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
//! # extract-words
//!
//! Extracts words from text without allocation
//!
//! ## Examples
//!
//! Iteration through words, discarding punctuation
//! ```
//! # use extract_words::extract_words;
//! let mut words = extract_words("¿Cómo estás?");
//! assert_eq!(words.next().unwrap(), "Cómo");
//! assert_eq!(words.next().unwrap(), "estás");
//! assert!(words.next().is_none());
//! ```
//!
//! Iteration through all entries
//! ```
//! # use extract_words::{Entries, Entry};
//! let mut entries = Entries::new("Bien :)");
//! assert_eq!(entries.next().unwrap(), Entry::Word("Bien"));
//! assert_eq!(entries.next().unwrap(), Entry::Other(" :)"));
//! assert!(entries.next().is_none());
//! ```
#![warn(clippy::all, missing_docs, nonstandard_style, future_incompatible)]
/// Extracts words from the text discarding punctuation
pub fn extract_words(text: &str) -> impl Iterator<Item = &str> {
Entries::new(text).filter_map(|e| match e {
Entry::Word(s) => Some(s),
Entry::Other(_) => None,
})
}
/// An iterator over text entries
pub struct Entries<'a> {
text: &'a str,
char_indices: std::str::CharIndices<'a>,
cur_entry: CurEntry,
}
/// Text entry
#[derive(Debug, PartialEq)]
pub enum Entry<'a> {
/// Punctuation, spaces, etc
Other(&'a str),
/// Word
Word(&'a str),
}
enum CurEntry {
None,
Other(usize),
Word(usize),
}
impl<'a> Entries<'a> {
/// Creates an iterator over the text entries
pub fn new(text: &'a str) -> Self {
Entries {
text,
char_indices: text.char_indices(),
cur_entry: CurEntry::None,
}
}
}
impl<'a> Iterator for Entries<'a> {
type Item = Entry<'a>;
fn next(&mut self) -> Option<Self::Item> {
for (i, c) in self.char_indices.by_ref() {
if c.is_alphanumeric() {
match self.cur_entry {
CurEntry::None => self.cur_entry = CurEntry::Word(i),
CurEntry::Other(start) => {
self.cur_entry = CurEntry::Word(i);
return Some(Entry::Other(&self.text[start..i]));
}
CurEntry::Word(_) => (),
}
} else {
match self.cur_entry {
CurEntry::None => self.cur_entry = CurEntry::Other(i),
CurEntry::Other(_) => (),
CurEntry::Word(start) => {
self.cur_entry = CurEntry::Other(i);
return Some(Entry::Word(&self.text[start..i]));
}
}
}
}
match self.cur_entry {
CurEntry::None => None,
CurEntry::Other(start) => {
self.cur_entry = CurEntry::None;
if start < self.text.len() {
Some(Entry::Other(&self.text[start..]))
} else {
None
}
}
CurEntry::Word(start) => {
self.cur_entry = CurEntry::None;
if start < self.text.len() {
Some(Entry::Word(&self.text[start..]))
} else {
None
}
}
}
}
}
impl<'a> AsRef<str> for Entry<'a> {
fn as_ref(&self) -> &str {
match self {
Entry::Other(s) => s,
Entry::Word(s) => s,
}
}
}
#[cfg(test)]
mod tests {
use super::extract_words;
fn extract_vec(text: &str) -> Vec<&str> {
extract_words(text).collect()
}
#[test]
fn test_empty_string() {
assert!(extract_vec("").is_empty());
}
#[test]
fn test_punctuation_only() {
assert!(extract_vec(".,!?-").is_empty());
}
#[test]
fn test_mixed_input() {
assert_eq!(
extract_vec("Hola,mundo! ¿Cómo estás?"),
["Hola", "mundo", "Cómo", "estás"]
);
}
#[test]
fn test_multiple_delimiters() {
assert_eq!(extract_vec("Hola, mundo!¿ .. !¿á"), ["Hola", "mundo", "á"]);
}
}