rust/tests/ui/regex.rs

153 lines
4.9 KiB
Rust
Raw Normal View History

#![allow(
unused,
clippy::needless_raw_strings,
clippy::needless_raw_string_hashes,
clippy::needless_borrow,
clippy::needless_borrows_for_generic_args
)]
#![warn(clippy::invalid_regex, clippy::trivial_regex, clippy::regex_creation_in_loops)]
2016-02-04 17:36:06 -06:00
extern crate regex;
2018-12-09 16:26:16 -06:00
use regex::bytes::{Regex as BRegex, RegexBuilder as BRegexBuilder, RegexSet as BRegexSet};
use regex::{Regex, RegexBuilder, RegexSet};
2016-02-04 17:36:06 -06:00
const OPENING_PAREN: &str = "(";
const NOT_A_REAL_REGEX: &str = "foobar";
2016-02-05 09:48:35 -06:00
2016-02-05 16:10:48 -06:00
fn syntax_error() {
2016-02-04 17:36:06 -06:00
let pipe_in_wrong_position = Regex::new("|");
//~^ ERROR: trivial regex
2016-05-25 14:36:51 -05:00
let pipe_in_wrong_position_builder = RegexBuilder::new("|");
//~^ ERROR: trivial regex
2016-02-05 14:54:29 -06:00
let wrong_char_ranice = Regex::new("[z-a]");
//~^ ERROR: regex syntax error: invalid character class range, the start must be <= th
//~| NOTE: `-D clippy::invalid-regex` implied by `-D warnings`
2016-05-07 17:56:23 -05:00
let some_unicode = Regex::new("[é-è]");
//~^ ERROR: regex syntax error: invalid character class range, the start must be <= th
2017-02-08 07:58:07 -06:00
2016-02-05 09:48:35 -06:00
let some_regex = Regex::new(OPENING_PAREN);
2017-02-08 07:58:07 -06:00
2016-05-25 10:15:19 -05:00
let binary_pipe_in_wrong_position = BRegex::new("|");
//~^ ERROR: trivial regex
2016-05-25 10:15:19 -05:00
let some_binary_regex = BRegex::new(OPENING_PAREN);
2016-05-25 14:36:51 -05:00
let some_binary_regex_builder = BRegexBuilder::new(OPENING_PAREN);
2017-02-08 07:58:07 -06:00
2016-02-05 09:48:35 -06:00
let closing_paren = ")";
let not_linted = Regex::new(closing_paren);
2016-05-25 10:15:19 -05:00
2018-12-09 16:26:16 -06:00
let set = RegexSet::new(&[r"[a-z]+@[a-z]+\.(com|org|net)", r"[a-z]+\.(com|org|net)"]);
2016-05-25 10:15:19 -05:00
let bset = BRegexSet::new(&[
r"[a-z]+@[a-z]+\.(com|org|net)",
r"[a-z]+\.(com|org|net)",
2018-04-07 15:18:51 -05:00
r".", // regression test
2016-05-25 10:15:19 -05:00
]);
2018-12-09 16:26:16 -06:00
let set_error = RegexSet::new(&[OPENING_PAREN, r"[a-z]+\.(com|org|net)"]);
let bset_error = BRegexSet::new(&[OPENING_PAREN, r"[a-z]+\.(com|org|net)"]);
// These following three cases are considering valid since regex-1.8.0
let raw_string_error = Regex::new(r"[...\/...]");
let raw_string_error = Regex::new(r#"[...\/...]"#);
let _ = Regex::new(r"(?<hi>hi)").unwrap();
let escaped_string_span = Regex::new("\\b\\c");
let aux_span = Regex::new("(?ixi)");
//~^ ERROR: regex syntax error: duplicate flag
let should_not_lint = Regex::new("(?u).");
let should_not_lint = BRegex::new("(?u).");
let invalid_utf8_should_not_lint = BRegex::new("(?-u).");
let invalid_utf8_should_lint = Regex::new("(?-u).");
//~^ ERROR: regex syntax error: pattern can match invalid UTF-8
2016-02-04 17:36:06 -06:00
}
2016-02-05 16:10:48 -06:00
fn trivial_regex() {
let trivial_eq = Regex::new("^foobar$");
