lexical analysis More...
#include <nlohmann_json.hpp>
Inherits detail::lexer_base< BasicJsonType >.
Public Types | |
| using | token_type = typename lexer_base< BasicJsonType >::token_type |
 Public Types inherited from detail::lexer_base< BasicJsonType > | |
| enum class | token_type { uninitialized , literal_true , literal_false , literal_null , value_string , value_unsigned , value_integer , value_float , begin_array , begin_object , end_array , end_object , name_separator , value_separator , parse_error , end_of_input , literal_or_value } |
| token types for the parser More... | |
Public Member Functions | |
| lexer (InputAdapterType &&adapter, bool ignore_comments_=false) noexcept | |
| lexer (const lexer &)=delete | |
| lexer (lexer &&)=default | |
| lexer & | operator= (lexer &)=delete |
| lexer & | operator= (lexer &&)=default |
| constexpr number_integer_t | get_number_integer () const noexcept |
| return integer value More... | |
| constexpr number_unsigned_t | get_number_unsigned () const noexcept |
| return unsigned integer value More... | |
| constexpr number_float_t | get_number_float () const noexcept |
| return floating-point value More... | |
| string_t & | get_string () |
| return current string value (implicitly resets the token; useful only once) More... | |
| constexpr position_t | get_position () const noexcept |
| return position of last read token More... | |
| std::string | get_token_string () const |
| JSON_HEDLEY_RETURNS_NON_NULL constexpr const char * | get_error_message () const noexcept |
| return syntax error message More... | |
| bool | skip_bom () |
| skip the UTF-8 byte order mark More... | |
| void | skip_whitespace () |
| token_type | scan () |
Private Types | |
| using | number_integer_t = typename BasicJsonType::number_integer_t |
| using | number_unsigned_t = typename BasicJsonType::number_unsigned_t |
| using | number_float_t = typename BasicJsonType::number_float_t |
| using | string_t = typename BasicJsonType::string_t |
| using | char_type = typename InputAdapterType::char_type |
| using | char_int_type = typename std::char_traits< char_type >::int_type |
Private Member Functions | |
| int | get_codepoint () |
get codepoint from 4 hex characters following \u More... | |
| bool | next_byte_in_range (std::initializer_list< char_int_type > ranges) |
| check if the next byte(s) are inside a given range More... | |
| token_type | scan_string () |
| scan a string literal More... | |
| bool | scan_comment () |
| scan a comment More... | |
| token_type | scan_number () |
| scan a number literal More... | |
| token_type | scan_literal (const char_type *literal_text, const std::size_t length, token_type return_type) |
| void | reset () noexcept |
| reset token_buffer; current character is beginning of token More... | |
| char_int_type | get () |
| void | unget () |
| unget current character (read it again on next get) More... | |
| void | add (char_int_type c) |
| add a character to token_buffer More... | |
Static Private Member Functions | |
| static JSON_HEDLEY_PURE char | get_decimal_point () noexcept |
| return the locale-dependent decimal point More... | |
| static void | strtof (float &f, const char *str, char **endptr) noexcept |
| static void | strtof (double &f, const char *str, char **endptr) noexcept |
| static void | strtof (long double &f, const char *str, char **endptr) noexcept |
Private Attributes | |
| InputAdapterType | ia |
| input adapter More... | |
| const bool | ignore_comments = false |
| whether comments should be ignored (true) or signaled as errors (false) More... | |
| char_int_type | current = std::char_traits<char_type>::eof() |
| the current character More... | |
| bool | next_unget = false |
| whether the next get() call should just return current More... | |
| position_t | position {} |
| the start position of the current token More... | |
| std::vector< char_type > | token_string {} |
| raw input token string (for error messages) More... | |
| string_t | token_buffer {} |
| buffer for variable-length tokens (numbers, strings) More... | |
| const char * | error_message = "" |
| a description of occurred lexer errors More... | |
| number_integer_t | value_integer = 0 |
| number_unsigned_t | value_unsigned = 0 |
| number_float_t | value_float = 0 |
| const char_int_type | decimal_point_char = '.' |
| the decimal point More... | |
Additional Inherited Members | |
| Static Public Member Functions inherited from detail::lexer_base< BasicJsonType > | |
| JSON_HEDLEY_RETURNS_NON_NULL static JSON_HEDLEY_CONST const char * | token_type_name (const token_type t) noexcept |
| return name of values of type token_type (only used for errors) More... | |
Detailed Description
class detail::lexer< BasicJsonType, InputAdapterType >
lexical analysis
This class organizes the lexical analysis during JSON deserialization.
Definition at line 7416 of file nlohmann_json.hpp.
Member Typedef Documentation
◆ number_integer_t
|
private |
Definition at line 7418 of file nlohmann_json.hpp.
