3 use expect_test::{expect, Expect};
5 fn check_raw_str(s: &str, expected_hashes: u8, expected_err: Option<RawStrError>) {
6 let s = &format!("r{}", s);
7 let mut cursor = Cursor::new(s);
9 let (n_hashes, err) = cursor.raw_double_quoted_string(0);
10 assert_eq!(n_hashes, expected_hashes);
11 assert_eq!(err, expected_err);
15 fn test_naked_raw_str() {
16 check_raw_str(r#""abc""#, 0, None);
20 fn test_raw_no_start() {
21 check_raw_str(r##""abc"#"##, 0, None);
25 fn test_too_many_terminators() {
26 // this error is handled in the parser later
27 check_raw_str(r###"#"abc"##"###, 1, None);
31 fn test_unterminated() {
35 Some(RawStrError::NoTerminator { expected: 1, found: 0, possible_terminator_offset: None }),
40 Some(RawStrError::NoTerminator {
43 possible_terminator_offset: Some(7),
46 // We're looking for "# not just any #
50 Some(RawStrError::NoTerminator { expected: 2, found: 0, possible_terminator_offset: None }),
55 fn test_invalid_start() {
56 check_raw_str(r##"#~"abc"#"##, 1, Some(RawStrError::InvalidStarter { bad_char: '~' }));
60 fn test_unterminated_no_pound() {
61 // https://github.com/rust-lang/rust/issues/70677
65 Some(RawStrError::NoTerminator { expected: 0, found: 0, possible_terminator_offset: None }),
70 fn test_too_many_hashes() {
71 let max_count = u8::MAX;
72 let mut hashes: String = "#".repeat(max_count.into());
74 // Valid number of hashes (255 = 2^8 - 1 = u8::MAX), but invalid string.
75 check_raw_str(&hashes, max_count, Some(RawStrError::InvalidStarter { bad_char: '\u{0}' }));
77 // One more hash sign (256 = 2^8) becomes too many.
82 Some(RawStrError::TooManyDelimiters { found: usize::from(max_count) + 1 }),
87 fn test_valid_shebang() {
88 // https://github.com/rust-lang/rust/issues/70528
89 let input = "#!/usr/bin/rustrun\nlet x = 5;";
90 assert_eq!(strip_shebang(input), Some(18));
94 fn test_invalid_shebang_valid_rust_syntax() {
95 // https://github.com/rust-lang/rust/issues/70528
96 let input = "#! [bad_attribute]";
97 assert_eq!(strip_shebang(input), None);
101 fn test_shebang_second_line() {
102 // Because shebangs are interpreted by the kernel, they must be on the first line
103 let input = "\n#!/bin/bash";
104 assert_eq!(strip_shebang(input), None);
108 fn test_shebang_space() {
109 let input = "#! /bin/bash";
110 assert_eq!(strip_shebang(input), Some(input.len()));
114 fn test_shebang_empty_shebang() {
115 let input = "#! \n[attribute(foo)]";
116 assert_eq!(strip_shebang(input), None);
120 fn test_invalid_shebang_comment() {
121 let input = "#!//bin/ami/a/comment\n[";
122 assert_eq!(strip_shebang(input), None)
126 fn test_invalid_shebang_another_comment() {
127 let input = "#!/*bin/ami/a/comment*/\n[attribute";
128 assert_eq!(strip_shebang(input), None)
132 fn test_shebang_valid_rust_after() {
133 let input = "#!/*bin/ami/a/comment*/\npub fn main() {}";
134 assert_eq!(strip_shebang(input), Some(23))
138 fn test_shebang_followed_by_attrib() {
139 let input = "#!/bin/rust-scripts\n#![allow_unused(true)]";
140 assert_eq!(strip_shebang(input), Some(19));
143 fn check_lexing(src: &str, expect: Expect) {
144 let actual: String = tokenize(src).map(|token| format!("{:?}\n", token)).collect();
145 expect.assert_eq(&actual)
151 "/* my source file */ fn main() { println!(\"zebra\"); }\n",
153 Token { kind: BlockComment { doc_style: None, terminated: true }, len: 20 }
154 Token { kind: Whitespace, len: 1 }
155 Token { kind: Ident, len: 2 }
156 Token { kind: Whitespace, len: 1 }
157 Token { kind: Ident, len: 4 }
158 Token { kind: OpenParen, len: 1 }
159 Token { kind: CloseParen, len: 1 }
160 Token { kind: Whitespace, len: 1 }
161 Token { kind: OpenBrace, len: 1 }
162 Token { kind: Whitespace, len: 1 }
163 Token { kind: Ident, len: 7 }
164 Token { kind: Bang, len: 1 }
165 Token { kind: OpenParen, len: 1 }
166 Token { kind: Literal { kind: Str { terminated: true }, suffix_start: 7 }, len: 7 }
