#include "sql/json_schema.h"
#include <my_rapidjson_size_t.h>
#include <assert.h>
#include <rapidjson/document.h>
#include <rapidjson/error/error.h>
#include <rapidjson/memorystream.h>
#include <rapidjson/pointer.h>
#include <rapidjson/reader.h>
#include <rapidjson/schema.h>
#include <rapidjson/stringbuffer.h>
#include <algorithm>
#include <cassert>
#include <cstdint>
#include <string>
#include <unordered_set>
#include <utility>
#include "my_alloc.h"
#include "my_inttypes.h"
#include "my_sys.h"
#include "mysqld_error.h"
#include "sql-common/json_syntax_check.h"
#include "sql/sql_exception_handler.h"

Functions
static bool	is_local_json_pointer_ref (const rapidjson::Value &ref_value)
	Check whether a `$ref` value is a local JSON Pointer reference. More...

static const rapidjson::Value *	resolve_local_json_pointer_ref (const rapidjson::Document &schema_document, const rapidjson::Value &ref_value)
	Resolve a local JSON Pointer `$ref` against the schema document. More...

static bool	json_schema_exceeds_expansion_depth (const rapidjson::Document &schema_document, const rapidjson::Value node, uint32_t depth_so_far, uint32_t limit, std::unordered_set< const rapidjson::Value > *visiting)
	Check whether any path from a schema node exceeds the expansion depth limit. More...

static bool	check_json_schema_expansion_depth (const rapidjson::Document &schema_document)
	Validate that a JSON Schema does not require excessive recursion depth during rapidjson schema compilation. More...

static bool	parse_json_schema (const char json_schema_str, size_t json_schema_length, const char function_name, rapidjson::Document *schema_document)
	parse_json_schema will parse a JSON input into a JSON Schema. More...

bool	is_valid_json_schema (const char document_str, size_t document_length, const char json_schema_str, size_t json_schema_length, const char function_name, bool is_valid, Json_schema_validation_report *validation_report)
	This function will validate a JSON document against a JSON Schema using the validation provided by rapidjson. More...

unique_ptr_destroy_only< const Json_schema_validator >	create_json_schema_validator (MEM_ROOT mem_root, const char json_schema_str, size_t json_schema_length, const char *function_name)
	Create a Json_schema_validator, allocated on a given MEM_ROOT. More...

Variables
static constexpr uint32_t	JSON_SCHEMA_MAX_EXPANSION_DEPTH = 100
	Maximum "expansion depth" of a JSON Schema during rapidjson schema compilation. More...

Function Documentation

◆ check_json_schema_expansion_depth()

static bool check_json_schema_expansion_depth ( const rapidjson::Document & schema_document )

static

Validate that a JSON Schema does not require excessive recursion depth during rapidjson schema compilation.

rapidjson schema compilation expands local $ref by recursively compiling the referenced subschemas. The recursion depth is therefore related to the number of local reference "hops" along the deepest expansion path. This depth can be large even if no referred object has a $ref at its own top level, as long as each referred object contains a nested object with a $ref.

This function only checks whether any expansion path exceeds the limit. Each step into a nested object/array and each local $ref expansion counts as 1.

It does this by walking JSON-tree edges (object members / array elements) and local $ref edges (JSON pointer references starting with #), with early exit as soon as the limit is exceeded.

If the limit is exceeded (JSON_SCHEMA_MAX_EXPANSION_DEPTH), ER_JSON_DOCUMENT_TOO_DEEP is reported.

Parameters

schema_document Parsed JSON schema document.

Return values

true	The schema exceeded the limit and an error was reported.
false	No expansion path exceeds the limit.

◆ create_json_schema_validator()

unique_ptr_destroy_only< const Json_schema_validator > create_json_schema_validator	(	MEM_ROOT *	mem_root,
		const char *	json_schema_str,
		size_t	json_schema_length,
		const char *	function_name
	)

Create a Json_schema_validator, allocated on a given MEM_ROOT.

Parameters

mem_root	The MEM_ROOT to allocate the validator on
json_schema_str	A pointer to the JSON Schema
json_schema_length	The length of the JSON Schema input
function_name	The function name of the caller (to be used in error reporting)

Return values

nullptr on error (my_error has been called)

◆ is_local_json_pointer_ref()

static bool is_local_json_pointer_ref ( const rapidjson::Value & ref_value )

static

Check whether a $ref value is a local JSON Pointer reference.

We only guard references of the form "#" or "#/...".

Parameters

ref_value The value of the $ref member.

Return values

true	The `$ref` is a local JSON pointer reference.
false	Otherwise.

