1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
/*
 * AquaVM Workflow Engine
 *
 * Copyright (C) 2024 Fluence DAO
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU Affero General Public License as
 * published by the Free Software Foundation version 3 of the
 * License.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU Affero General Public License for more details.
 *
 * You should have received a copy of the GNU Affero General Public License
 * along with this program.  If not, see <https://www.gnu.org/licenses/>.
 */

/*
 *
 * Based on the JSON parser from nom examples:
 *
 * Copyright (c) 2014-2019 Geoffroy Couprie
 *
 * Permission is hereby granted, free of charge, to any person obtaining
 * a copy of this software and associated documentation files (the
 * "Software"), to deal in the Software without restriction, including
 * without limitation the rights to use, copy, modify, merge, publish,
 * distribute, sublicense, and/or sell copies of the Software, and to
 * permit persons to whom the Software is furnished to do so, subject to
 * the following conditions:
 *
 * The above copyright notice and this permission notice shall be
 * included in all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
 * LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
 * OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
 * WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 */

use nom::{
    branch::alt,
    bytes::complete::{escaped, tag, take_while},
    character::complete::{char, one_of, satisfy},
    combinator::{cut, map, opt, value},
    error::{context, ContextError, ParseError},
    multi::separated_list0,
    number::complete::double,
    sequence::{delimited, preceded, separated_pair, terminated},
    IResult,
};
use std::collections::HashMap;
use std::str;

#[derive(Debug, PartialEq)]
pub enum JsonValue {
    Null,
    Str(String),
    Boolean(bool),
    Num(f64),
    Array(Vec<JsonValue>),
    Object(HashMap<String, JsonValue>),
}

/// parser combinators are constructed from the bottom up:
/// first we write parsers for the smallest elements (here a space character),
/// then we'll combine them in larger parsers
fn sp<'a, E: ParseError<&'a str>>(i: &'a str) -> IResult<&'a str, &'a str, E> {
    let chars = " \t\r\n";

    // nom combinators like `take_while` return a function. That function is the
    // parser,to which we can pass the input
    take_while(move |c| chars.contains(c))(i)
}

/// A nom parser has the following signature:
/// `Input -> IResult<Input, Output, Error>`, with `IResult` defined as:
/// `type IResult<I, O, E = (I, ErrorKind)> = Result<(I, O), Err<E>>;`
///
/// most of the times you can ignore the error type and use the default (but this
/// examples shows custom error types later on!)
///
/// Here we use `&str` as input type, but nom parsers can be generic over
/// the input type, and work directly with `&[u8]` or any other type that
/// implements the required traits.
///
/// Finally, we can see here that the input and output type are both `&str`
/// with the same lifetime tag. This means that the produced value is a subslice
/// of the input data. and there is no allocation needed. This is the main idea
/// behind nom's performance.
fn parse_str<'a, E: ParseError<&'a str>>(i: &'a str) -> IResult<&'a str, &'a str, E> {
    escaped(
        satisfy(|c| ('\u{20}'..='\u{10FFFF}').contains(&c) && (c != '\\') && (c != '"')),
        '\\',
        one_of("\"n\\"),
    )(i)
}

/// `tag(string)` generates a parser that recognizes the argument string.
///
/// we can combine it with other functions, like `value` that takes another
/// parser, and if that parser returns without an error, returns a given
/// constant value.
///
/// `alt` is another combinator that tries multiple parsers one by one, until
/// one of them succeeds
fn boolean<'a, E: ParseError<&'a str>>(input: &'a str) -> IResult<&'a str, bool, E> {
    // This is a parser that returns `true` if it sees the string "true", and
    // an error otherwise
    let parse_true = value(true, tag("true"));

    // This is a parser that returns `false` if it sees the string "false", and
    // an error otherwise
    let parse_false = value(false, tag("false"));

    // `alt` combines the two parsers. It returns the result of the first
    // successful parser, or an error
    alt((parse_true, parse_false))(input)
}

fn null<'a, E: ParseError<&'a str>>(input: &'a str) -> IResult<&'a str, (), E> {
    value((), tag("null"))(input)
}

/// this parser combines the previous `parse_str` parser, that recognizes the
/// interior of a string, with a parse to recognize the double quote character,
/// before the string (using `preceded`) and after the string (using `terminated`).
///
/// `context` and `cut` are related to error management:
/// - `cut` transforms an `Err::Error(e)` in `Err::Failure(e)`, signaling to
/// combinators like  `alt` that they should not try other parsers. We were in the
/// right branch (since we found the `"` character) but encountered an error when
/// parsing the string
/// - `context` lets you add a static string to provide more information in the
/// error chain (to indicate which parser had an error)
fn string<'a, E: ParseError<&'a str> + ContextError<&'a str>>(
    i: &'a str,
) -> IResult<&'a str, &'a str, E> {
    context(
        "string",
        preceded(char('\"'), cut(terminated(parse_str, char('\"')))),
    )(i)
}

/// some combinators, like `separated_list0` or `many0`, will call a parser repeatedly,
/// accumulating results in a `Vec`, until it encounters an error.
/// If you want more control on the parser application, check out the `iterator`
/// combinator (cf `examples/iterator.rs`)
fn array<'a, E: ParseError<&'a str> + ContextError<&'a str>>(
    i: &'a str,
) -> IResult<&'a str, Vec<JsonValue>, E> {
    context(
        "array",
        preceded(
            char('['),
            cut(terminated(
                separated_list0(preceded(sp, char(',')), json_value),
                preceded(sp, char(']')),
            )),
        ),
    )(i)
}

fn key_value<'a, E: ParseError<&'a str> + ContextError<&'a str>>(
    i: &'a str,
) -> IResult<&'a str, (&'a str, JsonValue), E> {
    separated_pair(
        preceded(sp, string),
        cut(preceded(sp, char(':'))),
        json_value,
    )(i)
}

pub fn hash<'a, E: ParseError<&'a str> + ContextError<&'a str>>(
    i: &'a str,
) -> IResult<&'a str, HashMap<String, JsonValue>, E> {
    context(
        "map",
        preceded(
            char('{'),
            cut(terminated(
                map(
                    separated_list0(preceded(sp, char(',')), key_value),
                    |tuple_vec| {
                        tuple_vec
                            .into_iter()
                            .map(|(k, v)| (String::from(k), v))
                            .collect()
                    },
                ),
                preceded(sp, char('}')),
            )),
        ),
    )(i)
}

/// here, we apply the space parser before trying to parse a value
pub fn json_value<'a, E: ParseError<&'a str> + ContextError<&'a str>>(
    i: &'a str,
) -> IResult<&'a str, JsonValue, E> {
    preceded(
        sp,
        alt((
            map(hash, JsonValue::Object),
            map(array, JsonValue::Array),
            map(string, |s| JsonValue::Str(String::from(s))),
            map(double, JsonValue::Num),
            map(boolean, JsonValue::Boolean),
            map(null, |_| JsonValue::Null),
        )),
    )(i)
}

/// the root element of a JSON parser is either an object or an array
#[allow(dead_code)]
pub fn root<'a, E: ParseError<&'a str> + ContextError<&'a str>>(
    i: &'a str,
) -> IResult<&'a str, JsonValue, E> {
    delimited(
        sp,
        alt((
            map(hash, JsonValue::Object),
            map(array, JsonValue::Array),
            map(null, |_| JsonValue::Null),
        )),
        opt(sp),
    )(i)
}