jless 0.9.0

A command-line JSON viewer
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
234
235
236
237
238
239
240

use std::fmt;
use std::fmt::Write;

pub struct UnescapeError {
    index: usize,
    codepoint_chars: [u8; 4],
    error: UnicodeError,
}

enum UnicodeError {
    UnexpectedLowSurrogate,
    UnmatchedHighSurrogate,
}

impl fmt::Display for UnescapeError {
    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
        write!(f, "unescaping error at char {}: ", self.index)?;
        let codepoint_chars = std::str::from_utf8(&self.codepoint_chars).unwrap();
        match &self.error {
            UnicodeError::UnexpectedLowSurrogate => {
                write!(f, "unexpected low surrogate \"\\u{codepoint_chars}\"")
            }
            UnicodeError::UnmatchedHighSurrogate => write!(
                f,
                "high surrogate \"\\u{codepoint_chars}\" not followed by low surrogate"
            ),
        }
    }
}

enum DecodedCodepoint {
    Char(char),
    LowSurrogate(u16),
    HighSurrogate(u16),
}

// Unescapes a syntactically valid JSON string into a valid UTF-8 string,
// except for Unicode control characters.
//
// This makes the assumption that the only characters following a '\' are:
// - single character escapes: "\/bfnrt
// - a unicode character escape: uxxxx
//
// Unicode escapes are exactly four characters, and essentially represent
// UTF-16 encoded codepoints.
//
// Unicode codepoints between U+010000 and U+10FFFF (codepoints outside
// the Basic Multilingual Plane) must be encoded as a surrogate pair.
//
// For more information, and a walkthrough of how to convert the surrogate pairs
// back into an actual char, see:
// https://en.wikipedia.org/wiki/UTF-16#Code_points_from_U+010000_to_U+10FFFF
pub fn unescape_json_string(s: &str) -> Result<String, UnescapeError> {
    let mut chars = s.chars();
    let mut unescaped = String::with_capacity(s.len());
    let mut index = 1;

    while let Some(ch) = chars.next() {
        index += 1;
        if ch != '\\' {
            if is_control(ch) {
                unescaped.push_str("\\u00");
                write!(unescaped, "{:02X}", ch as u32).unwrap();
            } else {
                unescaped.push(ch);
            }
            continue;
        }

        let escaped = chars.next().unwrap();
        index += 1;

        match escaped {
            '"' => unescaped.push('"'),
            '\\' => unescaped.push('\\'),
            '/' => unescaped.push('/'),
            // '\b' is backspace, a control character.
            'b' => unescaped.push_str("\\b"),
            'f' => unescaped.push('\x0c'),
            'n' => unescaped.push('\n'),
            'r' => unescaped.push('\r'),
            't' => unescaped.push('\t'),
            'u' => {
                let (codepoint, codepoint_chars) = parse_codepoint_from_chars(&mut chars);
                index += 4;

                match decode_codepoint(codepoint) {
                    DecodedCodepoint::Char(ch) => {
                        if is_control(ch) {
                            unescaped.push_str("\\u");
                            unescaped.push(codepoint_chars[0] as char);
                            unescaped.push(codepoint_chars[1] as char);
                            unescaped.push(codepoint_chars[2] as char);
                            unescaped.push(codepoint_chars[3] as char);
                        } else {
                            unescaped.push(ch)
                        }
                    }
                    DecodedCodepoint::LowSurrogate(_) => {
                        return Err(UnescapeError {
                            index: index - 6,
                            codepoint_chars,
                            error: UnicodeError::UnexpectedLowSurrogate,
                        });
                    }
                    DecodedCodepoint::HighSurrogate(hs) => match (chars.next(), chars.next()) {
                        (Some('\\'), Some('u')) => {
                            index += 2;
                            let (codepoint, _) = parse_codepoint_from_chars(&mut chars);
                            index += 4;

                            match decode_codepoint(codepoint) {
                                DecodedCodepoint::LowSurrogate(ls) => {
                                    let codepoint = (hs as u32) * 0x400 + (ls as u32) + 0x10000;
                                    unescaped.push(char::from_u32(codepoint).unwrap());
                                }
                                _ => {
                                    return Err(UnescapeError {
                                        index,
                                        codepoint_chars,
                                        error: UnicodeError::UnmatchedHighSurrogate,
                                    });
                                }
                            }
                        }
                        _ => {
                            return Err(UnescapeError {
                                index,
                                codepoint_chars,
                                error: UnicodeError::UnmatchedHighSurrogate,
                            });
                        }
                    },
                }
            }
            _ => panic!("Unexpected escape character in JSON string: {}", ch),
        }
    }

