json-lexer.c (340db1ed82f8ced40a3e778c08963005369e2926) json-lexer.c (eddc0a7f0ad84edd0f8dd27d4a70a305ccd7bc5f)
1/*
2 * JSON lexer
3 *
4 * Copyright IBM, Corp. 2009
5 *
6 * Authors:
7 * Anthony Liguori <aliguori@us.ibm.com>
8 *

--- 4 unchanged lines hidden (view full) ---

13
14#include "qemu/osdep.h"
15#include "qemu-common.h"
16#include "qapi/qmp/json-lexer.h"
17
18#define MAX_TOKEN_SIZE (64ULL << 20)
19
20/*
1/*
2 * JSON lexer
3 *
4 * Copyright IBM, Corp. 2009
5 *
6 * Authors:
7 * Anthony Liguori <aliguori@us.ibm.com>
8 *

--- 4 unchanged lines hidden (view full) ---

13
14#include "qemu/osdep.h"
15#include "qemu-common.h"
16#include "qapi/qmp/json-lexer.h"
17
18#define MAX_TOKEN_SIZE (64ULL << 20)
19
20/*
21 * Required by JSON (RFC 7159):
21 * From RFC 8259 "The JavaScript Object Notation (JSON) Data
22 * Interchange Format", with [comments in brackets]:
22 *
23 *
23 * \"([^\\\"]|\\[\"'\\/bfnrt]|\\u[0-9a-fA-F]{4})*\"
24 * -?(0|[1-9][0-9]*)(.[0-9]+)?([eE][-+]?[0-9]+)?
25 * [{}\[\],:]
26 * [a-z]+ # covers null, true, false
24 * The set of tokens includes six structural characters, strings,
25 * numbers, and three literal names.
27 *
26 *
28 * Extension of '' strings:
27 * These are the six structural characters:
29 *
28 *
30 * '([^\\']|\\[\"'\\/bfnrt]|\\u[0-9a-fA-F]{4})*'
29 * begin-array = ws %x5B ws ; [ left square bracket
30 * begin-object = ws %x7B ws ; { left curly bracket
31 * end-array = ws %x5D ws ; ] right square bracket
32 * end-object = ws %x7D ws ; } right curly bracket
33 * name-separator = ws %x3A ws ; : colon
34 * value-separator = ws %x2C ws ; , comma
31 *
35 *
32 * Extension for vararg handling in JSON construction:
36 * Insignificant whitespace is allowed before or after any of the six
37 * structural characters.
38 * [This lexer accepts it before or after any token, which is actually
39 * the same, as the grammar always has structural characters between
40 * other tokens.]
33 *
41 *
34 * %((l|ll|I64)?d|[ipsf])
42 * ws = *(
43 * %x20 / ; Space
44 * %x09 / ; Horizontal tab
45 * %x0A / ; Line feed or New line
46 * %x0D ) ; Carriage return
35 *
47 *
48 * [...] three literal names:
49 * false null true
50 * [This lexer accepts [a-z]+, and leaves rejecting unknown literal
51 * names to the parser.]
52 *
53 * [Numbers:]
54 *
55 * number = [ minus ] int [ frac ] [ exp ]
56 * decimal-point = %x2E ; .
57 * digit1-9 = %x31-39 ; 1-9
58 * e = %x65 / %x45 ; e E
59 * exp = e [ minus / plus ] 1*DIGIT
60 * frac = decimal-point 1*DIGIT
61 * int = zero / ( digit1-9 *DIGIT )
62 * minus = %x2D ; -
63 * plus = %x2B ; +
64 * zero = %x30 ; 0
65 *
66 * [Strings:]
67 * string = quotation-mark *char quotation-mark
68 *
69 * char = unescaped /
70 * escape (
71 * %x22 / ; " quotation mark U+0022
72 * %x5C / ; \ reverse solidus U+005C
73 * %x2F / ; / solidus U+002F
74 * %x62 / ; b backspace U+0008
75 * %x66 / ; f form feed U+000C
76 * %x6E / ; n line feed U+000A
77 * %x72 / ; r carriage return U+000D
78 * %x74 / ; t tab U+0009
79 * %x75 4HEXDIG ) ; uXXXX U+XXXX
80 * escape = %x5C ; \
81 * quotation-mark = %x22 ; "
82 * unescaped = %x20-21 / %x23-5B / %x5D-10FFFF
83 *
84 *
85 * Extensions over RFC 8259:
86 * - Extra escape sequence in strings:
87 * 0x27 (apostrophe) is recognized after escape, too
88 * - Single-quoted strings:
89 * Like double-quoted strings, except they're delimited by %x27
90 * (apostrophe) instead of %x22 (quotation mark), and can't contain
91 * unescaped apostrophe, but can contain unescaped quotation mark.
92 * - Interpolation:
93 * interpolation = %((l|ll|I64)[du]|[ipsf])
94 *
95 * Note:
96 * - Input must be encoded in UTF-8.
97 * - Decoding and validating is left to the parser.
36 */
37
38enum json_lexer_state {
39 IN_ERROR = 0, /* must really be 0, see json_lexer[] */
40 IN_DQ_UCODE3,
41 IN_DQ_UCODE2,
42 IN_DQ_UCODE1,
43 IN_DQ_UCODE0,

--- 347 unchanged lines hidden --- 		98 */
99
100enum json_lexer_state {
101 IN_ERROR = 0, /* must really be 0, see json_lexer[] */
102 IN_DQ_UCODE3,
103 IN_DQ_UCODE2,
104 IN_DQ_UCODE1,
105 IN_DQ_UCODE0,

--- 347 unchanged lines hidden ---