aboutsummaryrefslogtreecommitdiff
path: root/crates/ra_syntax/src/validation/byte_string.rs
blob: 7abe8f3303b24416d4e22c4b54884db7cc3df6db (plain)
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
use crate::{
    ast::{self, AstNode, AstToken},
    string_lexing::{self, StringComponentKind},
    yellow::{
        SyntaxError,
        SyntaxErrorKind::*,
    },
};

use super::byte;

pub(crate) fn validate_byte_string_node(node: &ast::ByteString, errors: &mut Vec<SyntaxError>) {
    let literal_text = node.text();
    let literal_range = node.syntax().range();
    let mut components = string_lexing::parse_byte_string_literal(literal_text);
    for component in &mut components {
        let range = component.range + literal_range.start();

        match component.kind {
            StringComponentKind::IgnoreNewline => { /* always valid */ }
            _ => {
                // Chars must escape \t, \n and \r codepoints, but strings don't
                let text = &literal_text[component.range];
                match text {
                    "\t" | "\n" | "\r" => { /* always valid */ }
                    _ => byte::validate_byte_component(text, component.kind, range, errors),
                }
            }
        }
    }

    if !components.has_closing_quote {
        errors.push(SyntaxError::new(UnclosedString, literal_range));
    }

    if let Some(range) = components.suffix {
        errors.push(SyntaxError::new(InvalidSuffix, range + literal_range.start()));
    }
}

#[cfg(test)]
mod test {
    use crate::{SourceFile, TreeArc};

    fn build_file(literal: &str) -> TreeArc<SourceFile> {
        let src = format!(r#"const S: &'static [u8] = b"{}";"#, literal);
        println!("Source: {}", src);
        SourceFile::parse(&src)
    }

    fn assert_valid_str(literal: &str) {
        let file = build_file(literal);
        assert!(file.errors().len() == 0, "Errors for literal '{}': {:?}", literal, file.errors());
    }

    fn assert_invalid_str(literal: &str) {
        let file = build_file(literal);
        assert!(file.errors().len() > 0);
    }

    #[test]
    fn test_ansi_codepoints() {
        for byte in 0..128 {
            match byte {
                b'\"' | b'\\' => { /* Ignore string close and backslash */ }
                _ => assert_valid_str(&(byte as char).to_string()),
            }
        }

        for byte in 128..=255u8 {
            assert_invalid_str(&(byte as char).to_string());
        }
    }

    #[test]
    fn test_unicode_codepoints() {
        let invalid = ["Ƒ", "バ", "メ", "﷽"];
        for c in &invalid {
            assert_invalid_str(c);
        }
    }

    #[test]
    fn test_unicode_multiple_codepoints() {
        let invalid = ["नी", "👨‍👨‍"];
        for c in &invalid {
            assert_invalid_str(c);
        }
    }

    #[test]
    fn test_valid_ascii_escape() {
        let valid = [r"\'", r#"\""#, r"\\", r"\n", r"\r", r"\t", r"\0", "a", "b"];
        for c in &valid {
            assert_valid_str(c);
        }
    }

    #[test]
    fn test_invalid_ascii_escape() {
        let invalid = [r"\a", r"\?", r"\"];
        for c in &invalid {
            assert_invalid_str(c);
        }
    }

    #[test]
    fn test_valid_ascii_code_escape() {
        let valid = [r"\x00", r"\x7F", r"\x55", r"\xF0"];
        for c in &valid {
            assert_valid_str(c);
        }
    }

    #[test]
    fn test_invalid_ascii_code_escape() {
        let invalid = [r"\x", r"\x7"];
        for c in &invalid {
            assert_invalid_str(c);
        }
    }

    #[test]
    fn test_invalid_unicode_escape() {
        let well_formed = [r"\u{FF}", r"\u{0}", r"\u{F}", r"\u{10FFFF}", r"\u{1_0__FF___FF_____}"];
        for c in &well_formed {
            assert_invalid_str(c);
        }

        let invalid = [
            r"\u",
            r"\u{}",
            r"\u{",
            r"\u{FF",
            r"\u{FFFFFF}",
            r"\u{_F}",
            r"\u{00FFFFF}",
            r"\u{110000}",
        ];
        for c in &invalid {
            assert_invalid_str(c);
        }
    }

    #[test]
    fn test_mixed_invalid() {
        assert_invalid_str(
            r"This is the tale of a string
with a newline in between, some emoji (👨‍👨‍) here and there,
unicode escapes like this: \u{1FFBB} and weird stuff like
this ﷽",
        );
    }

    #[test]
    fn test_mixed_valid() {
        assert_valid_str(
            r"This is the tale of a string
with a newline in between, no emoji at all,
nor unicode escapes or weird stuff",
        );
    }

    #[test]
    fn test_ignore_newline() {
        assert_valid_str(
            "Hello \
             World",
        );
    }
}