◆ is_valid_json_schema()

bool is_valid_json_schema	(	const char *	document_str,
		size_t	document_length,
		const char *	json_schema_str,
		size_t	json_schema_length,
		const char *	function_name,
		bool *	is_valid,
		Json_schema_validation_report *	report
	)

This function will validate a JSON document against a JSON Schema using the validation provided by rapidjson.

Parameters

	document_str	A pointer to the JSON document to be validated.
	document_length	The length of the JSON document to be validated.
	json_schema_str	A pointer to the JSON Schema.
	json_schema_length	The length of the JSON Schema.
	function_name	The name of the SQL function calling this function. Used in error reporting.
[out]	is_valid	A variable containing the result of the validation. If true, the JSON document is valid according to the given JSON Schema.
[out]	report	A structure containing a detailed report from the validation. Is only populated if is_valid is set to "false". Can be nullptr if a detailed report isn't needed.

Return values

true	if anything went wrong (like parsing the JSON inputs). my_error has been called with an appropriate error message.
false	if the validation succeeded. The result of the validation can be found in the output variable "is_valid".

◆ json_schema_exceeds_expansion_depth()

static bool json_schema_exceeds_expansion_depth	(	const rapidjson::Document &	schema_document,
		const rapidjson::Value *	node,
		uint32_t	depth_so_far,
		uint32_t	limit,
		std::unordered_set< const rapidjson::Value * > *	visiting
	)

static

Check whether any path from a schema node exceeds the expansion depth limit.

The expansion depth is the number of edges along a path in the schema's expansion graph:

JSON-tree edges (object members / array elements), and
local $ref edges (local JSON Pointer references).

visiting is used to break $ref cycles (cycles are treated as non-contributing; rapidjson will report cyclic references separately).

Parameters

	schema_document	Parsed JSON schema document (used for resolving `$ref`).
	node	The node to start the search from.
	depth_so_far	Current depth from the schema root.
	limit	Maximum allowed expansion depth.
[in,out]	visiting	Visitation set for cycle detection.

Return values

true	The limit is exceeded along some path.
false	No path exceeds the limit.

◆ parse_json_schema()

static bool parse_json_schema	(	const char *	json_schema_str,
		size_t	json_schema_length,
		const char *	function_name,
		rapidjson::Document *	schema_document
	)

static

parse_json_schema will parse a JSON input into a JSON Schema.

If the input isn't a valid JSON, or if the JSON is too deeply nested, an error will be returned to the user.

Parameters

	json_schema_str	A pointer to the JSON Schema input
	json_schema_length	The length of the JSON Schema input
	function_name	The function name of the caller (to be used in error reporting)
[out]	schema_document	An object where the JSON Schema will be put. This variable MUST be initialized.

Return values

true	on error (my_error has been called)
false	on success. The JSON Schema can be found in the output parameter schema_document.

◆ resolve_local_json_pointer_ref()

static const rapidjson::Value * resolve_local_json_pointer_ref	(	const rapidjson::Document &	schema_document,
		const rapidjson::Value &	ref_value
	)

static

Resolve a local JSON Pointer $ref against the schema document.

Parameters

schema_document	The full JSON schema document.
ref_value	The `$ref` member value (must be a local JSON pointer).

Returns: Pointer to the referenced schema node on success, otherwise nullptr.

Variable Documentation

◆ JSON_SCHEMA_MAX_EXPANSION_DEPTH

constexpr uint32_t JSON_SCHEMA_MAX_EXPANSION_DEPTH = 100

staticconstexpr

Maximum "expansion depth" of a JSON Schema during rapidjson schema compilation.

rapidjson schema compilation is recursive. The call stack depth is driven by a combination of:

JSON nesting within the schema (object members / array elements), and
local $ref expansion (compiling referenced subschemas recursively).

This cap bounds the maximum number of edges along any path in the schema's "expansion graph", where both JSON-tree edges and local $ref edges count as 1.

Since MySQL rejects JSON documents deeper than 100 levels (see sql-common/json_syntax_check.cc), schemas requiring more than 100 levels of expansion cannot describe JSON documents supported by MySQL. We therefore use 100 as the single guard limit here as well.

Functions

Variables

Function Documentation

◆ check_json_schema_expansion_depth()

◆ create_json_schema_validator()

◆ is_local_json_pointer_ref()

◆ is_valid_json_schema()

◆ json_schema_exceeds_expansion_depth()

◆ parse_json_schema()

◆ resolve_local_json_pointer_ref()

Variable Documentation

◆ JSON_SCHEMA_MAX_EXPANSION_DEPTH