◆ number_unsigned_t
|
private |
Definition at line 7419 of file nlohmann_json.hpp.
◆ number_float_t
|
private |
Definition at line 7420 of file nlohmann_json.hpp.
◆ string_t
|
private |
Definition at line 7421 of file nlohmann_json.hpp.
◆ char_type
|
private |
Definition at line 7422 of file nlohmann_json.hpp.
◆ char_int_type
|
private |
Definition at line 7423 of file nlohmann_json.hpp.
◆ token_type
| using detail::lexer< BasicJsonType, InputAdapterType >::token_type = typename lexer_base<BasicJsonType>::token_type |
Definition at line 7426 of file nlohmann_json.hpp.
Constructor & Destructor Documentation
◆ lexer()
|
inlineexplicitnoexcept |
Definition at line 7428 of file nlohmann_json.hpp.
Member Function Documentation
◆ get_decimal_point()
|
inlinestaticprivatenoexcept |
return the locale-dependent decimal point
Definition at line 7448 of file nlohmann_json.hpp.
◆ get_codepoint()
|
inlineprivate |
get codepoint from 4 hex characters following \u
For input "\u c1 c2 c3 c4" the codepoint is: (c1 * 0x1000) + (c2 * 0x0100) + (c3 * 0x0010) + c4 = (c1 << 12) + (c2 << 8) + (c3 << 4) + (c4 << 0)
Furthermore, the possible characters '0'..'9', 'A'..'F', and 'a'..'f' must be converted to the integers 0x0..0x9, 0xA..0xF, 0xA..0xF, resp. The conversion is done by subtracting the offset (0x30, 0x37, and 0x57) between the ASCII value of the character and the desired integer value.
- Returns
- codepoint (0x0000..0xFFFF) or -1 in case of an error (e.g. EOF or non-hex character)
Definition at line 7474 of file nlohmann_json.hpp.
◆ next_byte_in_range()
|
inlineprivate |
check if the next byte(s) are inside a given range
Adds the current byte and, for each passed range, reads a new byte and checks if it is inside the range. If a violation was detected, set up an error message and return false. Otherwise, return true.
- Parameters
-
[in] ranges list of integers; interpreted as list of pairs of inclusive lower and upper bound, respectively
- Precondition
- The passed list ranges must have 2, 4, or 6 elements; that is, 1, 2, or 3 pairs. This precondition is enforced by an assertion.
- Returns
- true if and only if no range violation was detected
Definition at line 7522 of file nlohmann_json.hpp.
◆ scan_string()
|
inlineprivate |
scan a string literal
This function scans a string according to Sect. 7 of RFC 8259. While scanning, bytes are escaped and copied into buffer token_buffer. Then the function returns successfully, token_buffer is not null-terminated (as it may contain \0 bytes), and token_buffer.size() is the number of bytes in the string.
- Returns
- token_type::value_string if string could be successfully scanned, token_type::parse_error otherwise
- Note
- In case of errors, variable error_message contains a textual description.
Definition at line 7559 of file nlohmann_json.hpp.
◆ scan_comment()
|
inlineprivate |
scan a comment
- Returns
- whether comment could be scanned successfully
Definition at line 8149 of file nlohmann_json.hpp.
◆ strtof() [1/3]
|
inlinestaticprivatenoexcept |
Definition at line 8217 of file nlohmann_json.hpp.
◆ strtof() [2/3]
|
inlinestaticprivatenoexcept |
Definition at line 8223 of file nlohmann_json.hpp.
◆ strtof() [3/3]
|
inlinestaticprivatenoexcept |
Definition at line 8229 of file nlohmann_json.hpp.
◆ scan_number()
|
inlineprivate |
scan a number literal
This function scans a string according to Sect. 6 of RFC 8259.
The function is realized with a deterministic finite state machine derived from the grammar described in RFC 8259. Starting in state "init", the input is read and used to determined the next state. Only state "done" accepts the number. State "error" is a trap state to model errors. In the table below, "anything" means any character but the ones listed before.
| state | 0 | 1-9 | e E | + | - | . | anything |
|---|---|---|---|---|---|---|---|
| init | zero | any1 | [error] | [error] | minus | [error] | [error] |
| minus | zero | any1 | [error] | [error] | [error] | [error] | [error] |
| zero | done | done | exponent | done | done | decimal1 | done |
| any1 | any1 | any1 | exponent | done | done | decimal1 | done |
| decimal1 | decimal2 | decimal2 | [error] | [error] | [error] | [error] | [error] |
| decimal2 | decimal2 | decimal2 | exponent | done | done | done | done |
| exponent | any2 | any2 | [error] | sign | sign | [error] | [error] |
| sign | any2 | any2 | [error] | [error] | [error] | [error] | [error] |
| any2 | any2 | any2 | done | done | done | done | done |
The state machine is realized with one label per state (prefixed with "scan_number_") and goto statements between them. The state machine contains cycles, but any cycle can be left when EOF is read. Therefore, the function is guaranteed to terminate.