167 Token { kind: CloseParen, len: 1 }
168 Token { kind: Semi, len: 1 }
169 Token { kind: Whitespace, len: 1 }
170 Token { kind: CloseBrace, len: 1 }
171 Token { kind: Whitespace, len: 1 }
177 fn comment_flavors() {
187 /** outer doc block */
188 /*! inner doc block */
191 Token { kind: Whitespace, len: 1 }
192 Token { kind: LineComment { doc_style: None }, len: 7 }
193 Token { kind: Whitespace, len: 1 }
194 Token { kind: LineComment { doc_style: None }, len: 17 }
195 Token { kind: Whitespace, len: 1 }
196 Token { kind: LineComment { doc_style: Some(Outer) }, len: 18 }
197 Token { kind: Whitespace, len: 1 }
198 Token { kind: LineComment { doc_style: Some(Inner) }, len: 18 }
199 Token { kind: Whitespace, len: 1 }
200 Token { kind: BlockComment { doc_style: None, terminated: true }, len: 11 }
201 Token { kind: Whitespace, len: 1 }
202 Token { kind: BlockComment { doc_style: None, terminated: true }, len: 4 }
203 Token { kind: Whitespace, len: 1 }
204 Token { kind: BlockComment { doc_style: None, terminated: true }, len: 18 }
205 Token { kind: Whitespace, len: 1 }
206 Token { kind: BlockComment { doc_style: Some(Outer), terminated: true }, len: 22 }
207 Token { kind: Whitespace, len: 1 }
208 Token { kind: BlockComment { doc_style: Some(Inner), terminated: true }, len: 22 }
209 Token { kind: Whitespace, len: 1 }
215 fn nested_block_comments() {
219 Token { kind: BlockComment { doc_style: None, terminated: true }, len: 11 }
220 Token { kind: Literal { kind: Char { terminated: true }, suffix_start: 3 }, len: 3 }
230 Token { kind: Literal { kind: Char { terminated: true }, suffix_start: 3 }, len: 3 }
231 Token { kind: Whitespace, len: 1 }
232 Token { kind: Literal { kind: Char { terminated: true }, suffix_start: 3 }, len: 3 }
233 Token { kind: Whitespace, len: 1 }
234 Token { kind: Literal { kind: Char { terminated: true }, suffix_start: 4 }, len: 4 }
244 Token { kind: Lifetime { starts_with_number: false }, len: 4 }
252 "r###\"\"#a\\b\x00c\"\"###",
254 Token { kind: Literal { kind: RawStr { n_hashes: 3, err: None }, suffix_start: 17 }, len: 17 }
260 fn literal_suffixes() {
277 Token { kind: Whitespace, len: 1 }
278 Token { kind: Literal { kind: Char { terminated: true }, suffix_start: 3 }, len: 3 }
279 Token { kind: Whitespace, len: 1 }
280 Token { kind: Literal { kind: Byte { terminated: true }, suffix_start: 4 }, len: 4 }
281 Token { kind: Whitespace, len: 1 }
282 Token { kind: Literal { kind: Str { terminated: true }, suffix_start: 3 }, len: 3 }
283 Token { kind: Whitespace, len: 1 }
284 Token { kind: Literal { kind: ByteStr { terminated: true }, suffix_start: 4 }, len: 4 }
285 Token { kind: Whitespace, len: 1 }
286 Token { kind: Literal { kind: Int { base: Decimal, empty_int: false }, suffix_start: 4 }, len: 4 }
287 Token { kind: Whitespace, len: 1 }
288 Token { kind: Literal { kind: Int { base: Binary, empty_int: false }, suffix_start: 5 }, len: 5 }
289 Token { kind: Whitespace, len: 1 }
290 Token { kind: Literal { kind: Int { base: Hexadecimal, empty_int: false }, suffix_start: 5 }, len: 5 }
291 Token { kind: Whitespace, len: 1 }
292 Token { kind: Literal { kind: Float { base: Decimal, empty_exponent: false }, suffix_start: 3 }, len: 3 }
293 Token { kind: Whitespace, len: 1 }
294 Token { kind: Literal { kind: Float { base: Decimal, empty_exponent: false }, suffix_start: 6 }, len: 6 }
295 Token { kind: Whitespace, len: 1 }
296 Token { kind: Literal { kind: Int { base: Decimal, empty_int: false }, suffix_start: 1 }, len: 3 }
297 Token { kind: Whitespace, len: 1 }
298 Token { kind: Literal { kind: RawStr { n_hashes: 3, err: None }, suffix_start: 12 }, len: 18 }
299 Token { kind: Whitespace, len: 1 }
300 Token { kind: Literal { kind: RawByteStr { n_hashes: 3, err: None }, suffix_start: 13 }, len: 19 }
301 Token { kind: Whitespace, len: 1 }