    Ok(unescaped)
}

fn is_control(ch: char) -> bool {
    matches!(ch as u32, 0x00..=0x1F | 0x7F..=0x9F)
}

// Consumes four hex characters from a Chars iterator, and converts it to a u16.
// Also returns the four original characters as a mini [u8] that can be safely
// interpreted as a str.
fn parse_codepoint_from_chars(chars: &mut std::str::Chars<'_>) -> (u16, [u8; 4]) {
    let mut codepoint = 0;
    let chars = [
        chars.next().unwrap(),
        chars.next().unwrap(),
        chars.next().unwrap(),
        chars.next().unwrap(),
    ];
    let utf8_chars = [
        chars[0] as u8,
        chars[1] as u8,
        chars[2] as u8,
        chars[3] as u8,
    ];
    codepoint += hex_char_to_int(chars[0]) * 0x1000;
    codepoint += hex_char_to_int(chars[1]) * 0x0100;
    codepoint += hex_char_to_int(chars[2]) * 0x0010;
    codepoint += hex_char_to_int(chars[3]);
    (codepoint, utf8_chars)
}

fn hex_char_to_int(ch: char) -> u16 {
    match ch {
        '0'..='9' => (ch as u16) - ('0' as u16),
        'a'..='f' => (ch as u16) - ('a' as u16) + 10,
        'A'..='f' => (ch as u16) - ('A' as u16) + 10,
        _ => panic!("Unexpected non-hex digit: {}", ch),
    }
}

// Interprets a codepoint in the Basic Multilingual Plane as either an actual
// char, or one of a surrogate pair. The value associated with the surrogate
// has had the offset removed.
fn decode_codepoint(codepoint: u16) -> DecodedCodepoint {
    match codepoint {
        0xD800..=0xDBFF => DecodedCodepoint::HighSurrogate(codepoint - 0xD800),
        0xDC00..=0xDFFF => DecodedCodepoint::LowSurrogate(codepoint - 0xDC00),
        _ => DecodedCodepoint::Char(char::from_u32(codepoint as u32).unwrap()),
    }
}

#[cfg(test)]
mod tests {
    use super::*;

    #[track_caller]
    fn check(escaped: &str, expected_unescaped: &str) {
        let unescaped = match unescape_json_string(escaped) {
            Ok(s) => s,
            Err(err) => format!("ERR: {err}"),
        };

        assert_eq!(expected_unescaped, &unescaped);
    }

    #[test]
    fn test_unescape_json_string() {
        // Ok
        check("abc", "abc");
        check("abc \\\\ \\\"", "abc \\ \"");
        check("abc \\n \\t \\r", "abc \n \t \r");
        check("abc \\n \\t \\r", "abc \n \t \r");
        check("€ \\u20AC", "€ \u{20AC}");
        check("𐐷 \\uD801\\uDC37", "𐐷 \u{10437}");

        // Control characters don't get unescaped
        check("12x\\b34", "12x\\b34");
        check(
            "\\u0000 | \\u001f | \\u0020 | \\u007e | \\u007f | \\u0080 | \\u009F | \\u00a0",
            "\\u0000 | \\u001f | \u{0020} | \u{007e} | \\u007f | \\u0080 | \\u009F | \u{00a0}",
        );

        // Non-ASCII unescaped control codes get escaped
        check("12 \u{0080} 34", "12 \\u0080 34");

        // Errors; make sure index is computed properly.
        check(
            "abc 𐐷 \\uD801\\uDC37 \\uD801",
            // "abc 𐐷 \uD801\uDC37 \uD801"
            // 0 2 4 6 8 0 2 4 6 8 0 2 4 6
            "ERR: unescaping error at char 26: high surrogate \"\\uD801\" not followed by low surrogate",
        );

        check(
            "abc 𐐷 \\uD801\\uDC37 \\uDC37",
            // "abc 𐐷 \uD801\uDC37 \uDC37"
            // 0 2 4 6 8 0 2 4 6 8 0 2 4 6
            "ERR: unescaping error at char 20: unexpected low surrogate \"\\uDC37\"",
        );
    }
}