dump() == "1"); } SECTION("deep nesting") @@ -1583,6 +1585,9 @@ TEST_CASE("json_view comparison") 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());