//~^ ERROR: trivial regex
2017-02-08 07:58:07 -06:00
2016-05-25 14:36:51 -05:00
let trivial_eq_builder = RegexBuilder::new("^foobar$");
//~^ ERROR: trivial regex
2017-02-08 07:58:07 -06:00
2016-02-05 16:10:48 -06:00
let trivial_starts_with = Regex::new("^foobar");
//~^ ERROR: trivial regex
2017-02-08 07:58:07 -06:00
2016-02-05 16:10:48 -06:00
let trivial_ends_with = Regex::new("foobar$");
//~^ ERROR: trivial regex
2017-02-08 07:58:07 -06:00
2016-02-05 16:10:48 -06:00
let trivial_contains = Regex::new("foobar");
//~^ ERROR: trivial regex
2017-02-08 07:58:07 -06:00
2016-02-05 16:10:48 -06:00
let trivial_contains = Regex::new(NOT_A_REAL_REGEX);
//~^ ERROR: trivial regex
2017-02-08 07:58:07 -06:00
2016-02-06 11:06:39 -06:00
let trivial_backslash = Regex::new("a\\.b");
//~^ ERROR: trivial regex
2017-02-08 07:58:07 -06:00
2016-02-05 16:10:48 -06:00
// unlikely corner cases
let trivial_empty = Regex::new("");
//~^ ERROR: trivial regex
2017-02-08 07:58:07 -06:00
2016-02-06 11:06:39 -06:00
let trivial_empty = Regex::new("^");
//~^ ERROR: trivial regex
2017-02-08 07:58:07 -06:00
2016-02-05 16:10:48 -06:00
let trivial_empty = Regex::new("^$");
//~^ ERROR: trivial regex
2017-02-08 07:58:07 -06:00
2016-05-25 10:15:19 -05:00
let binary_trivial_empty = BRegex::new("^$");
//~^ ERROR: trivial regex
2017-02-08 07:58:07 -06:00
2016-02-05 16:10:48 -06:00
// non-trivial regexes
2016-02-06 11:06:39 -06:00
let non_trivial_dot = Regex::new("a.b");
2016-05-25 14:36:51 -05:00
let non_trivial_dot_builder = RegexBuilder::new("a.b");
let non_trivial_dot = Regex::new(".");
let non_trivial_dot = BRegex::new(".");
2016-02-05 16:10:48 -06:00
let non_trivial_eq = Regex::new("^foo|bar$");
let non_trivial_starts_with = Regex::new("^foo|bar");
let non_trivial_ends_with = Regex::new("^foo|bar");
let non_trivial_ends_with = Regex::new("foo|bar");
2016-05-25 10:15:19 -05:00
let non_trivial_binary = BRegex::new("foo|bar");
2016-05-25 14:36:51 -05:00
let non_trivial_binary_builder = BRegexBuilder::new("foo|bar");
// #6005: unicode classes in bytes::Regex
let a_byte_of_unicode = BRegex::new(r"\p{C}");
2024-01-02 18:21:51 -06:00
// start and end word boundary, introduced in regex 0.10
let _ = BRegex::new(r"\<word\>");
let _ = BRegex::new(r"\b{start}word\b{end}");
2016-02-05 16:10:48 -06:00
}
fn regex_creation_in_loops() {
loop {
static STATIC_REGEX: std::sync::LazyLock<Regex> = std::sync::LazyLock::new(|| Regex::new("a.b").unwrap());
let regex = Regex::new("a.b");
//~^ ERROR: compiling a regex in a loop
let regex = BRegex::new("a.b");
//~^ ERROR: compiling a regex in a loop
#[allow(clippy::regex_creation_in_loops)]
let allowed_regex = Regex::new("a.b");
if true {
let regex = Regex::new("a.b");
//~^ ERROR: compiling a regex in a loop
}
for _ in 0..10 {
let nested_regex = Regex::new("a.b");
//~^ ERROR: compiling a regex in a loop
}
}
for i in 0..10 {
let dependant_regex = Regex::new(&format!("{i}"));
}
}
2016-02-05 16:10:48 -06:00
fn main() {
syntax_error();
trivial_regex();
regex_creation_in_loops();
2016-02-05 16:10:48 -06:00
}