During scanning, the read bytes are stored in token_buffer. This string is then converted to a signed integer, an unsigned integer, or a floating-point number.
- Returns
- token_type::value_unsigned, token_type::value_integer, or token_type::value_float if number could be successfully scanned, token_type::parse_error otherwise
- Note
- The scanner is independent of the current locale. Internally, the locale's decimal point is used instead of
.to work with the locale-dependent converters.
Definition at line 8274 of file nlohmann_json.hpp.
◆ scan_literal()
|
inlineprivate |
- Parameters
-
[in] literal_text the literal text to expect [in] length the length of the passed literal text [in] return_type the token type to return on success
Definition at line 8605 of file nlohmann_json.hpp.
◆ reset()
|
inlineprivatenoexcept |
reset token_buffer; current character is beginning of token
Definition at line 8625 of file nlohmann_json.hpp.
◆ get()
|
inlineprivate |
Definition at line 8642 of file nlohmann_json.hpp.
◆ unget()
|
inlineprivate |
unget current character (read it again on next get)
We implement unget by setting variable next_unget to true. The input is not changed - we just simulate ungetting by modifying chars_read_total, chars_read_current_line, and token_string. The next call to get() will behave as if the unget character is read again.
Definition at line 8679 of file nlohmann_json.hpp.
◆ add()
|
inlineprivate |
add a character to token_buffer
Definition at line 8706 of file nlohmann_json.hpp.
◆ get_number_integer()
|
inlineconstexprnoexcept |
return integer value
Definition at line 8717 of file nlohmann_json.hpp.
◆ get_number_unsigned()
|
inlineconstexprnoexcept |
return unsigned integer value
Definition at line 8723 of file nlohmann_json.hpp.
◆ get_number_float()
|
inlineconstexprnoexcept |
return floating-point value
Definition at line 8729 of file nlohmann_json.hpp.
◆ get_string()
|
inline |
return current string value (implicitly resets the token; useful only once)
Definition at line 8735 of file nlohmann_json.hpp.
◆ get_position()
|
inlineconstexprnoexcept |
return position of last read token
Definition at line 8745 of file nlohmann_json.hpp.
◆ get_token_string()
|
inline |
return the last read token (for errors only). Will never contain EOF (an arbitrary value that is not a valid char value, often -1), because 255 may legitimately occur. May contain NUL, which should be escaped.
Definition at line 8753 of file nlohmann_json.hpp.
◆ get_error_message()
|
inlineconstexprnoexcept |
return syntax error message
Definition at line 8778 of file nlohmann_json.hpp.
◆ skip_bom()
|
inline |
skip the UTF-8 byte order mark
- Returns
- true iff there is no BOM or the correct BOM has been skipped
Definition at line 8791 of file nlohmann_json.hpp.
◆ skip_whitespace()
|
inline |
Definition at line 8805 of file nlohmann_json.hpp.
◆ scan()
|
inline |
Definition at line 8814 of file nlohmann_json.hpp.
Member Data Documentation
◆ ia
|
private |
input adapter
Definition at line 8904 of file nlohmann_json.hpp.
◆ ignore_comments
|
private |
whether comments should be ignored (true) or signaled as errors (false)
Definition at line 8907 of file nlohmann_json.hpp.
◆ current
|
private |
the current character
Definition at line 8910 of file nlohmann_json.hpp.
◆ next_unget
|
private |
whether the next get() call should just return current
Definition at line 8913 of file nlohmann_json.hpp.
◆ position
|
private |
the start position of the current token
Definition at line 8916 of file nlohmann_json.hpp.
◆ token_string
|
private |
raw input token string (for error messages)
Definition at line 8919 of file nlohmann_json.hpp.
◆ token_buffer
|
private |
buffer for variable-length tokens (numbers, strings)
Definition at line 8922 of file nlohmann_json.hpp.
◆ error_message
|
private |
a description of occurred lexer errors
Definition at line 8925 of file nlohmann_json.hpp.
◆ value_integer
|
private |
Definition at line 8928 of file nlohmann_json.hpp.
◆ value_unsigned
|
private |
Definition at line 8929 of file nlohmann_json.hpp.
◆ value_float
|
private |
Definition at line 8930 of file nlohmann_json.hpp.
◆ decimal_point_char
|
private |
the decimal point
Definition at line 8933 of file nlohmann_json.hpp.
The documentation for this class was generated from the following file:
