slugify/lib.rs
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355
//! **A utility macro for flexible slug genereation that handles unicode.**
//!
//! The `slugify!` macro implements a flexible slug generator, allowing for stop words, custom separator
//! and maximum length options. The macro provides both a simple interface with sane default parameters
//! but also allows the parameters to be overriden when needed.
//!
//! Features:
//!
//!* Unicode strings support (phonetic conversion).
//!* Support for custom slug separator.
//!* Stop words filtering.
//!* Slug maximum length support.
//!
//!
//!# Usage
//!
//! This crate is on crates.io and can be used by adding `slugify` to the dependencies in your project's
//! `Cargo.toml`
//!
//! ```toml
//! [dependencies]
//! slugify = "0.1.0"
//! ```
//!
//! and this to your crate root:
//!
//!```rust,ignore
//! #[macro_use] extern crate slugify;
//!use slugify::slugify;
//!```
//!
//!# Examples
//!
//!## Basic slug generation
//!
//!```rust
//! # #[macro_use] extern crate slugify;
//! # use slugify::slugify;
//! # fn main() {
//!assert_eq!(slugify!("hello world"), "hello-world");
//! # }
//!```
//!
//!## Using a custom separator
//!
//! ```rust
//! # #[macro_use] extern crate slugify;
//! # use slugify::slugify;
//! # fn main() {
//!assert_eq!(slugify!("hello world", separator = "."), "hello.world");
//!assert_eq!(slugify!("hello world", separator = " "), "hello world");
//! # }
//! ```
//!
//!## Stop words filtering
//!
//!```rust
//! # #[macro_use] extern crate slugify;
//! # use slugify::slugify;
//! # fn main() {
//!assert_eq!(slugify!("the quick brown fox jumps over the lazy dog", stop_words = "the,fox"), "quick-brown-jumps-over-lazy-dog");
//! # }
//!```
//!
//!## Maximum length
//!
//!```rust
//! # #[macro_use] extern crate slugify;
//! # use slugify::slugify;
//! # fn main() {
//!assert_eq!(slugify!("hello world", max_length = 5), "hello");
//!assert_eq!(slugify!("the hello world", stop_words = "the", max_length = 5), "hello");
//! # }
//!```
//!
//!## Phonetic Conversion and accented text
//!
//!```rust
//! # #[macro_use] extern crate slugify;
//! # use slugify::slugify;
//! # fn main() {
//!assert_eq!(slugify!("影師嗎"), "ying-shi-ma");
//!assert_eq!(slugify!("Æúű--cool?"), "aeuu-cool");
//!assert_eq!(slugify!("Nín hǎo. Wǒ shì zhōng guó rén"), "nin-hao-wo-shi-zhong-guo-ren");
//! # }
//!```
//!
//!## Passing multiple optional parameters.
//!
//! **NOTE:** the order of optional parameters matters: **stop_words**, **separator**
//! and then **max_length**. All of them are optional, however when specifying more than one optional parameter, this
//! order must be adhered.
//!
//!```rust
//! # #[macro_use] extern crate slugify;
//! # use slugify::slugify;
//! # fn main() {
//!assert_eq!(slugify!("the hello world", stop_words = "the", separator = "-"), "hello-world");
//!assert_eq!(slugify!("the hello world", separator = ".", max_length = 10), "the.hello");
//!assert_eq!(slugify!("the hello world", stop_words = "the", max_length = 5), "hello");
//!assert_eq!(slugify!("the hello world", stop_words = "the", separator = "-", max_length = 20), "hello-world");
//! # }
//!```
//!
extern crate unidecode;
use unidecode::unidecode;
#[macro_export]
macro_rules! slugify {
($text:expr) => (
{
slugify($text, "", "-", None)
}
);
($text:expr, stop_words=$stopwords:expr) => (
{
slugify($text, $stopwords, "-", None)
}
);
($text:expr, separator=$sep:expr) => (
{
slugify($text, "", $sep, None)
}
);
($text:expr, max_length=$len:expr) => (
{
slugify($text, "", "-", Some($len))
}
);
($text:expr, stop_words=$stopwords:expr, separator=$sep:expr) => (
{
slugify($text, $stopwords, $sep, None)
}
);
($text:expr, stop_words=$stopwords:expr, max_length=$len:expr) => (
{
slugify($text, $stopwords, "-", Some($len))
}
);
($text:expr, separator=$sep:expr, max_length=$len:expr) => (
{
slugify($text, "", $sep, Some($len))
}
);
($text:expr, stop_words=$stopwords:expr, separator=$sep:expr, max_length=$len:expr) => (
{
slugify($text, $stopwords, $sep, Some($len))
}
);
}
pub fn slugify(string: &str, stop_words: &str, sep: &str, max_length: Option<usize>) -> String {
let char_vec: Vec<char> = sep.chars().collect();
let mut string: String = unidecode(string.into())
.to_lowercase()
.trim()
.trim_matches(char_vec[0])
.replace(' ', &sep.to_string());
// remove stop words
for word in stop_words.split(",") {
if !word.is_empty() {
string = string.replace(word, &sep.to_string());
}
}
let mut slug = Vec::with_capacity(string.len());
let mut is_sep = true;
for x in string.chars() {
match x {
'a'...'z' | '0'...'9' => {
is_sep = false;
slug.push(x as u8);
}
_ => {
if !is_sep {
is_sep = true;
slug.push(char_vec[0] as u8);
} else {
}
}
}
}
if slug.last() == Some(&(char_vec[0] as u8)) {
slug.pop();
}
let mut s = String::from_utf8(slug).unwrap();
match max_length {
Some(x) => {
s.truncate(x);
s = s.trim_right_matches(char_vec[0]).to_string();
}
None => {}
}
s
}
#[cfg(test)]
mod tests {
use slugify;
#[test]
fn basic() {
assert_eq!(slugify("hello world", "", "-", None), "hello-world");
assert_eq!(slugify("hello world-", "", "-", None), "hello-world");
assert_eq!(slugify("hello world ", "", "-", None), "hello-world");
}
#[test]
fn test_email() {
assert_eq!(slugify!("alice@bob.com"), "alice-bob-com");
}
#[test]
fn test_starts_with_number() {
assert_eq!(slugify!("10 amazing secrets"), "10-amazing-secrets");
}
#[test]
fn test_contains_numbers() {
assert_eq!(slugify!("the 101 dalmatians"), "the-101-dalmatians");
}
#[test]
fn test_ends_with_number() {
assert_eq!(slugify!("lucky number 7"), "lucky-number-7");
}
#[test]
fn test_numbers_only() {
assert_eq!(slugify!("101"), "101");
}
#[test]
fn test_numbers_and_symbols() {
assert_eq!(slugify!("1000 reasons you are #1"),
"1000-reasons-you-are-1");
}
#[test]
fn test_stop_words() {
assert_eq!(slugify("hello world", "world", "-", None), "hello");
assert_eq!(slugify!("hello world", stop_words = "world"), "hello");
}
#[test]
fn test_differently_cased_stopword_match() {
assert_eq!(slugify("Foo A FOO B foo C", "foo", "-", None), "a-b-c");
}
#[test]
fn test_multiple_stop_words() {
assert_eq!(slugify("the quick brown fox jumps over the lazy dog",
"the",
"-",
None),
"quick-brown-fox-jumps-over-lazy-dog");
assert_eq!(slugify("the quick brown fox jumps over the lazy dog",
"the,fox",
"-",
None),
"quick-brown-jumps-over-lazy-dog");
assert_eq!(slugify!("the quick brown fox jumps over the lazy dog",
stop_words = "the,fox"),
"quick-brown-jumps-over-lazy-dog");
}
#[test]
fn test_stopwords_with_different_separator() {
assert_eq!(slugify("the quick brown fox jumps over the lazy dog",
"the",
" ",
None),
"quick brown fox jumps over lazy dog");
assert_eq!(slugify!("the quick brown fox jumps over the lazy dog",
stop_words = "the",
separator = " "),
"quick brown fox jumps over lazy dog");
}
#[test]
fn test_separator() {
assert_eq!(slugify("hello world", "", ".", None), "hello.world");
assert_eq!(slugify("hello world", "", "_", None), "hello_world");
assert_eq!(slugify!("hello world", separator = "_"), "hello_world");
}
#[test]
fn test_phonetic_conversion() {
assert_eq!(slugify("影師嗎", "", "-", None), "ying-shi-ma");
}
#[test]
fn test_accented_text() {
assert_eq!(slugify("Æúű--cool?", "", "-", None), "aeuu-cool");
assert_eq!(slugify("Nín hǎo. Wǒ shì zhōng guó rén", "", "-", None),
"nin-hao-wo-shi-zhong-guo-ren");
}
#[test]
fn test_accented_text_non_word_chars() {
assert_eq!(slugify!("jaja---lol-méméméoo--a"), "jaja-lol-mememeoo-a");
}
#[test]
fn test_cyrillic_text() {
assert_eq!(slugify!("Компьютер"), "komp-iuter");
}
#[test]
fn test_macro() {
assert_eq!(slugify!("Компьютер"), "komp-iuter");
assert_eq!(slugify!("hello world", separator = "-"), "hello-world");
assert_eq!(slugify!("hello world", separator = " "), "hello world");
assert_eq!(slugify!("hello world", max_length = 5), "hello");
assert_eq!(slugify!("hello world", max_length = 6), "hello");
assert_eq!(slugify!("hello world", separator = " ", max_length = 8),
"hello wo");
assert_eq!(slugify!("hello world", separator = "x", max_length = 8),
"helloxwo");
assert_eq!(slugify!("the hello world", stop_words = "the", separator = "-"),
"hello-world");
assert_eq!(slugify!("the hello world", stop_words = "the", max_length = 5),
"hello");
assert_eq!(slugify!("the hello world",
stop_words = "the",
separator = "-",
max_length = 10),
"hello-worl");
assert_eq!(slugify!("the hello world",
stop_words = "the",
separator = "-",
max_length = 20),
"hello-world");
}
}